Method and system for setting difficulty level of exercise program using large language model

Abstract

A method for setting a difficulty level of an exercise program using a large language model according to the present invention may comprise the steps of: providing, to an electronic device, at least one questionnaire related to a user's indication; and receiving response data to the questionnaire from the electronic device.

Description

Method and System for Setting Difficulty Levels in Exercise Programs Using Large Language Models

[0001] The present invention relates to a method and system for setting the difficulty level of an exercise program using a large language model. This research was conducted with funding from the Ministry of Health and Welfare and supported by the Health and Medical Technology Research and Development Project of the Korea Health Industry Development Institute. (Project Unique Number: 2460000121, Project Number: RS-2024-00401350, Ministry: Ministry of Health and Welfare, Project Management (Specialized) Agency: Korea Health Industry Development Institute, Research Project Name: Translational Research Linked to Clinical Field Demand, Research Project Title: Development and Clinical Validation of a Comprehensive Digital Healthcare Service for Personalized Self-Rehabilitation After Rotator Cuff Reconstruction and Shoulder Arthroplasty, Project Executing Agency: Sungkyunkwan University Industry-Academic Cooperation Foundation, Research Period: 2024-04-01~2026-12-31).

[0002] With the rapid advancement of artificial intelligence (AI) technology in recent years, generative AI models capable of natural conversation with humans (e.g., ChatGPT) have emerged. In particular, Large Language Models (LLMs), unlike existing dictionary-rule-based chatbots, provide conversational quality similar to humans based on the ability to understand various contexts and generate natural language, and are being rapidly adopted in various industrial fields such as medical, education, and healthcare.

[0003] Furthermore, alongside the advancement of artificial intelligence (AI) technology, its application in the medical industry is rapidly expanding. For example, there is growing interest in AI technology that utilizes large language models to provide personalized, non-face-to-face rehabilitation to patients requiring consistent management and rehabilitation during treatment. In this medical and healthcare field, large language models can be effectively utilized for the management and rehabilitation of musculoskeletal disorders.

[0004] Musculoskeletal disorders refer to pain or injury occurring in the musculoskeletal system, including muscles, nerves, tendons, ligaments, bones, and surrounding tissues. As a general principle, the treatment of musculoskeletal disorders should begin with less invasive procedures; non-pharmacological conservative treatments (e.g., exercise therapy and education, cognitive therapy, or relaxation therapy) should be implemented first, followed by pharmacological treatment and surgical treatment in sequence. Treatment guidelines strongly recommend non-pharmacological conservative treatment for musculoskeletal disorders, and active research on methods for implementing such treatments is being conducted, primarily in the United States and Europe. However, since continuous treatment and rehabilitation are crucial for non-pharmacological conservative treatment, the requirement for patients to visit the hospital frequently poses a significant burden.

[0005] Consequently, interest in services providing non-face-to-face rehabilitation is increasing. In non-face-to-face rehabilitation, it is essential to deliver an exercise program accompanied by setting the difficulty level of rehabilitation exercises while considering the user's age, gender, occupation, level of daily living activities, current primary diagnosis and history of related diseases, past medical history and surgical history, medication history, current physical functional status (muscle strength, range of motion, balance, presence and severity of pain, etc.), cardiorespiratory function, neurological status, mental / psychological state, lifestyle habits (smoking, drinking, dietary habits, exercise experience, etc.), residential and exercise environments (use of mobility aids, exercise equipment owned, etc.), specific details (skin condition, condition of surgical site, etc.), and user goals. If exercise difficulty is set uniformly without considering the user's functional level or medical history (e.g., arthritis, rotator cuff injury, surgical records, etc.), exercises of inappropriate difficulty may be delivered due to a failure to account for differences in diseases, functional levels, and age. This can increase the risk of cardiorespiratory strain, musculoskeletal damage, and re-injury, which may lead to the worsening of pain or functional decline.

[0006] Furthermore, in non-face-to-face rehabilitation therapy, if the difficulty level is inappropriate, the effectiveness of the rehabilitation may be diminished. For example, if an exercise program of easy difficulty is conducted, the body may not receive appropriate stimulation (exercise threshold), failing to induce physical changes; consequently, necessary recovery may not occur, or achieving goals may take longer. Additionally, if the exercise feels boring or meaningless, user motivation may decrease, potentially leading to a higher dropout rate from the program.

[0007] On the other hand, during remote rehabilitation, if an exercise program is presented that includes movements at an excessive level compared to the patient's current ability, the patient may be unable to perform the movements properly or may avoid exercise due to pain. Such repeated experiences of failure lead to the discontinuation of rehabilitation, increasing the dropout rate and acting as a factor that hinders long-term rehabilitation effectiveness. To address these issues with remote rehabilitation and to ensure consistent management and rehabilitation for specific conditions, there is a need to customize the difficulty level of provided exercise programs to suit the user.

[0008] The present invention is intended to provide a method and system for setting the difficulty level of an exercise program using a large language model capable of generating an exercise program set to a user-customized difficulty level.

[0009] More specifically, the present invention aims to provide a method and system for setting the difficulty level of an exercise program using a large language model, which can evaluate exercise performance ability by providing different evaluation items based on user response data and history information regarding a survey provided to an electronic device using a large language model.

[0010] Furthermore, the present invention aims to provide a method and system for setting the difficulty level of an exercise program using a large language model, which can set the difficulty level of the exercise program through a large language model based on user response data and an evaluation of exercise performance ability.

[0011] Furthermore, the present invention aims to provide a method and system for setting the difficulty level of an exercise program using a large language model, which can generate an exercise program based on a set difficulty level using a large language model.

[0012] To solve the problem described above, the present invention proposes a method that utilizes a large language model to interact with a user remotely and to set the difficulty level of an exercise program for the user's indication to a user-customized difficulty level. The method for setting the difficulty level of an exercise program using a large language model according to the present invention may include the steps of: providing at least one survey related to the user's indication to an electronic device; receiving response data for the survey from the electronic device; setting evaluation criteria for evaluating the user's exercise performance ability based on at least one of the response data and the user's history information; specifying at least one evaluation item among a plurality of evaluation items related to the evaluation of exercise performance ability based on the evaluation criteria; inputting the user's exercise data into a pre-trained motion evaluation model to evaluate the user's exercise performance ability regarding the at least one evaluation item; generating a prompt to be input into a large language model using the response data and the evaluation result regarding the exercise performance ability; inputting the prompt into the large language model to obtain an exercise difficulty level related to the user's indication from the large language model; and generating an exercise program related to the user's indication based on the obtained exercise difficulty level.

[0013] Furthermore, the evaluation criteria are set differently based on at least one of the response data and history information for the survey, and the step of specifying the at least one evaluation item may include the step of specifying an evaluation restriction item that satisfies an unsuitability condition among a plurality of evaluation items related to the exercise performance evaluation based on the differently set evaluation criteria, and the step of specifying the at least one evaluation item among the plurality of evaluation items based on the specified evaluation restriction item.

[0014] Furthermore, the above evaluation limitation items may be specified based on at least one of the degree of pain in the user's pain area and medical records included in at least one of the response data to the above survey and the above history information.

[0015] Furthermore, the above-mentioned non-compliance condition may be a condition specifying the evaluation restriction item that is excluded from the user's exercise performance evaluation based on the degree of pain and a restriction standard previously set in at least one of the medical records.

[0016] Furthermore, the step of evaluating the exercise performance ability of the user may include receiving the user’s exercise data corresponding to the specified at least one evaluation item from the electronic device, analyzing at least one of the user’s static posture, joint range of motion, balance ability, and muscle strength using the previously learned motion evaluation model or through response data, and generating an exercise performance ability evaluation result for the at least one evaluation item.

[0017] Furthermore, the above exercise program is configured to include a plurality of exercise modules, each of the plurality of exercise modules is matched to a different type of exercise and may include at least one exercise motion content related to the type of exercise matched to each exercise module.

[0018] Furthermore, the step of acquiring the exercise difficulty level can acquire a specific exercise difficulty level among multiple exercise difficulty levels through the large language model into which the prompt is input, based on a pre-set difficulty setting standard.

[0019] Furthermore, the above at least one exercise motion content includes motion difficulty information, and each of the plurality of exercise modules may include at least one specific exercise motion content that satisfies a preset motion difficulty condition based on the specific exercise difficulty.

[0020] The above-mentioned difficulty setting criteria include multiple different setting criteria, and the specific exercise difficulty can satisfy all of the multiple different setting criteria.

[0021] Furthermore, the step of generating the exercise program may include the step of extracting at least one specific exercise movement content satisfying the preset exercise difficulty condition using the specific exercise difficulty and the prompt, and the step of generating the exercise program composed of the plurality of exercise modules based on the exercise type matched to the extracted at least one specific exercise movement content through the large language model.

[0022] Furthermore, the above-mentioned at least one survey may include a basic survey containing questions related to the user's indications and at least one additional survey provided differently depending on the user's response to the basic survey.

[0023] Furthermore, each of the above basic survey and the above additional survey may include at least one of a multiple-choice survey consisting of at least one question item related to the user's indication and a plurality of selection items corresponding to each of a plurality of different responses to the question item, and an interactive survey capable of receiving natural language input from the electronic device in relation to the user's indication.

[0024] Furthermore, the step of receiving response data for the above survey may include the step of receiving response data for the selection type survey from the electronic device, which includes a response matched to an item selected by user input among the plurality of selection items, and the step of processing the natural language input entered into the electronic device as input to the large language model to receive response data for the conversational survey from the large language model.

[0025] Meanwhile, the difficulty setting system of an exercise program using a large language model according to the present invention includes a control unit that provides at least one survey related to a user's indication to an electronic device, and a communication unit that receives response data for the survey from the electronic device.

[0026] The control unit sets an evaluation criterion for evaluating the user's exercise performance ability based on at least one of the response data and the user's history information, specifies at least one evaluation item among a plurality of evaluation items related to the evaluation of exercise performance ability based on the evaluation criterion, inputs the user's exercise data into a pre-trained motion evaluation model to evaluate the user's exercise performance ability for the at least one evaluation item, generates a prompt to be input into a large language model using the response data and the evaluation result of the exercise performance ability, inputs the prompt into the large language model to obtain an exercise difficulty related to the user's indication from the large language model, and can generate an exercise program related to the user's indication based on the obtained exercise difficulty.

[0027] Meanwhile, the program is executed by one or more processes in an electronic device and is stored on a computer-readable recording medium, and the program may include instructions for performing the steps of: providing at least one survey related to a user's indication to the electronic device; receiving response data for the survey from the electronic device; setting evaluation criteria for evaluating the user's exercise performance ability based on at least one of the response data and the user's history information; specifying at least one evaluation item among a plurality of evaluation items related to the evaluation of exercise performance ability based on the evaluation criteria; inputting the user's exercise data into a pre-trained motion evaluation model to evaluate the user's exercise performance ability for the at least one evaluation item; generating a prompt to be input into a large language model using the response data and the evaluation result for the exercise performance ability; inputting the prompt into the large language model to obtain an exercise difficulty related to the user's indication from the large language model; and generating an exercise program related to the user's indication based on the obtained exercise difficulty.

