Electronic device, method and non-transitory computer-readable storage medium for providing personalized exercise coaching guide

Abstract

The present disclosure provides an electronic device. The electronic device comprises a display, a communication circuit, a memory, and at least one processor including a processing circuit. The at least one processor can determine, on the basis of a rule-based machine learning model, a first exercise coaching guide level for monitoring exercise of a user, output at least one piece of coaching content generated by means of a large language model (LLM) using, as inputs, the first exercise coaching guide level and a predetermined exercise process, receive sensor data from a wearable electronic device worn by the user, and maintain the first exercise coaching guide level while it is determined that performance of exercise by the user is suitable for the first exercise coaching guide level by analyzing the sensor data.

Description

Electronic device, method, and non-transitory computer-readable storage medium providing a personalized exercise coaching guide

[0001] The present disclosure relates to an electronic device, a method, and a non-transitory computer-readable storage medium for providing a personalized exercise coaching guide.

[0002] Electronic devices (e.g., smart phones, mobile terminals, or wearable devices (e.g., smart watches, smart rings)) can measure a user's exercise information, analyze the measured user's exercise information, and store the analysis results in an application (e.g., health application) or provide exercise coaching based on the analysis results.

[0003] For example, a fitness application could receive an assessment of one's exercise ability (e.g., beginner / intermediate / expert level) and determine coaching content for today's workout. The fitness application could determine coaching content to achieve a set exercise goal or to verify posture accuracy during the workout.

[0004] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0005] An electronic device according to one embodiment of the present disclosure includes: a camera; at least one sensor for detecting a biosignal or movement; a microphone; a speaker; a display; a communication circuit; a memory; and at least one processor including a processing circuit; The memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: determine a first exercise coaching guide level for monitoring the user's exercise based on a rule-based machine learning model learned to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance ability level; output at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the determined exercise process as input while providing an exercise process determined according to a type of exercise selected by the user; monitor the user's exercise motion according to the progress of the exercise process, receive sensor data detecting the user's movement or biosignal from a wearable electronic device worn by the user, and analyze the received sensor data to cause the electronic device to monitor the user's exercise motion while maintaining the first exercise coaching guide level while determining that the user's exercise performance process is suitable for the first exercise coaching guide level.

[0006] According to one embodiment, a method of operating an electronic device may be provided. The method may include: determining a first exercise coaching guide level for monitoring a user's exercise based on a rule-based machine learning model trained to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance level; outputting at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the determined exercise process as input while providing an exercise process determined according to a type of exercise selected by a user input; monitoring the user's exercise motion according to the progress of the exercise process and receiving sensor data detecting the user's movement or biosignal from a wearable electronic device worn by the user; and monitoring the user's exercise motion while maintaining the first exercise coaching guide level while analyzing the received sensor data and determining that the user's exercise performance process is suitable for the first exercise coaching guide level.

[0007] According to one embodiment, a storage medium storing at least one computer-readable instruction may be provided. The at least one instruction, when executed by at least a part of at least one processor of the electronic device, may cause the electronic device to perform at least one operation. The at least one operation may include: determining a first exercise coaching guide level for monitoring a user's exercise based on a rule-based machine learning model that is trained to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance level; outputting at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the determined exercise process as input while providing an exercise process determined according to a type of exercise selected by a user input; monitoring the user's exercise motion according to the progress of the exercise process and receiving sensor data detecting the user's movement or biosignal from a wearable electronic device worn by the user; And it may include an operation of monitoring the user's exercise motion while maintaining the first exercise coaching guide level while analyzing the received sensor data and determining that the user's exercise performance process is suitable for the first exercise coaching guide level.