[0028] The method and system for setting the difficulty level of an exercise program using a large language model according to the present invention can perform a user-customized exercise performance evaluation by applying different evaluation items according to the user's current state based on response data and history information to a user's survey. Through this, the user's current exercise performance ability can be precisely evaluated to generate an exercise program of a difficulty level suitable for the user's rehabilitation.

[0029] Furthermore, the method and system for setting the difficulty level of an exercise program using a large language model according to the present invention can minimize the risk of injury due to overload and provide a safe evaluation environment that does not strain the user by considering the user's medical records (or treatment records) included in the history information and adjusting exercise performance evaluation items based on medical information such as existing medical history or surgical records.

[0030] Furthermore, by generating and providing an exercise program to a user with a user-customized difficulty level using a large language model according to the present invention, the risk of pain aggravation and withdrawal from the exercise program during exercise performance can be minimized, long-term rehabilitation continuity can be secured, and functional recovery for returning to actual daily life or work can be aided by providing an appropriate exercise threshold to the user's body to help improve physical function.

[0031] FIG. 1 is a conceptual diagram illustrating a difficulty setting system for an exercise program using a large language model according to the present invention.

[0032] FIG. 2 is a flowchart for explaining, in general, a method for setting the difficulty level of an exercise program using a large language model according to the present invention.

[0033] FIGS. 3a to 3c are conceptual diagrams for explaining the process of conducting a survey according to the present invention.

[0034] FIGS. 4a and FIGS. 4b are conceptual diagrams for explaining user-customized exercise performance evaluation criteria and exercise performance evaluation items according to the present invention.

[0035] FIGS. 5a and FIGS. 5b are conceptual diagrams illustrating a user-customized exercise performance evaluation process according to the present invention.

[0036] FIGS. 6a and FIGS. 6b are conceptual diagrams for explaining the process of obtaining the difficulty level of an exercise program using a large language model according to the present invention.

[0037] FIG. 7 is a conceptual diagram illustrating the process of generating a user-customized exercise program with a difficulty level according to the present invention and providing it to an electronic device.

[0038] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Identical or similar components are assigned the same reference number regardless of the drawing symbols, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification and do not have distinct meanings or roles in themselves. Furthermore, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of related prior art could obscure the essence of the embodiments disclosed in this specification, such detailed description will be omitted. Additionally, the attached drawings are intended only to facilitate understanding of the embodiments disclosed in this specification; the technical concept disclosed in this specification is not limited by the attached drawings, and it should be understood that they include all modifications, equivalents, and substitutions that fall within the spirit and technical scope of the present invention.

[0039] Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. These terms are used solely for the purpose of distinguishing one component from another.

[0040] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0041] A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0042] In this application, terms such as “comprising” or “having” are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0043] The present invention relates to a method and system for setting the difficulty level (or exercise difficulty) of an exercise program using a large language model. More specifically, the present invention relates to a method and system capable of evaluating a user's exercise performance ability based on different evaluation criteria according to the user's current state, and setting the difficulty level (or exercise difficulty) of an exercise program to be provided to the user through a large language model based on the results of the exercise performance evaluation. Here, a “Large Language Model” may refer to an artificial intelligence model capable of understanding and generating natural language by learning a vast amount of data.

[0044] The “exercise program” according to the present invention may refer to an exercise plan provided to an electronic device in relation to the user’s indication. Here, “indication” refers to a symptom or clinical situation requiring specific treatment or examination, and may be understood as the user’s disease or symptom. For example, in the present invention, if the user has an indication related to a specific body part (e.g., lower back (lumbar spine)), an exercise program for the rehabilitation of the user’s indication can be generated.

[0045] More specifically, an exercise program according to the present invention may be configured to include at least one exercise module. Here, an “exercise module” may refer to a constituent unit of an exercise program that includes at least one exercise motion content. In this case, the “exercise motion content” may include various information such as a name for a specific exercise motion, exercise time information, exercise difficulty information, exercise type information, exercise body part information, and exercise posture information.

[0046] In the exercise program according to the present invention, different exercise difficulty levels may be set according to the current state (or situation) of each of the plurality of users. Here, depending on the “exercise difficulty level of the exercise program,” the difficulty level of the exercise motion content included in the exercise module constituting the exercise program may differ. Meanwhile, the “exercise motion” described in the present invention refers to a gesture (movement) performed during the process of performing exercise, and may be used interchangeably with terms such as “movement,” “action,” “movement,” and “gesture.”

[0047] The present invention can perform an exercise performance evaluation considering the user's current pain state by utilizing response data to a survey provided on an electronic device and historical data including the user's medical records (or treatment records). Furthermore, through the exercise performance evaluation considering the user's current state, the present invention can precisely evaluate the user's exercise performance and generate and provide an exercise program set to a user-customized difficulty level.

[0048] For convenience of explanation, the present invention focuses on “indications related to musculoskeletal disorders,” but is not necessarily limited thereto. As an example, the exercise program described in the present invention may be for the treatment of users requiring rehabilitation treatment for musculoskeletal disorders and users suffering from various diseases (e.g., cancer, diabetes, hypertension, etc.).

[0049] Furthermore, the present invention may generate exercise programs necessary for health promotion in daily life, rather than rehabilitation exercises for therapeutic purposes related to the user's indications. For example, the exercise according to the present invention is not limited to any specific purpose and may be an exercise performed for various purposes, such as rehabilitation exercises, fitness exercises, ball sports, or dance exercises, for therapeutic, health promotion, or cosmetic purposes.

[0050] Furthermore, the exercise program according to the present invention may refer to a set of exercise modules for various exercises, such as rehabilitation exercises, fitness exercises, ball sports, and dance exercises, for various purposes including therapeutic, health promotion, and beauty purposes, and may be understood not to be limited to a specific category of exercise. That is, there is no limitation on the type of exercise according to the present invention, nor is there a limitation on the location of the exercise, such as indoor or outdoor exercise.

[0051] In the foregoing, a method for setting the difficulty level of an exercise program using a large language model according to the present invention has been generally described, and this can be implemented by a system for setting the difficulty level of an exercise program using a large language model described below. Below, with reference to FIG. 1, a system for setting the difficulty level of an exercise program using a large language model according to the present invention will be described in detail. FIG. 1 is a conceptual diagram for explaining a system for setting the difficulty level of an exercise program using a large language model according to the present invention.

[0052] As illustrated in FIG. 1, the difficulty setting system for an exercise program using a large language model according to the present invention (hereinafter referred to as the “difficulty setting system,” 100) may include at least one of a communication unit (110), a storage unit (120), and a control unit (130). At this time, the difficulty setting system (100) according to the present invention is not limited to the components described above and may further include components that perform the same or similar roles as the functions described in the specification. Meanwhile, the difficulty setting system (100) according to the present invention may be implemented as an application or software. The difficulty setting system (100) implemented as software in this manner may be downloaded through a program (e.g., Play Store) that allows the application to be downloaded on an electronic device (10), or implemented through an initial installation program on an electronic device (10). In this case, the communication unit (110), the storage unit (120), and the control unit (130) according to the present invention may be utilized as components of the electronic device (10). In the present invention, the electronic device (10) can be understood to mean an application installed on the electronic device (10). Such an application (or software) can be understood as a component of the difficulty setting system (100) according to the present invention.

[0053] In the present invention, the electronic device (10) may also be named a 'mobile terminal' or 'electronic device', and the electronic device (10) described in this specification may include a mobile phone, a smartphone, a smart TV, a laptop computer, a digital broadcasting terminal, a PDA (personal digital assistants), a PMP (portable multimedia player), a navigation device, a slate PC, a tablet PC, an ultrabook, a wearable device (e.g., a smartwatch, a smart glass, a head-mounted display), etc.

[0054] More specifically, the electronic device (10) according to the present invention is not limited to an electronic device with an application activated, but may refer to an electronic device connected to an electronic device with an application activated. As an example, based on the fact that the electronic device (10) with an application activated according to the present invention is a smartphone, the electronic device (10) may refer to a smart TV connected to the smartphone. That is, the electronic device (10) according to the present invention may refer to at least one of an electronic device owned by a user (or logged in with a user account), an electronic device owned by a medical professional (or logged in with a medical professional account), and an electronic device used in common.

[0055] Meanwhile, the difficulty setting system (100) may exist inside a server (hereinafter referred to as the server) established to perform a specific purpose (e.g., setting the difficulty of an exercise program and creating an exercise program), or it may exist as a separate device from the server. When the difficulty setting system (100) exists inside the server, the difficulty setting system (100) according to the present invention may set the difficulty of an exercise program and create an exercise program corresponding to the set user-customized difficulty through at least one component among the communication unit (110), storage unit (120), and control unit (130) located inside the server, or through a module that performs a function similar to each of the above components. In this case, the application may provide the exercise program to the electronic device (10) on which the application is installed through communication with the server. Furthermore, the difficulty setting system (100) according to the present invention may provide the exercise program according to the present invention to the electronic device (10) by linking with a plurality of different external servers.

[0056] A user (or patient, U) and a medical staff member (or doctor) according to the present invention may possess an account registered in the difficulty setting system (100) according to the present invention. For convenience of explanation, the account of a user (or patient) in this specification is referred to as a "user account (or patient account)." The "account" described above may be created through a page linked to the difficulty setting system (100). Alternatively, the "account" may be created on at least one other server (e.g., a medical staff server) linked to the difficulty setting system (100) according to the present invention. Accordingly, in this specification, without distinguishing the server where the account was issued, all accounts based on the difficulty setting system (100) according to the present invention are referred to as "accounts already registered in the difficulty setting system (100) according to the present invention."

[0057] Furthermore, a user (U, or patient) according to the present invention may receive an exercise program with a user-customized difficulty level set in relation to the user's (U) indications through an application or webpage provided by the difficulty setting system (100) according to the present invention.

[0058] Meanwhile, the medical staff (D) may possess a medical staff account already registered in the difficulty setting system (100) according to the present invention. In this specification, an electronic device logged in with a medical staff account is described as an electronic device (10) owned by the medical staff. Furthermore, the “medical staff” described in the present invention refers to a person employed at a medical institution (e.g., a hospital) and may include, for example, at least one of a doctor, a nurse, or a physical therapist. For convenience of explanation, the present invention describes doctors and physical therapists as examples of medical staff. However, medical staff are not limited thereto, and any user employed at a medical institution to set the difficulty level of a user-customized exercise program and to create an exercise program corresponding to the set difficulty level may be considered medical staff according to the present invention.

[0059] The difficulty setting system (100) according to the present invention can collect sensing information including at least one of voice data and video data based on a microphone, camera, and sensor unit equipped in an electronic device (10). Here, the sensor unit may include at least one sensor among an infrared sensor, a LiDAR sensor, an accelerometer, an illuminance sensor, a proximity sensor, a position sensor, a face recognition sensor, an iris scanner, a heart rate sensor, a touch sensor, and a pressure sensor.

[0060] According to the present invention, the communication unit (110) may be connected to an electronic device (10), an LLM server (140), a central server, a device, and at least one network via a wireless or wired network, and may be configured to receive or transmit overall data and information necessary for the operation of the attitude estimation system (100) according to the present invention.