[0008] According to another embodiment of the present disclosure, a wearable electronic device includes an activity sensor for detecting movement of the wearable electronic device; a biosensor for detecting a biosignal; a speaker; a display; a communication circuit; a memory; and at least one processor including a processing circuit; The memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: receive exercise process information determined according to a type of exercise selected by a user input from the electronic device through the communication circuit, output a first screen providing the exercise process through the display based on the exercise process information, detect a movement or a biosignal of the user using at least one of the activity sensor or the biosensor, collect sensor data, and transmit the sensor data to the electronic device, receive, from the electronic device through the communication circuit, first exercise coaching guide level information and at least one coaching content generated using a large language model (LLM) according to the first exercise coaching guide level, and generate a second screen reflecting the first exercise coaching guide level information or the at least one coaching content, and output the second screen through the display.

[0009] According to one embodiment, a method of operating a wearable electronic device may be provided. The method may include: receiving, from an electronic device through the communication circuit, exercise process information determined according to a type of exercise selected by a user input; outputting a first screen providing the exercise process through the display based on the exercise process information; detecting a user's movement or a biosignal using at least one of the activity sensor or the biosensor to collect sensor data; transmitting the sensor data to the electronic device; receiving, from the electronic device through the communication circuit, first exercise coaching guide level information and at least one coaching content generated using a large language model (LLM) according to the first exercise coaching guide level; and generating a second screen reflecting the first exercise coaching guide level information or the at least one coaching content and outputting the second screen through the display.

[0010] According to one embodiment, a storage medium storing at least one computer-readable instruction may be provided. The at least one instruction, when executed by at least a part of at least one processor of a wearable electronic device, may cause the wearable electronic device to perform at least one operation. The at least one operation may include: receiving, from the electronic device through the communication circuit, exercise process information determined according to a type of exercise selected by a user input; outputting, through the display, a first screen providing the exercise process based on the exercise process information; collecting sensor data by detecting a movement or a biosignal of a user using at least one of the activity sensor or the biosensor; transmitting the sensor data to the electronic device; receiving, from the electronic device through the communication circuit, first exercise coaching guide level information and at least one coaching content generated using a large language model (LLM) according to the first exercise coaching guide level; And it may include an action of generating a second screen by reflecting the first exercise coaching guide level information or the at least one coaching content and outputting it through the display.

[0011] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0012] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0013] FIG. 2 is a flowchart illustrating an operation of an electronic device for providing a personalized exercise coaching guide according to one embodiment.

[0014] FIG. 3 illustrates a data flow according to an operation of providing a personalized exercise coaching guide of an electronic device according to one embodiment.

[0015] Figure 4 is a block diagram of a wearable electronic device according to one embodiment.

[0016] FIG. 5 is a flowchart illustrating a real-time exercise coaching monitoring method based on an exercise coaching guide level of an electronic device according to one embodiment.

[0017] FIG. 6 is a flowchart illustrating a method for determining a coaching guide level of an electronic device according to one embodiment.

[0018] FIG. 7 is a table illustrating exercise coaching guide levels of an electronic device according to one embodiment.

[0019] FIG. 8 is a table illustrating a coaching guide and feedback guide of an electronic device according to one embodiment.

[0020] FIG. 9 is a flowchart illustrating a method for changing an exercise coaching guide level during real-time exercise monitoring of an electronic device according to one embodiment.

[0021] FIG. 10 is a table illustrating a feedback guide generated according to a changed exercise coaching guide level of an electronic device according to one embodiment.

[0022] FIGS. 11A and 11B are examples of a user data input screen of an electronic device according to one embodiment.

[0023] FIGS. 11c and 11d are examples of screens displaying user movement data of an electronic device according to one embodiment.

[0024] FIGS. 12a, 12b, and 12c are examples of exercise coaching guide screens of an electronic device according to one embodiment.

[0025] FIGS. 13A and 13B are examples of exercise monitoring screens of a wearable electronic device according to one embodiment.

[0026] FIG. 14 is an example of an exercise coaching guide screen of a wearable electronic device according to one embodiment.

[0027] FIG. 15 is an example of a screen for changing the exercise coaching guide level of a wearable electronic device according to one embodiment.