[0061] Specifically, the communication unit (110) can transmit at least one survey related to the user's indication to the electronic device (10). For example, the communication unit (110) can transmit at least one survey related to the user's indication to the electronic device (10) in which at least one of the user account and medical staff account is logged. Furthermore, the communication unit (110) can receive response data (or explanatory response data) for at least one survey provided to the electronic device (10). Here, “receiving response data” may mean receiving an input signal (or selection signal) corresponding to a user input entered through the electronic device (10).

[0062] The communication unit (110) can receive history information from the database (200). Furthermore, the communication unit (110) can receive exercise motion content stored in a database (or DB, 200) that includes an exercise program DB. Additionally, the communication unit (110) can receive user exercise data from the electronic device (10). Here, “exercise data” may refer to at least one of an image and a video of a user’s exercise motion captured (or sensed) by at least one of the camera and sensor unit equipped in the electronic device (10).

[0063] The communication unit (110) may include at least one communication module capable of wireless communication and wired communication between the attitude estimation system (100) and the communication target. Additionally, the communication unit (110) may include a communication module that connects the difficulty setting system (100) to at least one network.

[0064] Meanwhile, the communication unit (110) can support various communication methods depending on the communication standard of the communicating device. For example, the communication unit (110) may be configured to perform communication using at least one of the following technologies: WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G (5th Generation Mobile Telecommunication), Bluetooth (Bluetooth™ Frequency Identification), Infrared Communication (Infrared Data Association; IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus).

[0065] Next, the storage unit (120) may be configured to store various information related to the present invention. In the present invention, the storage unit (120) may be provided in the difficulty setting system (100) itself, or alternatively, at least a part of the storage unit (120) may mean a database (Database: DB, 200).

[0066] The storage unit (120) may include one or more non-transient computer-readable storage media that can be read and / or accessed by at least one processor. One or more computer-readable storage media may include volatile and / or non-volatile storage components such as optical, magnetic, organic, or other memory or disk storage devices. In some examples, the storage unit (120) may be implemented using a single physical device (e.g., one optical, magnetic, organic, or other memory or disk storage device), whereas in other examples, the storage unit (120) may be implemented using multiple physical devices. The storage unit (120) may include computer-readable instructions and additional data.

[0067] The storage unit (120) may include a storage space necessary to perform at least some of the methods and techniques described in this specification and / or at least some of the functions of the device and network. That is, the storage unit (120) is sufficient as a space where information necessary to set the exercise difficulty of an exercise program according to the present invention and to generate an exercise program corresponding to the set exercise difficulty is stored, and the storage unit (120) can be understood as not being restricted by physical space.

[0068] Data and commands necessary for the operation of the difficulty setting system (100) according to the present invention may be stored in the storage unit (120). More specifically, data and commands necessary for the operation of the motion evaluation model (132) may be stored in the storage unit (120). Here, the motion evaluation model (132) may refer to an artificial intelligence model that analyzes the user's exercise motion performed according to user-customized exercise performance evaluation items and performs an evaluation of the exercise motion.

[0069] For example, the motion evaluation model (132) of the present invention is a posture estimation model learned using a learning data set containing position information for joint points, and can estimate the exercise posture of a user (U) from an image of a user's exercise motion received from an electronic device (10). Here, "joint point" may refer to a plurality of joints of the user (U) (or a part of the user (U)'s body including joints). And, "key point" may refer to an area corresponding to each of the plurality of joint points of the user (U) in the exercise motion image.

[0070] The storage unit (120) may store user authentication information included in user account information. Here, “user authentication information” may refer to information used in a user authentication process performed to log in to a user account on an electronic device. As an example, user authentication information may be various, such as i) ID, ii) password, iii) password pattern, iv) user’s fingerprint authentication information, v) face authentication information, vi) voice authentication information, vii) iris authentication information, viii) vein authentication information, etc., set by the user. Additionally, the storage unit (120) may store at least one of an exercise video and an exercise description corresponding to each exercise movement.

[0071] Meanwhile, the database (DB, 200) may be configured to store various information related to providing a user-customized exercise program. Specifically, the database (200) may store exercise movement content (e.g., exercise name, number of exercises, timing of exercises, difficulty of exercises, etc.) corresponding to each of multiple pain sites related to the indication (e.g., shoulder, elbow, wrist & hand, hip & pelvis, knee, ankle & foot, neck, back, waist, abdomen, etc.). Furthermore, the database (200) may store at least one of an exercise video and an exercise description corresponding to each exercise movement content.

[0072] Additionally, the database (200) may store history information for each of multiple different users. For example, the database (200) may store history information including at least one of the user's i) name, ii) date of birth, iii) type of indication, iv) exercise history, v) medical records, vi) surgical records, vii) past medical history, viii) prescription information, ix) past response data, and x) exercise rehabilitation.

[0073] In the present invention, the storage unit (120) is described as existing separately from the database (200), but is not limited thereto, and the storage unit (120) may include the database (200).

[0074] Next, the control unit (130) may be configured to control the overall operation of the difficulty setting system (100) related to the present invention. The control unit (130) may include at least one of a prompt generation unit (131) and an operation evaluation model (132). Furthermore, the control unit (130) may process signals, data, information, etc. that are input or output through the components described above, or provide or process appropriate information and functions to the user.

[0075] The control unit (130) can control the output of a service page for setting the difficulty level of an exercise program through a display unit (or touchscreen) provided in the electronic device (10). Such a service page may be output on the electronic device (10) through an application or web page installed on the electronic device (10). The service page may be a page linked to the difficulty setting system (100) according to the present invention and may be configured to be controlled by the difficulty setting system (100) according to the present invention.

[0076] Furthermore, if the service page is provided in the form of an application, the service page may be controlled by the CPU (Central processing unit) of the electronic device (10) on which the application is installed. In this case, the CPU of the electronic device (10) may set the difficulty level of an exercise program based on information provided by the difficulty setting system (100) according to the present invention, and generate an exercise program corresponding to the set difficulty level.

[0077] Meanwhile, the control unit (130) may provide at least one survey related to the user's indications on a service page provided to the electronic device (10). Furthermore, the control unit (130) may set evaluation criteria to evaluate the user's exercise performance ability using response data and history information regarding at least one survey received through the electronic device (10). At this time, the “evaluation criteria” may refer to a criterion for specifying at least one evaluation item among a plurality of evaluation items related to the evaluation of exercise performance ability, based on the user's current state based on the response data and history information.

[0078] Furthermore, the control unit (130) can evaluate the user's exercise performance ability according to at least one specified evaluation item using a previously learned motion evaluation model (132). More specifically, the control unit (130) can generate an exercise performance ability evaluation result by inputting the user's exercise data, captured (or sensed) using at least one of the camera and sensor unit provided in the electronic device (10), into the motion evaluation model.

[0079] The control unit (130) can generate a prompt to be input to the LLM server (140) using at least one of the response data for at least one survey provided to the electronic device (10) and the result of an exercise performance evaluation. At this time, the LLM server (140) according to the present invention may include at least one large language model. For example, the LLM server (140) may include at least one large language model based on at least one of GPT (Generative Pre-trained Transformer), T5 (Text-to-Text Transfer Transformer), Vision-Language Models (e.g., CLIP, Flamingo), Multimodal Generative Models (GPT-4 Multimodal, PaLM-E), BERT (Bidirectional Encoder Representations from Transformers), and LaMDA (Language Model for Dialogue Applications).

[0080] In the present invention, the LLM server (140) is described as existing separately from the difficulty setting system (100), but is not limited thereto, and the difficulty setting system (100) may be configured to include the LLM server (140). That is, the difficulty setting system (100) and the LLM server (140) according to the present invention may exist separately, or the LLM server (140) may be included in the difficulty setting system (100). For convenience of explanation, the LLM server (140) and the large language model are used interchangeably below, and the use of the large language model by the control unit (130) can be understood as using at least one large language model included in the LLM server (140).

[0081] Additionally, although the present invention describes the control unit (130) as including a prompt generation unit (131), it is not limited thereto, and the control unit (130) and the prompt generation unit (131) may exist separately. In this case, the control unit (130) can generate a prompt in conjunction with the prompt generation unit (131).

[0082] The control unit (130) according to the present invention can obtain a user-customized exercise difficulty corresponding to a prompt through a large language model (140). More specifically, the control unit (130) can obtain an exercise difficulty of an exercise program according to a pre-set difficulty setting standard by linking with the large language model (140), and can generate an exercise program corresponding to the obtained exercise difficulty. In the present invention, it is described that the control unit (130) obtains an exercise difficulty and generates an exercise program by linking with the large language model (140), but it is not limited thereto; the control unit (130) itself may specify an exercise difficulty and generate an exercise program by including the function of the large language model (140) or performing the same function. Therefore, in this specification, the control unit (130) obtaining an exercise difficulty and generating an exercise program and the large language model (140) generating an exercise difficulty and generating an exercise program may be expressed interchangeably.

[0083] Meanwhile, the difficulty setting system (100) may include one or more processors, and such processors may include one or more general-purpose processors and / or one or more special-purpose processors (e.g., digital signal processors, tensor processing units (TPUs), graphics processing units (GPUs), neural network processing units (NPUs), application integrated circuits, application semiconductors (ASICs), etc.). One or more processors may be configured to execute instructions, computer-readable instructions, and / or other instructions described herein that are stored (or included) in the storage unit (120). The difficulty setting system (100) may perform data processing described below in cooperation with memory and at least one processor. The processor may perform a series of operations and data processing using data and information stored in memory. Here, “memory” may be a component of the storage unit (120), and “processor” may be used interchangeably with the control unit (130).

[0084] In the above description, the difficulty setting system (100) of the present invention has been described, and it can be implemented based on the method for setting the difficulty of an exercise program using a large language model described below.

[0085] Hereinafter, with reference to FIG. 2 together with FIG. 3a to 3c, FIG. 4a, FIG. 4b, FIG. 5a, FIG. 5b, FIG. 6a, FIG. 6b, and FIG. 7, a method for setting the difficulty level of an exercise program using a large language model according to the present invention will be described in more detail. FIG. 2 is a flowchart for generally explaining the method for setting the difficulty level of an exercise program using a large language model according to the present invention, and FIG. 3a to 3c are conceptual diagrams for explaining the survey execution process according to the present invention. FIG. 4a and FIG. 4b are conceptual diagrams for explaining the user-customized exercise performance evaluation criteria and exercise performance evaluation items according to the present invention, and FIG. 5a and FIG. 5b are conceptual diagrams for explaining the user-customized exercise performance evaluation process according to the present invention. FIG. 6a and FIG. 6b are conceptual diagrams for explaining the process of obtaining the difficulty level of an exercise program using a large language model according to the present invention, and FIG. 7 is a conceptual diagram for explaining the process of generating an exercise program having a user-customized difficulty level and providing it to an electronic device according to the present invention.

[0086] In the present invention, a process of providing at least one questionnaire related to the user's indication to an electronic device may be carried out (S210, see FIG. 2).