[0028] FIG. 16 is an example of an exercise completion feedback screen of a wearable electronic device according to one embodiment.

[0029] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0030] An embodiment of the present disclosure is described below with reference to the attached drawings.

[0031] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0032] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0033] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0034] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0035] The number of processors (120) may be one or more. For example, the processor (120) may have a multi-core processor structure such as a dual core, quad core, or hexa core.

[0036] The processor (120) can control the operations of the electronic device (101) by executing instructions stored in the memory (130). For example, the processor (120) can correspond to multiple processors that divide multiple operations among the processors and perform them collectively (or collectively).

[0037] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0038] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0039] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0040] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0041] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0042] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0043] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0044] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) to an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multi-media interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0045] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0046] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0047] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0048] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0049] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0050] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0051] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large-scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for realizing URLLC.

[0052] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0053] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0054] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0055] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0056] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0057] FIG. 2 is a flowchart illustrating an operation of an electronic device for providing a personalized exercise coaching guide according to one embodiment.

[0058] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0059] According to one embodiment, steps 210 to 260 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1).

[0060] An electronic device according to one embodiment (e.g., electronic device (101) of FIG. 1) can continuously monitor a user's real-time exercise performance and learn feedback information for the exercise coaching guide to personalize the exercise coaching guide to be received by the user based on the user's condition and exercise purpose.

[0061] In step 210, an electronic device (101) according to an embodiment may determine an exercise coaching guide level for performing real-time exercise monitoring of a user using a rule-based machine learning model based on a personalized exercise purpose, condition score, and exercise performance level of the user. The coaching guide level may serve as a coaching direction indicator that serves as a basis for generating coaching feedback while monitoring the user's exercise in real time. The electronic device (101) may generate a coaching guide that adjusts the coaching content of a given exercise process (e.g., range of motion, exercise intensity, number of repetitions, exercise time, speed, rest time, and motion accuracy error range) using a large language model (LLM), or may generate coaching feedback including a feedback guide message to be provided to the user. The electronic device (101) may monitor the user's exercise and provide continuous personalized exercise coaching based on the guide level. The LLM refers to an artificial neural network-based language model that has learned a large amount of text data through pre-learning. LLMs can contain many more parameters than typical language models (e.g., over 10 billion).

[0062] At step 220, the electronic device (101) according to one embodiment may initiate exercise coaching that provides guidance and real-time monitoring for a series of movements related to the user's exercise. The exercise coaching may be provided, for example, in the form of a health application. The exercise coaching may include a process of monitoring the user's exercise movements and biometric information while performing a set exercise process based on a type of exercise set by the user input. For example, in response to a user input selecting a squat exercise, the electronic device (101) may generate exercise coaching that provides coaching guidance and coaching feedback, including an exercise process for the squat exercise (e.g., posture guidance, number of repetitions, rest time, and performance time), and provide the coaching to the user through one or more output devices (e.g., a display, a speaker, an external wearable electronic device).

[0063] At step 230, the electronic device (101) according to one embodiment can detect whether the user has started exercising using a motion detection sensor (e.g., the sensor module (176) of FIG. 1). The electronic device (101) can activate the motion detection sensor and detect the user's movement. The electronic device (101) can maintain a standby state until it detects the user's initiation of exercise.

[0064] In step 240, the electronic device (101) according to one embodiment may perform real-time exercise monitoring and provide real-time coaching in response to detecting that the user has started exercising. The electronic device (101) may monitor the exercise by detecting the user's movement or bio-signals using at least one of a camera (e.g., the camera module (180) of FIG. 1) or a sensor (176) of the electronic device (101). The electronic device (101) may generate at least one coaching guide or feedback guide according to an exercise coaching guide level and provide the guide to the user through an output device during the exercise process. The electronic device (101) may determine whether the level of coaching guide provided to the user is appropriate based on the user's behavioral response to the provided exercise coaching and whether the coaching is reflected. The electronic device (101) may continuously change the direction of coaching during the exercise process by changing the coaching guide level in real time based on the determination of the appropriateness of the coaching guide level.

[0065] At step 250, the electronic device (101) according to one embodiment can detect whether the user has finished exercising using the motion detection sensor (176). The electronic device (101) can repeat step 240 as long as it does not detect that the user has finished exercising.

[0066] At step 260, the electronic device (101) according to one embodiment may, in response to detecting that the user has finished exercising, provide coaching feedback upon completion of the exercise. The electronic device (101) may collect movement information, biosignal change information, coaching guides according to the exercise process, and feedback guides detected while the user is exercising, and use them as learning data for a personalized exercise performance model that learns exercise patterns for exercise performance analysis. As user data according to exercise performance accumulates, the personalized exercise performance model may be optimized for the user. The electronic device (101) may personalize the coaching guides that the user will receive based on the user's condition and exercise purpose, and continuously learn data according to the user's exercise performance.

[0067] FIG. 3 illustrates a data flow according to an operation of providing a personalized exercise coaching guide of an electronic device according to one embodiment.

[0068] An electronic device (e.g., electronic device (101) of FIG. 1) according to an embodiment collects data for determining an exercise coaching guide level from user body information and user exercise information, determines a coaching guide level using an artificial intelligence model (e.g., machine learning) as input for the collected data, and performs real-time exercise monitoring of a user using a wearable electronic device (e.g., watch-type wearable electronic device (301), TWS (true wireless stereo) earphone electronic device (302), ring-type wearable electronic device (303)) worn by a user during exercise, while providing a coaching guide according to the level, and collects and analyzes feedback information generated during exercise.

[0069] An electronic device (101) according to an embodiment may include user health information (311), a personalized exercise performance model (312), a data collection module (320), a coaching guide level determination module (330), an exercise monitoring module (340), and a user feedback management module (350). Each component may be a functional unit for describing the operation of the electronic device (101) according to an embodiment and may not correspond to a physical hardware component. For example, the user health information (311) and the personalized exercise performance model (312) may be included in a memory (e.g., the memory (130) of FIG. 1). At least a part of the data collection module (320), the coaching guide level determination module (330), the exercise monitoring module (340), or the user feedback management module (350) may be performed by a processor (e.g., the processor (120) of FIG. 1). The processor (120) may include at least one processing circuit, and the operation of each module may be performed by each processing circuit.

[0070] An electronic device (101) according to one embodiment can receive user information required by user input (310). For example, the electronic device (101) can receive at least one of an exercise purpose or an exercise type.

[0071] User health information (311) may include body data, exercise record information, and physical condition information. The body data may be collected from user profile information (e.g., height, weight, gender, and age) based on user input. The exercise record information may include various information monitored during exercise previously performed by the user through the electronic device (101) or the user's wearable electronic devices (301, 302, and 303). For example, the exercise record information may include heart rate during exercise, exercise intensity, exercise distance, exercise speed, recovery time for rest time, and maximum oxygen uptake (Vo2max). The exercise record information may be stored by calculating the average, maximum, minimum, and variance of accumulated data. The exercise record information includes data on recently performed exercise during a set period, and old data may be excluded, and the set period may be changed. The physical condition information may include information related to sleep and activity level. For example, physical condition information may include sleep duration, heart rate during sleep, heart rate variability (HRV) during sleep, and sleep duration regularity data collected over a set recent period.

[0072] The personalized exercise performance model (312) may include an artificial intelligence model (e.g., machine learning) that has learned the user's exercise patterns. The artificial intelligence model can analyze sensor data acquired through a wearable electronic device (e.g., a watch-type wearable device (303)) while the user is exercising to understand the user's exercise patterns, including exercise habits and preferences. The exercise patterns can be expressed in numerical values, such as frequency, time, type, intensity, duration, location, and recovery patterns. For example, a trained artificial intelligence model can determine which exercise a user prefers at a specific time, how often the user exercises, and what characteristics the user exhibits during a specific exercise.