[0087] As illustrated in FIG. 3(a), the control unit (130) may provide a basic survey (300) in relation to the user’s indications on a service page (1000) provided on an electronic device (10). Here, the “basic survey” may refer to a survey related to at least one of the user’s personal details, the pain area related to the user’s indications, and the degree of pain (or pain level). Specifically, the control unit (130) may receive user information (310) including at least one of the user’s gender, age, occupation, and underlying disease (or diagnosed disease) through the basic survey (300) provided on the service page (1000).

[0088] Furthermore, the control unit (130) can receive information on the body part with pain (or discomfort) in relation to the user's indication through a basic survey (300) provided on the service page (1000). Specifically, the control unit (130) can provide a pain area survey that allows the user to input the body part (or musculoskeletal part) with pain. The control unit (130) can provide the electronic device (10) with a survey that includes a selection type survey that allows the user to select the body part (or pain area) with pain in relation to the user's indication.

[0089] For example, the control unit (130) may provide the electronic device (10) with a plurality of body icons corresponding to each body part in the body diagram (320). Furthermore, the control unit (130) may provide guidance information (e.g., “Please select the area where you have pain or discomfort.”) to induce the user to select at least one body part. As an example, the control unit (130) may display a plurality of body icons corresponding to each of the multiple body parts (e.g., “neck (cervical spine), “shoulder,” “back (thoracic spine),” “waist (lumbar spine),” “elbow,” “wrist,” “knee,” “ankle,” etc.) in the body diagram (320) provided to the electronic device (10). The user (U) may identify at least one body part with pain through a selection survey that allows the user to select the painful area.

[0090] Specifically, the control unit (130) can identify a body part (e.g., waist (lumbar spine)) corresponding to a specific icon as the user's pain area based on user input (322) for a specific icon (321) among a plurality of body icons provided to the electronic device (10) by the user (U). At this time, the control unit (130) can identify a plurality of pain areas through a plurality of body icons, and in this case, can provide a pain area survey for additionally inputting the pain area with the most severe pain among the plurality of pain areas.

[0091] As illustrated in (c) of FIG. 3a, the control unit (130) may provide a basic survey (300) including a pain level survey that allows the user to input the pain level (or pain level, pain score) on a service page (1000) provided to the electronic device (10) when the pain area (or, the area with the most severe pain) is identified. At this time, the pain level survey may include a selection type survey that allows the user to input the pain level for the identified pain area.

[0092] Specifically, the control unit (130) may provide a selection item (324) that allows the user (U) to input the degree of pain regarding a specific pain area on the electronic device (10) through a pain area survey. Here, “degree of pain” may mean a score corresponding to the numerical value of pain subjectively felt by the user (U). For example, the degree of pain may mean at least one of the Numerical Rating Scale (NRS) and the Visual Analogue Scale (VAS), and may consist of numbers from 0 to 10. Specifically, the control unit (130) may provide a selection survey that includes a selection item (324) to express the degree of pain felt by the user (U) as a number.

[0093] The control unit (130) may provide a survey related to the user's indication in response to user input (325) regarding the degree of pain being applied to a selection item (324) where the user (U) can input the degree of pain. As illustrated in FIG. 3b (a), the control unit (130) may provide at least one of a selection survey (or selection survey item, 330) configured to allow the user (U) to directly select about the user's health condition based on the input of the degree of pain for a specific pain area, an interactive survey (340), and an additional survey (350) related to the specific pain area. Here, the “selection survey” may be composed of a question related to the user's indication and a plurality of selection items corresponding to each of a plurality of different responses to the question.

[0094] The storage unit (120) stores multiple optional questionnaires for each of the multiple pain areas to check the user's symptoms for that area. These optional questionnaires can be configured differently depending on the specific pain area of ​​the user. The control unit (130) can refer to the storage unit (120) and provide the optional questionnaire (330) for a specific pain area among the multiple body parts to the electronic device (10) to determine the user's indication status for the specific pain area.

[0095] As illustrated in (b) of FIG. 3b, the control unit (130) can conduct a multi-faceted survey on the user's indication by providing the electronic device (10) with a plurality of multiple-choice surveys (331, 332, 333, 334) and a selection item corresponding to each of a plurality of different responses to each of the question items related to the user's indication included in the multiple-choice surveys. For example, the control unit (130) can conduct a survey related to the user's indication by using a multiple-choice survey that includes a question item related to symptoms of the pain area (331), a question item related to the timing of pain (332), a question item related to exercise habits (333), a question item related to risk factors (or RED FLAG) (334), a question item related to medications taken, a question item related to the place where exercise is performed, and a question item related to exercise equipment possessed.

[0096] Furthermore, the control unit (130) can conduct an AI-based conversational survey. Here, “conversational survey” may refer to a survey that can receive natural language input from the electronic device in relation to the user’s indication. At this time, the conversational survey may be conducted using at least one of a large language model (140) and a chatbot. Here, the at least one large language model (140) may refer to a large language model (140) based on at least one of GPT (Generative Pre-trained Transformer), T5 (Text-to-Text Transfer Transformer), Vision-Language Models (e.g., CLIP, Flamingo), Multimodal Generative Models (GPT-4 Multimodal, PaLM-E), BERT (Bidirectional Encoder Representations from Transformers), and LaMDA (Language Model for Dialogue Applications).

[0097] In addition, the “chatbot” according to the present invention may be implemented to receive information that is difficult to obtain from multiple-choice questions in relation to the user’s indication. For example, the “chatbot” according to the present invention may include at least one of a rule-based chatbot, an artificial intelligence chatbot, a natural language processing chatbot, and a hybrid chatbot.

[0098] As illustrated in (c) of FIG. 3b, the control unit (130) can conduct an interactive survey (340) with the user's indications. More specifically, the control unit (130) can conduct an interactive survey (340) to collect information related to indications that is difficult to verify in detail through a multiple-choice survey. For example, the control unit (130) can generate and provide an interactive survey question (341) related to the user's indications on a service page (1000) provided on an electronic device (10). In this case, the control unit (130) can provide the interactive survey (340) through at least one of a large language model (140) and a chatbot so that the user can freely respond to the interactive survey question (341). Furthermore, the control unit (130) can receive the user's response (342) to the interactive survey question (341) through the service page (1000).

[0099] Furthermore, the control unit (130) may provide an additional survey (350) related to the pain area specified by the user in the basic survey (300). Specifically, the control unit (130) may provide the additional survey to the electronic device, which includes at least one question related to the specified pain area.

[0100] As illustrated in FIG. 3c (a) and (b), the control unit (130) may provide the electronic device (10) with an additional survey (350) related to a specific pain area based on user input regarding the pain area survey included in the basic survey. For example, if the user selects a first body part (e.g., “waist (lumbar spine)”) as the pain area in the basic survey, the control unit (130) may provide the electronic device (10) with a first additional survey (351) containing at least one question item (353 to 355) associated with the first body part. Alternatively, if the user selects a second body part (e.g., “shoulder”) as the pain area in the basic survey, the control unit (130) may provide the electronic device (10) with a second additional survey (352) containing at least one question item (356 to 358) associated with the second body part.

[0101] More specifically, the control unit (130) can provide the user with an additional survey (350) to receive response data related to the user's indications that were not obtained from the basic survey (300). For example, the control unit (130) can provide the electronic device (10) with an additional survey that includes at least one question item related to a specific pain area, such as a pain-inducing motion question item (353), a symptom-related question item (354, 355, 358), and a daily life-related question item (357), and a plurality of selection items corresponding to each of the plurality of different responses to the said question item.

[0102] That is, in the present invention, at least one survey provided to the electronic device (10) in relation to a user indication may include at least one of a basic survey including questions related to the user indication and an additional survey provided differently depending on the user's response to the basic survey. Furthermore, each of the basic survey and the additional survey may include at least one of a selection type survey consisting of at least one question item related to the user indication and a plurality of selection items corresponding to each of a plurality of different responses to the question item, and at least one of an interactive survey capable of receiving natural language input from the electronic device in relation to the user indication.

[0103] Meanwhile, each of the basic survey (300) and additional survey (350) according to the present invention is not limited to the examples of surveys (or questions) described above, and may include at least one survey among a selection type survey and an interactive survey, and the at least one survey may include various surveys (or questions) related to user indications.

[0104] In the present invention, a process of receiving response data for the survey from an electronic device may be carried out (S220, see FIG. 2).

[0105] The control unit (130) can receive response data for a selection survey (or selection survey response data) that includes a response matched to an item selected by user input among a plurality of selection items from the electronic device (10). As illustrated in (b) of FIG. 3b, the control unit (130) can receive as selection response data a response that matches a selection item selected by user input among a plurality of selection items for a question related to the user's indication included in the selection survey (330) (e.g., “Please select all symptoms of the current pain area.”).

[0106] As illustrated in (c) of FIG. 3b, the control unit (130) can process the natural language input entered into the electronic device (10) as input to the large language model (140) and receive response data (or, conversational survey response data) for the conversational survey from the large language model (140). Specifically, the control unit (130) can provide at least one conversational survey question (341) to the electronic device (10) on the service page (1000) and receive the user's natural language input (342) for the conversational survey question (341) in a manner that converses with the user. Furthermore, the control unit (130) can process the natural language input (342) received from the electronic device (10) as input to at least one of the large language model (140) and the chatbot.

[0107] For example, the control unit (130) can process natural language input (342) entered in the conversational survey (340) as input to the large language model (140) and receive conversational survey response data from the large language model (140). As another example, the control unit (130) can process natural language input (342) entered in the conversational survey (340) as input to the chatbot and receive conversational survey response data from the chatbot.

[0108] Furthermore, the control unit (130) can provide a preset number of interactive survey questions to the electronic device (10) and receive the user's interactive survey response data for each of the interactive survey questions. At this time, the control unit (130) can provide a sample answer to the interactive survey question (341) along with the interactive survey question (341) so that important information regarding the interactive survey question (341) can be entered.

[0109] In the present invention, a process of setting evaluation criteria for evaluating a user's exercise performance ability based on at least one of response data and user history information may be performed (S230, see FIG. 2).

[0110] The control unit (130) can evaluate the user’s exercise performance ability using evaluation criteria that consider the user’s current indication status. Here, “evaluation criteria” may refer to criteria that specify at least one evaluation item among a plurality of evaluation items related to the evaluation of exercise performance ability according to the user’s current indication status based on response data and history information. At this time, the history information includes at least one of medical records related to the user’s indication and past response data to a survey, and the medical records may include at least one of the user’s medical records and rehabilitation records.

[0111] Specifically, the “exercise performance ability” according to the present invention is a key indicator reflecting the current physical functional state of the user, and can be evaluated by synthesizing the evaluation results of at least one evaluation item performed during the exercise performance ability evaluation process. In addition, the “evaluation item” according to the present invention may include at least one exercise movement matched to different evaluation types (e.g., user’s static posture, range of motion, balance (or coordination) ability, and muscle strength (or muscle endurance)) in order to evaluate the user’s exercise performance ability.