[0073] An artificial intelligence model according to one embodiment may be trained based on direct data regarding exercise records (e.g., number of repetitions, speed, distance, duration of exercise) and indirect data regarding exercise environments or operating methods (e.g., rest time, ambient temperature, indoor / outdoor presence). In addition, exercise record information included in user health information (311) (e.g., maximum heart rate during exercise, recovery rate for rest time, maximum oxygen uptake) may also be included in the training data. The artificial intelligence model may be retrained based on sensor data accumulated according to the user's exercise performance and feedback information according to an exercise coaching guide.

[0074] The data collection module (320) may include a purpose management module (321), a condition score module (322), and a user exercise performance analysis module (323). The electronic device (101) may determine an exercise coaching guide level to provide personalized exercise coaching guidance while monitoring the user's exercise. The electronic device (101) may collect data necessary to determine the exercise coaching guide level in response to a user input, such as "start today's exercise."

[0075] The purpose management module (321) can receive data regarding exercise purposes based on user input. For example, the purpose management module (321) can select keywords related to exercise purposes or receive sentences regarding exercise purposes from text or user speech. The purpose management module (321) can classify exercise purposes based on the received keywords or sentences into defined exercise purpose items. The types of exercise purposes may include, for example, at least some of record-breaking, weight control, core balance improvement, stamina improvement, mental stability, muscle strengthening, flexibility enhancement, body profile photography, competition preparation, and bodybuilding. Each type of exercise purpose can be subdivided and specified as a number (target weight, competition date). The user's exercise purpose may include one or more items. For example, exercise purposes may include record-breaking and muscle strengthening based on the user's selection. Exercise purposes may be determined by user input at the time of starting the initial exercise, or may be changed, added, or deleted at the user's request.

[0076] According to one embodiment, an electronic device (101) may output a suggestion for changing the exercise purpose based on an analysis of the user's exercise performance. If the performance improvement is maintained, the electronic device (101) may output a message suggesting to raise the exercise purpose. The electronic device (101) may generate recommended exercise purpose keywords based on the user's profile information, previous exercise records, and current condition data. The electronic device (101) may generate recommended exercise purpose keywords by analyzing the user's average exercise performance data (e.g., average exercise time, calories burned), body data, and diet data. For example, the electronic device (101) may recommend keywords such as "record update" and "bodybuilding" for a male user who is gradually increasing the number of times and intensity of exercise for a competition.

[0077] The condition score module (322) can calculate an energy score to determine the user's exercise performance ability based on the user's health information (311). The energy score can represent a representative indicator of the user's condition. A higher energy score indicates a state in which the user is able to be active and focused, while a lower energy score indicates a state in which rest is needed. An electronic device (101) according to one embodiment can calculate an energy score based on sleep and activity factors. The sleep and activity factors can be defined as shown in Table 1.

[0078] Item dataSleep time averageAverage sleep time for the last 7 daysSleep time regularitySleep time trend analysis for the last 7 daysBedtime / wake time regularitySleep / wake trend analysis for the last 7 daysSleep timeSleep / wake time analysis for the last 7 daysPrevious day activityActivity time, exercise records, heart rate information during exercise detected by activity sensor or biometric sensor for the previous dayHeart rate during sleepLowest heart rate during major sleep zoneHeart rate variability during sleepHighest heart rate variability during major sleep zone

[0079] The items in Table 1 are exemplary, and some items may be modified, deleted, or added. For example, items such as "if the previous day's sleep time was below a threshold" or "if the previous day's exercise time was above a threshold" may be added. The energy score is an indicator of the user's condition for exercising and may be reflected in the exercise coaching guide level. The electronic device (101) can determine the condition level based on the energy score. The condition level can be quantified by level, and the energy score that distinguishes the level may vary for each user. For example, the condition level may be divided into five levels (poor / low / normal / high / best), and one of the five levels may be determined based on the sum of the user's current energy score. For example, in response to determining that the user's condition is high based on the energy score, the electronic device (101) may induce the user to perform improved performance compared to his or her existing exercise ability, or set a coaching direction to perform a more accurate posture. According to one embodiment, the electronic device (101) may determine the user's condition level with equal weights for each sub-item of the energy score. Since the sub-items of the energy score reflect the user's average sleep and average activity level, equal weights may be applied.