[0112] As illustrated in FIG. 4a, the control unit (130) can evaluate the user's exercise performance ability considering the user's current indication status by using survey response data (410) for at least one of the basic survey and additional survey and user history information (420) already stored in the database (200). Specifically, the control unit (130) can set an evaluation criterion (400) to specify an exercise performance ability evaluation item (450) considering the user's current indication status by using at least one of the survey response data (410) and history information (420).

[0113] As previously explained, the basic survey and additional survey according to the present invention may each include at least one of a selection survey and an interactive survey. The control unit (130) may set the evaluation criteria (400) using the selection survey response data (411) and the interactive survey response data (412) received based on the user's response (or user input) to the basic survey and additional survey. Additionally, the control unit (130) may set the evaluation criteria (400) using the user's history information (420) collected from the database (200). Here, the history information (420) may include information related to at least one of the user's i) name, ii) date of birth, iii) type of indication, iv) exercise history, v) medical records, vi) surgical records, vii) past medical history, viii) prescription information, ix) past response data, and x) exercise rehabilitation.

[0114] The control unit (130) can set evaluation criteria using evaluation information extracted from at least one of a specific user's survey response data (410) and history information (420). Here, the “evaluation criteria” according to the present invention may be set differently based on at least one of the survey response data and history information. Additionally, the “evaluation information” according to the present invention may include at least one of the user’s name, pain location and symptoms, duration of pain, pain level (or degree of pain), diagnosed disease (or underlying disease), risk factors, medical records, and exercise environment (e.g., exercise location) extracted from at least one of the survey response data and history information.

[0115] For example, the control unit (130) may set a criterion for specifying an exercise performance evaluation item of the first user as a first evaluation criterion (438) by using a first evaluation information (430) that includes at least one of the first user's survey response data and the first user's history information. Alternatively, the control unit (130) may set a criterion for specifying an exercise performance evaluation item of the second user as a second evaluation criterion (448) by using a second evaluation information (440) that includes at least one of the second user's survey response data and the second user's history information.

[0116] In the present invention, based on evaluation criteria, a process of specifying at least one evaluation item among a plurality of evaluation items related to exercise performance evaluation may be carried out (S240, see FIG. 2).

[0117] The control unit (130) can identify evaluation restriction items that satisfy unsuitability conditions among a plurality of evaluation items related to exercise performance evaluation based on evaluation criteria set differently according to at least one of response data and history information. Here, “evaluation restriction items” can be identified based on at least one of the pain level of the user’s pain area and medical records included in at least one of the response data and history information for the survey. Additionally, the unsuitability condition may refer to a condition for identifying evaluation restriction items that are excluded from the user’s exercise performance evaluation based on restriction criteria previously set in at least one of the pain level and medical records.

[0118] At this time, the “pre-set restriction criteria” according to the present invention may exist as criteria for determining whether a specific evaluation item is subject to performance restriction based on evaluation information, and may be pre-set by at least one of an electronic device (10) logged in with a medical staff account and a difficulty setting system (100). Specifically, the pre-set restriction criteria may include restriction criteria corresponding to information related to at least one of the pain area and symptoms, duration of pain, level of pain (or degree of pain), diagnosed disease (or underlying disease), risk factors, medical records, and location of exercise performance included in the evaluation information.

[0119] For example, the control unit (130) can compare the pain level of a specific pain area with a specific threshold (e.g., 5 points) based on a limiting criterion for the pain level, and identify an evaluation item that satisfies the non-compliance criterion as an evaluation limiting item.

[0120] As illustrated in (a) and (b) of FIG. 4b, as an example, the control unit (130) may specify a first evaluation item (461) associated with the first pain area as an evaluation restriction item based on the first evaluation information (430), if the first user feels a first pain level (e.g., 7 points) regarding the first pain area (e.g., lower back). On the other hand, the control unit (130) may specify a fourth evaluation item (464) associated with the second pain area as an evaluation restriction item based on the second evaluation information (440), if the second user feels a second pain level (e.g., 5 points) regarding the second pain area (e.g., shoulder).

[0121] Additionally, the control unit (130) may specify an evaluation item satisfying the above non-conforming condition as an evaluation restriction item based on the restriction criteria for the risk factor. Specifically, the control unit (130) may specify an evaluation item associated with a specific risk factor matched to a specific evaluation item as an evaluation restriction item based on the restriction criteria for the risk factor. For example, if the first evaluation information (430) includes a first risk factor (e.g., hypertension), the control unit (130) may specify a third evaluation item (463) associated with the first risk factor as an evaluation restriction item. As another example, if the second evaluation information (440) includes a second risk factor (e.g., pregnancy), the control unit (130) may specify a second evaluation item (462) associated with the second risk factor as an evaluation restriction item.

[0122] Furthermore, the control unit (130) may specify an evaluation item that satisfies the above-mentioned unsuitable condition as an evaluation restriction item based on the restriction criteria for the exercise environment. Specifically, the control unit (130) may specify an evaluation restriction item according to the exercise environment information matched to the specific evaluation item. For example, if the second evaluation information (440) includes a second exercise environment (e.g., company), the control unit (130) may specify a fifth evaluation item (465) that is not matched with the second exercise environment as an evaluation restriction item.

[0123] Meanwhile, the control unit (130) can specify evaluation restriction items based on the user's medical records (e.g., surgery records, medical records, etc.) included in the history information. For example, based on the fact that there is a surgery record for a second body part (e.g., shoulder) among the user's body parts, the control unit (130) can specify evaluation items associated with said second body part as evaluation restriction items that are excluded from performance within a preset period from the time of surgery. In this way, the preset restriction criteria in the present invention can be set by at least one of an electronic device (10) with a medical staff account logged in and a difficulty setting system so as to select exercise performance evaluation items suitable for each user's condition.

[0124] Furthermore, the control unit (130) can specify at least one evaluation item among a plurality of evaluation items based on a specified evaluation restriction item. Specifically, the control unit (130) can specify an evaluation restriction item that satisfies the above-mentioned unsuitability condition among a plurality of evaluation items performed according to the exercise performance evaluation, and exclude the specified evaluation restriction item from the plurality of evaluation items to specify at least one evaluation item to be performed in the exercise performance evaluation.

[0125] In the present invention, a process may be performed to evaluate the user's exercise performance ability for at least one evaluation item by inputting the user's exercise data into a pre-trained motion evaluation model (S250, see FIG. 2).

[0126] The control unit (130) can evaluate the user's exercise performance ability based on different evaluation types (e.g., user's static posture, range of motion, balance (or coordination) ability, and muscle strength (or muscle endurance)) using a previously learned motion evaluation model (132). Specifically, the control unit (130) can specify at least one evaluation item among a plurality of evaluation items including exercise movements matched to each different evaluation type, and can perform an evaluation of exercise performance ability for different evaluation types based on the specified at least one evaluation item. At this time, the control unit (130) can perform an evaluation of exercise performance ability for different evaluation types according to an evaluation item related to the user's pain area included in the user's evaluation information.

[0127] As illustrated in FIG. 5a, the control unit (130) can perform an exercise performance evaluation (510) related to the first pain area (e.g., lower back) based on the first state information (430) when the pain area of ​​the first user is the first pain area (e.g., lower back). For example, the control unit (130) can perform a motion analysis evaluation of the first user based on a motion analysis evaluation item list (511) composed of evaluation items associated with the first pain area (e.g., lower back). Here, “motion analysis evaluation” may mean an exercise performance evaluation related to at least one of the static posture and joint range of motion of the user. As another example, the control unit (130) can perform a coordination (or coordination) ability evaluation of the first user based on a coordination (or coordination) ability evaluation list (512) composed of evaluation items associated with the first pain area (e.g., lower back). Additionally, the control unit (130) can perform an evaluation of the first user's muscle strength (or muscle endurance) based on a muscle strength (or muscle endurance) ability evaluation list (513) composed of evaluation items associated with the first pain area (e.g., lower back).

[0128] On the other hand, the control unit (130) can perform an exercise performance evaluation (520) related to the second pain area if the second user's pain area is the second pain area (e.g., shoulder) based on the second state information (440). For example, the control unit (130) can perform a motion analysis evaluation of the second user based on a motion analysis evaluation item list (521) composed of evaluation items associated with the second pain area (e.g., shoulder). Additionally, the control unit (130) can perform a coordination (or coordination) ability evaluation of the second user based on a coordination (or coordination) ability evaluation list (522) composed of evaluation items associated with the second pain area (e.g., shoulder). Likewise, the control unit (130) can perform a muscle strength (or muscle endurance) evaluation of the second user based on a muscle strength (or muscle endurance) evaluation list (523) composed of evaluation items associated with the second pain area (e.g., shoulder).

[0129] Based on FIG. 5b, the control unit (130) can receive the user’s exercise data corresponding to at least one specified evaluation item from the electronic device. Specifically, the control unit (130) can collect the user’s exercise data (530) using at least one of the camera and sensor unit provided in the electronic device (10) and evaluate the user’s current exercise performance ability based on at least one specified evaluation item (450). Here, “exercise data” may include at least one of an image and video of the user’s movements performed for the exercise performance evaluation provided in the electronic device. For example, the control unit (130) can receive exercise data for a specific posture of the user captured by a camera provided in the electronic device (10).

[0130] Specifically, the control unit (130) may activate at least one sensor equipped in the electronic device (10) to evaluate the user's exercise performance ability. For example, when an exercise performance ability evaluation is performed from the electronic device (10), the control unit (130) may activate a sensor unit including a microphone, a camera, and a plurality of different sensors equipped in the electronic device (10).

[0131] Furthermore, the control unit (130) can receive sensing information based on the activation of at least one of the microphone, camera, and sensor unit equipped in the electronic device (10). For example, the control unit (130) can receive exercise data (530) including at least one of a user's exercise motion image and an exercise motion video from the camera based on the activation of at least one of the camera and microphone. At this time, the video received through the camera can be displayed in real time on the display unit of the electronic device (10).

[0132] Furthermore, the control unit (130) can analyze at least one of the user's static posture, joint range of motion, balance (or coordination) ability, and muscle strength (or muscle endurance) using a previously learned motion evaluation model (132). Here, the motion evaluation model (132) is a posture estimation model learned using a learning data set containing position information for joint points, and may refer to an artificial intelligence model learned to estimate the user's (U) movement from exercise data. Here, "joint point" may refer to a plurality of joints of the user (U) (or a part of the user's (U) body including joints). And, "key point" may refer to an area corresponding to each of the user's (U) plurality of joint points in at least one of an image and video containing the user's movement.

[0133] The control unit (130) can use a pre-learned motion evaluation model (132) to extract key points corresponding to the user's joint points from the user's exercise data and evaluate the user's (U) exercise motion based on an analysis of the positional relationship between the extracted key points. In the present invention, a series of processes for evaluating the user's exercise performance ability from exercise data using key points extracted through the motion evaluation model (132) can be named the “exercise performance ability evaluation process.”

[0134] In the present invention, the physical space and subject where the exercise performance evaluation process takes place are not separately distinguished, and it can be described as taking place in the difficulty setting system (100). The exercise performance evaluation process can be performed using key points extracted from the motion evaluation model (132).

[0135] More specifically, the control unit (130) can analyze motion data (530) received from the camera on a frame-by-frame basis to extract key points corresponding to joint points corresponding to the user's motion. For example, the motion evaluation model (132) may include various object detection algorithms. For example, the motion evaluation model (132) may include an algorithm (Weighted Box Fusion, WBF) that ensembles multiple bounding boxes. However, it is obvious that the control unit (130) is not limited to the object detection algorithms described above and can use various object detection algorithms capable of detecting objects corresponding to the user (U) from images or videos included in the motion data (530).

[0136] In the present invention, the training data for which the operation evaluation model (132) performs training may be stored in a database (200), and a part of this database (200) may also be named a “training data DB.” Further details regarding the training data will be described later.

[0137] Furthermore, the control unit (130) can perform training for the motion evaluation model (132) based on a training data set existing in the training data DB. As previously described, the training data set may include location information of joint points matched with the user's joint points. The control unit (130) can train the motion evaluation model (132) to extract key points corresponding to the user's joint points from the motion data (530) using the training data set.

[0138] As illustrated in FIG. 5a, the control unit (130) can perform motion analysis evaluations (511, 521) for the user. Here, the “motion analysis evaluation (511, 521)” may include at least one of static posture evaluation (or body shape analysis) and joint range of motion evaluation. Specifically, the control unit (130) can perform motion analysis evaluations (511, 521) for each of a plurality of different body parts to evaluate the user’s exercise performance ability in the electronic device (10). For example, the control unit (130) can analyze the user’s body shape from an image (or video) of the user’s static posture captured by the electronic device (10) using a pre-learned motion evaluation model (132). For example, the control unit (130) can analyze the alignment status of the user's body parts (e.g., head, neck, shoulders, pelvis, knees, etc.) from an image (or video) of the static posture using a previously learned motion evaluation model (132).

[0139] Furthermore, the control unit (130) can perform an evaluation of the joint range of motion for each of a plurality of different body parts in order to evaluate the user's exercise performance ability in the electronic device (10). Specifically, the control unit (130) can use a pre-learned motion evaluation model (132) to perform an analysis of at least one of the joint travel distance, joint movement speed (or acceleration), and the user's body balance, body equilibrium, and body alignment state (e.g., leg axis alignment state, spine alignment state, etc.) included in the exercise video to be analyzed.

[0140] For example, the control unit (130) can use a camera provided in the electronic device (10) to capture the user's movement based on a plurality of shooting topics for evaluating the range of motion of the joint. At this time, among the plurality of shooting topics (first shooting topic to fourth shooting topic), the first shooting topic may be related to a "static posture," the second shooting topic may be related to a "range of motion of the joint (shoulder)," the third shooting topic may be related to a "range of motion of the joint (elbow)," and the fourth shooting topic may be related to a "range of motion of the joint (torso)." Meanwhile, for each of the plurality of shooting items corresponding to the plurality of shooting topics, at least one of the shooting target scene (or scene), shooting method, and shooting order may be matched and exist.

[0141] The control unit (130) can receive user exercise data according to the shooting method and shooting order matched to the shooting topic selected in the electronic device (10), and perform user motion analysis evaluation (511, 521) from the exercise data.

[0142] Furthermore, the control unit (130) can perform an evaluation of the user's balance (or coordination) ability (512, 522) and an evaluation of muscle strength (or muscle endurance) (513, 523) using a pre-learned motion evaluation model (132). Specifically, the control unit (130) can evaluate at least one of the user's balance (or coordination) ability and muscle strength (or muscle endurance) from the user's exercise data performing a pre-set exercise motion (e.g., one-leg standing motion, dead bug motion, plank motion, etc.). At this time, the control unit (130) can provide a sample video of the pre-set exercise motion to the electronic device (10) and induce the user to perform the pre-set exercise motion according to the provided sample video.

[0143] The control unit (130) measures the time during which a user performs and maintains a preset exercise movement (e.g., one-leg standing posture, plank posture) in a proper posture, and based on the maintenance time, may perform at least one of an evaluation of the user's balance (or coordination) ability (512, 522) and an evaluation of muscle strength (or muscle endurance) (513, 523). For example, the control unit (130) may evaluate the measured maintenance time according to preset time intervals to perform an evaluation of the user's balance (or coordination) ability and muscle strength (or muscle endurance). Here, the “preset time intervals” may include multiple different time intervals. The control unit (130) can evaluate the user’s balance (or coordination) ability and muscle strength (or muscle endurance) as “insufficient (or low)” based on the first time interval (e.g., less than 1 minute) among a plurality of different measured maintenance times, as “average (or medium)” based on the second time interval (e.g., 1 minute to 3 minutes), and as “good (or high)” based on the third time interval (e.g., more than 3 minutes). At this time, the pre-set time interval according to the present invention is not limited to the described examples and can be set in various ways by the difficulty setting system (100).

[0144] As another example, the control unit (130) measures the number of times a user performs a preset exercise motion (e.g., dead bug motion) in a set posture for a preset time (e.g., 30 seconds), and based on the number of times, may perform at least one of an evaluation of the user's balance (or coordination) ability (512, 522) and an evaluation of muscle strength (or muscle endurance) (513, 523). For example, the control unit (130) may evaluate the measured number of times according to a preset number interval to perform an evaluation of the user's balance (or coordination) ability and muscle strength (or muscle endurance). Here, the “preset number interval” may include multiple different number intervals. The control unit (130) can evaluate the user’s balance (or coordination) ability and muscle strength (or muscle endurance) as “insufficient (or low)” based on the first repetition interval (e.g., less than 10) among a plurality of different repetition intervals, as “average (or medium)” based on the second repetition interval (e.g., 10 to 20), and as “good (or high)” based on the third repetition interval (e.g., more than 20). At this time, the preset repetition interval according to the present invention is not limited to the described example and can be set in various ways by the difficulty setting system (100).

[0145] As illustrated in FIG. 5b, the control unit (130) can generate the exercise performance evaluation result for at least one evaluation item. Specifically, the control unit (130) can receive exercise data (530) using at least one of the camera and sensor unit provided in the electronic device (10). Furthermore, the control unit (130) can generate the user's exercise performance evaluation result (500) by processing the exercise data (530) as input to a pre-learned motion evaluation model (132).

[0146] Specifically, the exercise performance evaluation result (500) may include at least one of the user's motion analysis evaluation result (540), balance (or coordination) ability evaluation result (550), and muscle strength (or muscle endurance) evaluation result (460). Furthermore, the control unit (130) may comprehensively evaluate the user's exercise performance based on the user's motion analysis evaluation result (540), balance (or coordination) ability evaluation result (550), and muscle strength (or muscle endurance) evaluation result (560) based on pre-set evaluation criteria. Here, “pre-set evaluation criteria” may refer to criteria by which medical personnel evaluate the user's exercise performance based on the evaluation of the user's static posture, joint range of motion, balance (or coordination) ability, and muscle strength (or muscle endurance). The control unit (130) may generate an exercise performance evaluation result (500) that further includes a comprehensive evaluation result (570) for the comprehensive evaluation.

[0147] In the present invention, a process of generating a prompt to be input into a large language model can be carried out using response data and evaluation results of exercise performance ability (S260, see FIG. 2).

[0148] As illustrated in FIG. 6a, the control unit (130) can generate a prompt (600) to be input into a large language model (140) from survey response data (410), which includes multiple-choice survey response data (411) and interactive survey response data (412), and exercise performance evaluation results (500), using a prompt generation unit (131). Specifically, the prompt generation unit (131) can generate a prompt (600) that includes a response matched to an item selected by user input among the multiple selection items for a question related to the user's indication included in the multiple-choice survey.

[0149] For example, the prompt generation unit (131) can generate a prompt (600) to include information regarding at least one of the specified pain site, pain level, underlying disease, medical record, risk factor, and exercise equipment possessed in relation to the user's indication included in the optional survey response data (411). Furthermore, the prompt generation unit (131) can generate a prompt (600) to include the user's natural language input included in the interactive survey response data (412) and the response of the large language model (140) to the natural language input.

[0150] Additionally, the prompt generation unit (131) can generate a prompt (600) that includes the user's motion analysis evaluation result (540) included in the user's exercise performance evaluation result (500). The control unit (130) can generate a prompt (600) that includes the balance (or coordination) ability evaluation result (550) and the muscle strength (or muscle endurance) evaluation result (560). Furthermore, the control unit (130) can generate a prompt (600) that includes the comprehensive evaluation result (570) of the user's exercise performance.

[0151] In the present invention, a process may be carried out in which a prompt is input into a large language model to obtain an exercise difficulty level related to the user's indication from the large language model (S270, see FIG. 2).

[0152] The exercise difficulty according to the present invention may be determined based on a pre-set difficulty setting standard. Here, a plurality of different setting standards may be included. For example, the pre-set difficulty setting standard may refer to a standard for setting the exercise difficulty of an exercise program according to at least one of response data, history information, and exercise performance evaluation included in the prompt. Here, the “exercise program” is configured to include a plurality of exercise modules, and each of the plurality of exercise modules is matched to a different exercise type and may include at least one exercise motion content related to the exercise type matched to each exercise module. At this time, the different exercise types may refer to at least one of a first exercise type (or main exercise type), a second exercise type (e.g., warm-up exercise type), and a third exercise type (or cool-down exercise type).

[0153] Specifically, the control unit (130) can obtain a specific exercise difficulty among a plurality of exercise difficulty levels through the large language model into which the prompt is input, based on a pre-set difficulty setting standard. At this time, at least one exercise movement content includes movement difficulty information, and each of the plurality of exercise modules may include at least one specific exercise movement content based on the specific exercise difficulty. In the present invention, it is described that the control unit (130) obtains the exercise difficulty by linking with the large language model (140), but it is not limited thereto, and the control unit (130) itself may specify (or generate) the exercise difficulty by including the function of the large language model (140) or performing the same function. Therefore, in this specification, the control unit (130) obtaining the exercise difficulty and the large language model (140) generating or specifying the exercise difficulty may be expressed interchangeably.

[0154] As illustrated in FIG. 6b, a large language model (140) can determine the exercise difficulty (610) of an exercise program based on at least one of the response data, history information, and exercise performance evaluation results included in the prompt, according to the difficulty setting criteria (630). Here, the “difficulty setting criteria (630)” may include a plurality of difficulty setting criteria based on at least one of the response data, history information, and exercise performance evaluation results included in the prompt. For example, among the plurality of difficulty setting criteria, the first setting criterion (631) may mean a difficulty setting criterion based on information related to at least one of the degree of pain (or pain score), pain-inducing movements, and duration of pain in relation to the user’s pain.

[0155] Specifically, the first setting criterion (631) may include a difficulty limit criterion for each of the information related to at least one of the pain level (or pain score), the pain-inducing movement, and the duration of the pain. As an example, the large language model (140) may specify an exercise difficulty level of a specific difficulty level (e.g., third difficulty level) or lower based on a difficulty limit criterion matched to the first score when the pain score for the user's pain area is a first score (e.g., 5 points). As another example, the large language model (140) may specify an exercise difficulty level based on a difficulty limit criterion matched to the duration of the pain for the user's pain area.