[0080] Alternatively, the electronic device (101) according to one embodiment may set different weights for the detailed items of the energy score and determine the user's condition level. For example, on the last day of an exam period, the user may have less sleep time than average, have a low overall index, but have a high heart rate variability during sleep. The electronic device (101) may set a low weight for sleep time and a high weight for heart rate variability related to stress resilience or recovery. In this way, the electronic device (101) may adjust the weights for the detailed items of the energy score to reflect the situation in which the exam, which is the cause of stress, has ended.

[0081] The user's exercise performance analysis module (323) can analyze the current exercise performance ability to determine the exercise coaching guide level. The electronic device (101) can determine the exercise performance ability level for performing the current exercise based on previous exercise records and feedback information using the personalized exercise performance model (312). The exercise performance ability level can be quantified by level. For example, the exercise performance ability level can be sequentially divided into beginner, entry-level, intermediate, expert, and professional levels. The exercise performance ability level can be applied equally to the user, and the exercise coaching direction can be determined corresponding to each level. For example, the electronic device (101) can generate an exercise coaching guide that frequently provides cheering messages to a beginner user, and can generate an exercise coaching guide that provides goal-stimulating messages to a professional user when the exercise speed decreases.

[0082] The coaching guide level determination module (330) can determine the coaching guide level using a rule-based learning model based on the current exercise purpose data, condition score data, and user exercise performance ability data collected by the data collection module (320). The electronic device (101) can set rules for the ratio of influence of each condition (e.g., combination of collected data) and continuously update the learning model to reflect the user's exercise pattern.

[0083] In one embodiment, the coaching guidance levels may be broadly categorized into low level, mid level, and high level. Each level may be further subdivided into minus (-), mid level, and plus (+). For example, the low level may be low-, low, or low+. In the low level, the coaching guidance may be adjusted toward a performance direction lower than the user's average exercise performance ability. In the mid level, the coaching guidance may be provided toward a performance direction that maintains the user's average exercise performance ability. In the high level, the coaching guidance may be adjusted toward a performance direction higher than the user's average exercise performance ability. The average exercise performance ability range may include at least some of the following: exercise type, posture accuracy, exercise sets or repetitions, or exercise speed. The above coaching guidance levels are exemplary only, and in various embodiments, the composition of the coaching guidance levels may be different and further subdivided.

[0084] An electronic device (101) according to an embodiment may generate one or more coaching guides and coaching feedbacks based on a coaching guide level. In an embodiment, the coaching guides may be generated for detailed items of an exercise process, including at least some of exercise performance range, exercise intensity, or exercise posture accuracy. In addition, the coaching feedback may include an exercise coaching guide message generated based on the LLM. The exercise coaching guide message may include main items for which the exercise coaching guide level is determined, detailed items of the exercise process that vary according to the exercise coaching guide level, and a coaching message personalized for the user.

[0085] In one embodiment, the electronic device (101) may generate coaching feedback based on a determination that the user's physical condition is not good in response to determining that the coaching guidance level is low. For example, while the user is performing squats, the electronic device (101) may adjust the exercise performance range by lowering the sensing threshold range for the sitting posture so that the user can complete the squat movement more easily than usual. The electronic device (101) may suggest a type of exercise that can help the user reduce tension and relax, and generate coaching feedback so that the user can focus on the exercise. During a difficult exercise routine, the electronic device may focus on maintaining balance information and recovery values ​​during aerobic exercise, and may adjust the exercise intensity to lower the intensity during strength training such as squats.

[0086] In one embodiment, the electronic device (101) may generate coaching feedback based on a judgment that the user's condition is not good but that the exercise goal is achieved, in response to a coaching guidance level that is usually at a negative level and a set exercise goal. For example, if the user's exercise goal is set to "short-term muscle strength improvement," the electronic device (101) may generate coaching feedback so that the exercise performance range or intensity does not differ significantly from usual even when the user is not in good condition. Taking into account the poor condition, the electronic device (101) may adjust the coaching feedback in the direction of increasing the sensing threshold in response to confirming that the accuracy and recovery value of the movement that sufficiently loosens the body in relaxation exercise are maintained above a certain level. If the accuracy of the movement is not maintained, the electronic device (101) may adjust the coaching feedback so that the number of repetitions of the movement can be filled at a low threshold level so as not to lose the feel of the exercise.

[0087] In one embodiment, the electronic device (101) may generate coaching feedback based on a judgment that the user's condition is good and that the exercise goal is achieved, in response to a coaching guidance level being usually at a plus level and an exercise goal being set. While the user is performing squats, the electronic device (101) may precisely adjust the range of accuracy of posture judgment in response to a judgment that the user's condition is very good, thereby adjusting the accuracy of the exercise posture to induce a correct posture, or may adjust the exercise intensity to induce additional repetitions or additional weight. However, if the exercise goal is set to "maintain records or maintain physical strength," the electronic device (101) may readjust the adjusted exercise range or intensity so that it does not differ significantly from usual.

[0088] The exercise monitoring module (340) can perform real-time exercise monitoring based on a personalized exercise coaching guide. The exercise monitoring module (340) acquires real-time exercise sensor data (341) using the user's wearable electronic device (301, 302, 303), and analyzes the acquired sensor data through the exercise performance analysis module (342) to determine in real time whether the user's exercise performance level is appropriate for the exercise coaching guide level.

[0089] Real-time exercise sensor data (341) may include the user's bio-signals and movement signals acquired through one or more sensors built into an electronic device (101) that the user carries or a wearable electronic device (e.g., a watch-type wearable device (301), a TWS device (302), a ring-type wearable device (303)) that the user wears while exercising.

[0090] In one embodiment, the electronic device (101) may collect data acquired through a camera (e.g., a camera module (180) of FIG. 1) or a sensor (e.g., a sensor module (176) of FIG. 1) that detects the user's movement or biosignals based on a user input for an exercise coaching request.

[0091] In one embodiment, one or more wearable electronic devices (301, 302, 303) connected to the electronic device (101) may collect data acquired through sensors that detect user movements or bio-signals in response to a user input for an exercise coaching request or a request from the electronic device (101), and transmit the data to the electronic device (101). The electronic device (101) may store sensor data received from the wearable electronic devices (301, 302, 303) in real-time exercise sensor data (341).

[0092] The exercise performance analysis module (342) can monitor the user's exercise in real time based on real-time exercise sensor data (341) and determine the degree of suitability according to the exercise coaching guide level. The exercise performance analysis module (342) can analyze the type, intensity, posture accuracy, and numerical records (e.g., speed, distance, and number of times) of the exercise being performed by the user in real time based on the exercise coaching guide level. The exercise performance analysis module (342) can transmit the degree of suitability according to the exercise coaching guide level to the user feedback management module (350) or the coaching guide level determination module (330). The coaching guide level determination module (330) can determine to adjust the level in response to determining that the exercise performance result is not suitable or is significantly superior compared to the exercise coaching guide level. The user feedback management module (350) can generate a feedback guide message according to the degree of suitability according to the exercise coaching guide level and provide it to the user in real time. The exercise performance analysis module (342) can recognize the user's exercise motion or response information in response to the exercise coaching guide (e.g., a feedback guide message) being provided. The exercise performance analysis module (342) can detect environmental information in which the current exercise coaching guide is provided, whether exercise status indicators are improving, the consistency between the timing of the guide being provided and the user's motion, and the change trend of the user's exercise-related sensor data, and repeatedly evaluate the suitability of the exercise coaching guide level.