[0156] Specifically, the large language model (140) may specify the user's pain as a first state (e.g., acute) based on the duration of the pain being a first period (e.g., one week), and specify the exercise difficulty as a specific difficulty level (e.g., third difficulty level) or lower based on a second difficulty limit criterion matched to the first state. Alternatively, the large language model (140) may specify the user's pain as a second state (e.g., chronic) based on the duration of the pain being a second period (e.g., six months), and specify the exercise difficulty as a specific difficulty level (e.g., fifth difficulty level) or lower based on a difficulty limit criterion matched to the second state.

[0157] Additionally, among the multiple difficulty setting criteria, the second setting criterion (632) may refer to a difficulty setting criterion based on at least one of static posture, joint range of motion, balance (or coordination) ability, and muscle strength (or muscle endurance) based on the exercise performance evaluation results included in the prompt. Specifically, the second setting criterion (632) may include a difficulty limit criterion for each of the evaluation results for at least one of static posture, joint range of motion, balance (or coordination) ability, and muscle strength (or muscle endurance). As an example, the large language model (140) may specify the exercise difficulty to a specific difficulty level (e.g., third difficulty level) or lower based on the difficulty limit criterion matched to the first grade when the balance (or coordination) ability in the user's exercise performance evaluation results is a first grade (e.g., normal grade).

[0158] Additionally, among the multiple difficulty setting criteria, the third setting criterion (633) may refer to a difficulty setting criterion based on at least one of medical records (e.g., surgical records, diagnostic records) and underlying disease information included in the response data and history information included in the prompt. Specifically, the third setting criterion (633) may include difficulty limit criteria for each of the medical records (e.g., surgical records, diagnostic records) and underlying disease information. As an example, if the user has a specific underlying disease (e.g., hypertension), the large language model (140) may specify an exercise difficulty level of a specific difficulty (e.g., third difficulty) or lower based on the difficulty limit criteria matched to the specific underlying disease.

[0159] Additionally, among the multiple difficulty setting criteria, the fourth setting criterion (634) may refer to a difficulty setting criterion based on at least one of the exercise frequency, exercise time, and exercise location included in the exercise habit and environment information included in the prompt. Specifically, the fourth setting criterion (634) may include a difficulty limit criterion for each of the exercise frequency, exercise time, and exercise location. As an example, if the user's exercise frequency is a first frequency (e.g., 3 times a week), the large language model (140) may specify the exercise difficulty to be below a specific difficulty level (e.g., 5th difficulty level) based on the difficulty limit criterion matched to the first frequency. As another example, if the user's exercise location is a first location (e.g., company), the large language model (140) may specify the exercise difficulty to be below a specific difficulty level (e.g., 2nd difficulty level) based on the difficulty limit criterion matched to the first location.

[0160] In this way, the large language model (140) can determine the exercise difficulty to be set in the exercise program based on a difficulty setting criterion based on at least one of the response data included in the prompt, the exercise performance evaluation result, and the history information. Furthermore, the control unit (130) can obtain the specific exercise difficulty from the response of the large language model (140). At this time, the specific exercise difficulty may mean an exercise difficulty that satisfies any one of the above-mentioned multiple different setting criteria. Alternatively, the specific exercise difficulty may mean an exercise difficulty that satisfies all of the above-mentioned multiple different setting criteria.

[0161] In the present invention, based on the acquired exercise difficulty, a process of generating an exercise program related to the user's indications may be carried out (S280, see FIG. 2).

[0162] As described above, the exercise program according to the present invention is configured to include a plurality of exercise modules, each of which is matched to a different type of exercise, and may include at least one exercise motion content associated with the type of exercise matched to each exercise module.

[0163] The control unit (130) can obtain a specific exercise difficulty level among a plurality of different exercise difficulty levels according to the pre-set difficulty setting criteria. Here, for each of the plurality of different exercise difficulty levels, a pre-set difficulty level of the exercise content to be included in the specific exercise module may exist. Specifically, the at least one exercise movement content may include movement difficulty information, and each of the plurality of exercise modules may include at least one specific exercise movement content that satisfies a pre-set movement difficulty condition based on the specific exercise difficulty level. Here, the “pre-set movement difficulty condition” may mean a condition that limits the difficulty of the exercise movement content included in at least one exercise module constituting an exercise program in which the specific exercise difficulty level is set.

[0164] At this time, a pre-set movement difficulty attribute value may be labeled on the exercise movement content. For example, at least one of a first movement difficulty attribute value (e.g., “1”), a second movement difficulty attribute value (e.g., “2”), a third movement difficulty attribute value (e.g., “3”), a fourth movement difficulty attribute value (e.g., “4”), a fifth movement difficulty attribute value (e.g., “5”), and a sixth movement difficulty attribute value (e.g., “6”) may be labeled on the exercise movement content.

[0165] As illustrated in FIG. 6b(a), the exercise difficulty set in the exercise program according to the present invention may mean at least one of a plurality of exercise difficulty levels. Here, each of the plurality of exercise difficulty levels may be classified into a first difficulty level (621) to a sixth difficulty level (625) based on a pre-set movement difficulty setting standard for different exercise types. As an example, the first difficulty level (ex, “A”) may mean an exercise difficulty level that includes an exercise movement content among a plurality of movement contents associated with the first exercise type, wherein the movement difficulty is set to a first movement difficulty level or a second movement difficulty level, for a first exercise module (or main exercise module) corresponding to a first exercise type (or main exercise type).

[0166] Additionally, the first difficulty level (e.g., “A”) may refer to an exercise difficulty level that includes an exercise movement content among a plurality of movement contents associated with the second exercise type (or warm-up exercise type) in which the movement difficulty level is set to the first movement difficulty level, for a second exercise module (or warm-up exercise module) corresponding to the second exercise type (or warm-up exercise type). Likewise, the first difficulty level (e.g., “A”) may refer to an exercise difficulty level that includes an exercise movement content among a plurality of movement contents associated with the third exercise type in which the movement difficulty level is set to the first movement difficulty level, for a third exercise module (e.g., cool-down exercise module) corresponding to the third exercise type (or cool-down exercise type).

[0167] As another example, the second difficulty level (e.g., “B”) may refer to an exercise difficulty level that includes, among a plurality of motion contents associated with the first exercise type, an exercise motion content in which the motion difficulty level is set to any one of the first motion difficulty level to the third motion difficulty level, for a first exercise module (or main exercise module) corresponding to a first exercise type (or main exercise type). Additionally, the second difficulty level (e.g., “B”) may refer to an exercise difficulty level that includes, among a plurality of motion contents associated with the second exercise type, an exercise motion content in which the motion difficulty level is set to the first motion difficulty level or the second motion difficulty level, for a second exercise module (or warm-up exercise module) corresponding to a second exercise type (or warm-up exercise type). Likewise, the second difficulty level (e.g., “B”) may mean an exercise difficulty level that includes an exercise motion content among a plurality of motion contents associated with the third exercise type, wherein the motion difficulty level is set to the first motion difficulty level or the second motion difficulty level, for a third exercise module (e.g., cool-down exercise module) corresponding to the third exercise type (or cool-down exercise type).

[0168] In order to avoid redundant explanations, the description of the pre-set operational difficulty setting criteria for the third difficulty (“C”), fourth difficulty (“D”), fifth difficulty (“E”), and sixth difficulty (“F”) illustrated in FIG. 6(a) will be omitted below. It should be understood that each of the operational difficulty and the pre-set operational difficulty setting criteria according to the present invention is not limited to the examples described above. The various different operational difficulty and the pre-set operational difficulty setting criteria described in the present invention may be set in various ways by at least one of the electronic device (10) to which a medical staff account is logged in and the difficulty providing system (100).

[0169] The control unit (130) can process a prompt generated using at least one of the survey response data and the exercise performance evaluation results, and a specified movement difficulty level, as input to a large language model (140). Furthermore, the control unit (130) can extract at least one specific exercise movement content that satisfies a preset movement difficulty condition using the specific exercise difficulty level and the prompt. Specifically, the control unit (130) can extract multiple different exercise movement contents from a database (200) containing an exercise program DB (710) using the large language model (140).

[0170] According to the present invention, the exercise program DB (710) may store and contain multiple different exercise motion contents (711 to 713) related to each of the various body parts (or pain parts) of a person. As previously described, the “exercise motion contents” may include various information such as a name for a specific exercise motion, exercise time information, motion difficulty information, exercise type information, exercise body part information, exercise posture information, and exercise equipment information. At this time, each of the information (e.g., name for a specific exercise motion, exercise time information, motion difficulty information, exercise type information, exercise body part information, exercise posture information, exercise equipment information) included in the multiple exercise motion contents (711 to 713) stored in the exercise program DB (710) may be labeled (or tagged) with a pre-set attribute value.

[0171] For example, based on exercise type information matched to a plurality of exercise motion contents (711 to 713) stored in the exercise program DB (610), the exercise motion content corresponding to the second exercise type (“warm-up exercise type”) and the third exercise type (“cool-down exercise type”) may be labeled with a first type attribute value (e.g., “1”), and the exercise motion content corresponding to the second exercise type (“main exercise”) may be labeled with a second type attribute value (e.g., “2”). The description of the attribute values ​​described above is merely one embodiment, and the attribute values ​​labeled on the information constituting the exercise motion content are not limited to the described examples and can be set in various ways.

[0172] Furthermore, the large language model (140) can extract attribute values ​​for each of the multiple pieces of information included in the exercise motion content in order to extract at least one exercise motion content to be included in the exercise program. The large language model (140) receives attribute values ​​corresponding to each of the extracted multiple pieces of information and can extract exercise motion content including information corresponding to the extracted attribute values ​​from the exercise program DB (710).

[0173] The control unit (130) can use a large language model (140) to extract multiple different exercise motion contents from the exercise program DB (710) and generate at least one exercise module based on an exercise type matched to each of the extracted multiple exercise motion contents. For example, the control unit (130) can identify an exercise motion content related to a pain area based on information about the user's pain area included in the prompt (600) among multiple different exercise motion contents (711 to 713) from the exercise program DB (710).

[0174] Additionally, the control unit (130) can identify exercise motion content related to a body part in which the user's joint range of motion satisfies a preset condition, based on the user's motion analysis evaluation result included in the prompt (600) among a plurality of different exercise motion contents (711 to 713) from the exercise program DB (710). Here, the “preset condition” may mean a condition satisfied based on the user’s joint range of motion not corresponding to a normal standard range or being limited to below a specific threshold. At this time, the “normal standard range” and the specific threshold may be set in various ways by at least one of the electronic device (10) in which a medical staff account is logged and the difficulty setting system (100).

[0175] Furthermore, the large language model (140) can generate an exercise program composed of multiple exercise modules to correspond to the acquired exercise difficulty level by utilizing specific exercise motion content. In the present invention, it is described that the control unit (130) generates an exercise program using the large language model (140), but it is not limited thereto, and the control unit (130) itself may generate an exercise program by including the function of the large language model (140) or performing the same function. Accordingly, in this specification, the control unit (130) acquiring an exercise program and the large language model (140) generating an exercise program may be expressed interchangeably.

[0176] As illustrated in FIG. 7, the control unit (130) can generate the exercise program composed of a plurality of exercise modules based on an exercise type matched to at least one specific exercise motion content extracted through a large language model (140). Specifically, the control unit (130) can generate a plurality of different exercise modules (720, 730, 740) based on an exercise type matched to each of the specified exercise motion content. At this time, the exercise motion content included in each of the plurality of exercise modules can be configured based on an exercise difficulty setting standard pre-set for a specific difficulty level (610) obtained from the large language model (140).

[0177] For example, based on the acquired exercise difficulty being “second difficulty,” the control unit (130) can generate an exercise program (700) such that among the specified exercise motion contents, the first exercise type (“warm-up exercise type”) exercise motion content (e.g., “both hip joint circular rotation 1 - difficulty 1”, “inner thigh dynamic stretching - difficulty 2”, 721) is included in the first exercise module (“warm-up exercise module”, 720). At this time, the control unit (130) can generate an exercise program (700) composed of the first exercise module (“warm-up exercise module”, 720), the second exercise module (“main exercise module”, 630), and the third exercise module (“cool-down exercise module”, 640) in that order using a large language model (140).

[0178] Furthermore, the large language model (140) can generate an exercise program (700) that enables a user to continuously perform the same exercise movements based on exercise posture information included in the exercise movement content, for the continuity of the movement posture in a specific exercise module. Specifically, the large language model (140) can extract multiple exercise movement contents containing the same exercise posture information and generate an exercise program in which the multiple exercise movement contents are arranged continuously for a predetermined number (e.g., 3).

[0179] Meanwhile, the control unit (130) can generate an exercise program (700) containing exercise movement content that can be performed using exercise equipment (750) possessed by the user by using a large language model (140). Specifically, the large language model (140) can extract at least one exercise movement content containing specific exercise equipment information by using the user's response data to questions related to exercise equipment from the survey response data included in the prompt (600). For example, the large language model (140) can extract at least one exercise movement content containing exercise equipment information corresponding to the "foam roller" and "stretching band" based on the user's response in the survey response data that they have a "foam roller" and a "stretching band." Furthermore, the large language model (140) can generate an exercise program (700) containing the extracted at least one exercise movement content.

[0180] Meanwhile, the control unit (130) can use a large language model (140) to generate an exercise program (700) corresponding to the total exercise time (760) that is pre-set in the electronic device (10) logged in with a medical staff account. More specifically, the large language model (140) can include multiple exercise movement contents in different exercise modules to correspond to the total exercise time that is pre-set, based on exercise time information included in the exercise movement contents. As an example, if the total exercise time that is pre-set in the electronic device (10) logged in with the medical staff account of the control unit (130) is “20” minutes, the warm-up exercise module and the cool-down exercise module can each be set to 5 minutes of exercise time, and the main exercise module can be set to 10 minutes of exercise time. Furthermore, the large language model (140) can combine multiple exercise movement contents to satisfy the exercise time set in each exercise module, thereby generating an exercise program (700) that reflects the total exercise time (760) that is pre-set in the exercise program.

[0181] The method and system for setting the difficulty level of an exercise program using a large language model according to the present invention can perform a user-customized exercise performance evaluation by applying different evaluation items based on the user's current state, based on user survey response data and history information. Through this, the user's current exercise performance ability can be precisely evaluated to generate an exercise program of a difficulty level suitable for the user's rehabilitation.

[0182] Furthermore, the method and system for setting the difficulty level of an exercise program using a large language model according to the present invention can minimize the risk of re-injury due to overload and provide a safe evaluation environment that does not strain the user by considering the user's medical records (or treatment records) included in the history information and adjusting exercise performance evaluation items based on medical information such as existing medical history or surgical records.

[0183] Furthermore, by generating and providing an exercise program to a user with a user-customized difficulty level using a large language model according to the present invention, the risk of pain aggravation and withdrawal from the exercise program during exercise performance can be minimized, and long-term rehabilitation continuity can be secured.

[0184] Meanwhile, computer-readable media include all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SSD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0185] Furthermore, the computer-readable medium may be a server or cloud storage that includes a storage and is accessible to an electronic device via communication. In this case, the computer may download the program according to the present invention from the server or cloud storage via wired or wireless communication.

[0186] Furthermore, in the present invention, the computer described above is an electronic device equipped with a processor, namely a CPU (Central Processing Unit), and no special limitations are placed on its type.

[0187] Meanwhile, the above detailed description should not be interpreted restrictively in all respects but should be considered exemplary. The scope of the invention shall be determined by a reasonable interpretation of the appended claims, and all modifications within the equivalent scope of the invention are included within the scope of the invention.

Claims

1. A step of providing at least one questionnaire related to the user's indication to an electronic device; A step of receiving response data for the survey from the electronic device; A step of setting evaluation criteria for evaluating the user's exercise performance ability based on at least one of the above response data and the user's history information; A step of specifying at least one evaluation item among a plurality of evaluation items related to exercise performance evaluation based on the above evaluation criteria; A step of inputting the exercise data of the above user into a pre-trained motion evaluation model to evaluate the exercise performance ability of the above user for at least one evaluation item; A step of generating a prompt to be input into a large language model using the above response data and the evaluation results of the above exercise performance ability; A step of inputting the above prompt into the above large language model to obtain an exercise difficulty related to the user's indication from the above language model; and A method for setting the difficulty level of an exercise program using a large language model, characterized by including the step of generating an exercise program related to the user's indications based on the obtained exercise difficulty level.

2. In Paragraph 1, The above evaluation criteria are, It is set differently based on at least one of the response data and history information for the above survey, and The step of specifying at least one evaluation item above is, A step of identifying evaluation restriction items that satisfy unsuitability conditions among a plurality of evaluation items related to the exercise performance evaluation, based on the evaluation criteria set differently above; and A method for setting the difficulty level of an exercise program using a large language model, characterized by including the step of specifying at least one evaluation item among the plurality of evaluation items based on the specified evaluation limit item.

3. In Paragraph 2, The above evaluation limitation items are, A method for setting the difficulty level of an exercise program using a large language model, characterized by being determined based on at least one of the pain level of the user's pain area and medical records included in at least one of the response data to the above survey and the above history information.

4. In Paragraph 3, The above non-conforming conditions are, A method for setting the difficulty level of an exercise program using a large language model, characterized by a condition specifying the evaluation restriction item that is excluded from the evaluation of the user's exercise performance ability based on the pain level and a restriction standard previously set in at least one of the medical records.

5. In Paragraph 2, The step of evaluating the exercise performance ability of the above user is, A step of receiving the user's exercise data corresponding to at least one specified evaluation item from the electronic device; A step of analyzing at least one of the user's static posture, joint range of motion, balance ability, and muscle strength using the above-mentioned learned motion evaluation model; and A method for setting the difficulty level of an exercise program using a large language model, characterized by including the step of generating an exercise performance evaluation result for at least one evaluation item.

6. In Paragraph 1, The above exercise program is configured to include a plurality of exercise modules, and Each of the above plurality of motion modules is, A method for setting the difficulty level of an exercise program using a large language model, characterized by being matched to different exercise types and including at least one exercise motion content related to the exercise type matched to each of the exercise modules.

7. In Paragraph 6, The step of acquiring the above exercise difficulty level is, A method for setting the difficulty of an exercise program using a large language model, characterized by obtaining a specific exercise difficulty among a plurality of exercise difficulty levels through the large language model into which the prompt is input, based on a pre-set difficulty setting standard.

8. In Paragraph 7, The above-mentioned at least one exercise motion content includes motion difficulty information, and Each of the above plurality of motion modules is, A method for setting the difficulty level of an exercise program using a large language model, characterized by including at least one specific exercise movement content that satisfies a preset exercise difficulty condition based on the aforementioned specific exercise difficulty level.

9. In Paragraph 8, The above-mentioned difficulty setting criteria include multiple different setting criteria, and A method for setting the difficulty level of an exercise program using a large language model, characterized in that the above-mentioned specific exercise difficulty level satisfies all of the above-mentioned different multiple setting criteria.

10. In Paragraph 7, The step of generating the above exercise program is, A step of extracting at least one specific exercise movement content satisfying the preset exercise difficulty condition using the specific exercise difficulty and the prompt; and A method for setting the difficulty level of an exercise program using a large language model, characterized by including the step of generating the exercise program composed of the plurality of exercise modules based on the exercise type matched to at least one specific exercise motion content extracted through the large language model.

11. In Paragraph 1, The above at least one survey is, A basic questionnaire including questions related to the indications of the above-mentioned user and A method for setting the difficulty level of an exercise program using a large language model, characterized by including at least one additional survey provided differently depending on the user's response to the basic survey above.

12. In Paragraph 11, Each of the above basic survey and the above additional survey is, A multiple-choice questionnaire comprising at least one question item related to the indications of the user and a plurality of selection items corresponding to each of a plurality of different responses to the question item, and A method for setting the difficulty level of an exercise program using a large language model, characterized by including at least one interactive questionnaire capable of receiving natural language input from the electronic device in relation to the indications of the user.

13. In Paragraph 12, The step of receiving response data for the above survey is, A step of receiving response data for the selection survey from the electronic device, the response being matched to an item selected by user input among the plurality of selection items; and A method for providing an exercise program using a large language model, characterized by including the step of processing the natural language input entered into the electronic device as input to the large language model and receiving response data for the conversational survey from the large language model.

14. A control unit that provides at least one questionnaire related to a user's indication to an electronic device, and a communication unit that receives response data for the questionnaire from the electronic device. The above control unit is, An exercise program providing system using a large language model, characterized by establishing an evaluation criterion for evaluating the exercise performance ability of the user based on at least one of the above response data and the user's history information, specifying at least one evaluation item among a plurality of evaluation items related to the evaluation of exercise performance ability based on the above evaluation criterion, inputting the user's exercise data into a pre-trained motion evaluation model to evaluate the user's exercise performance ability for the at least one evaluation item, generating a prompt to be input into a large language model using the above response data and the evaluation result of the exercise performance ability, inputting the prompt into the large language model to obtain an exercise difficulty related to the user's indication from the large language model, and generating an exercise program related to the user's indication based on the obtained exercise difficulty.

15. A program that is executed by one or more processes in an electronic device and stored on a computer-readable recording medium, The above program is, A step of providing at least one questionnaire related to the user's indications to an electronic device; A step of receiving response data for the survey from the electronic device; A step of setting evaluation criteria for evaluating the user's exercise performance ability based on at least one of the above response data and the user's history information; A step of specifying at least one evaluation item among a plurality of evaluation items related to exercise performance evaluation based on the above evaluation criteria; A step of inputting the exercise data of the above user into a pre-trained motion evaluation model to evaluate the exercise performance ability of the above user for at least one evaluation item; A step of generating a prompt to be input into a large language model using the above response data and the evaluation results of the above exercise performance ability; A step of inputting the above prompt into the above large language model to obtain an exercise difficulty related to the user's indication from the above language model; and A program stored on a computer-readable recording medium characterized by including instructions that perform the step of generating an exercise program related to the user's indications based on the acquired exercise difficulty.

Images