[0093] The user feedback management module (350) can generate and manage coaching feedback according to the exercise coaching guide level. In one embodiment, the coaching feedback can be generated for detailed items of an exercise process, including at least some of exercise performance range, exercise intensity, or exercise posture accuracy. In addition, the coaching feedback can include a feedback message for an exercise coaching guide generated based on the LLM. The feedback message can include the current exercise coaching guide level, the basis for determining the guide level, and coaching content changed according to the guide level. The current exercise coaching guide level can be reflected in the feedback message in relation to a positive or negative degree from low, medium, or high. The basis for determining the level can be information about the exercise purpose, condition score, and the user's exercise performance ability reflected in the feedback message. The coaching content changed according to the guide level can include information about the error range of accuracy, the number of exercises, and exercise intensity adjustment. For example, the user feedback management module (350) can generate a feedback message such as, "Your energy score is high today. I think it's because you got enough rest yesterday. If you're in such good condition, you might as well try to break your record. So, I'm going to try to do squats a little more intensely today. Should I start squatting by adding a 5kg plate?" In the feedback message, the "high energy score" part can indicate condition score information as the basis for level determination. The "if you're in good condition, you might as well try to break your record" part can indicate that it reflects the user's exercise purpose information. The "a little more intensely" part and the "add a 5kg plate" part can indicate coaching content that has been changed according to the current guide level.

[0094] The user feedback management module (350) can determine whether to maintain or change the current guide level based on the appropriateness of the coaching guide level analyzed by the exercise performance analysis module (342). In response to a decision to change the guide level, the user feedback management module (350) can request the coaching guide level determination module (330) to change the guide level. If the guide level changes during the user's exercise, the user feedback management module (350) can create new coaching content based on the changed guide level.

[0095] Figure 4 is a block diagram of a wearable electronic device according to one embodiment.

[0096] A wearable electronic device (301) according to an embodiment (e.g., the wearable electronic device (301) of FIG. 3) may detect a user's movement or bio-signals during exercise and provide a voice message or guide screen according to an exercise coaching guide. The wearable electronic device (301) may include at least a portion of a processor (3010), a memory (3020), a communication circuit (3030), a display (3040), a speaker (3050), a microphone (3060), an activity sensor (3070), and a bio-sensor (3080).

[0097] The processor (3010), memory (3020), communication circuit (3030), display (3040), speaker (3050), and microphone (3060) may correspond to each component of the electronic device (101) of FIG. 1.

[0098] The activity sensor (3070) can detect the user's movements. The activity sensor may include at least one of an acceleration sensor, a gyro sensor, a global positioning system (GPS), a geomagnetic sensor, or a barometric pressure sensor. The activity sensor (3070) can identify the location information (altitude, latitude and longitude, directionality) of the user wearing the wearable electronic device (301) and can identify patterns of movement gestures or actions. The processor (3010) can determine the type of exercise, intensity (strength), accuracy of the action, and exercise distance based on the data acquired by the activity sensor (3070).

[0099] The biometric sensor (3080) may include at least some of a photoplethysmography (PPG), an electrocardiogram (ECG), a bioelectrical impedance analysis (BIA), a thermometer, and a skin optical sensor. The PPG sensor can measure heart rate and blood flow by irradiating light to the skin and detecting changes in the light reflected from the skin that change according to blood flow. The processor (3010) can monitor heart rate using the PPG sensor and measure blood pressure or stress level. The ECG sensor can measure the rate and consistency of the user's heartbeat. The BIA sensor can measure body composition (muscle, fat) by measuring internal impedance. The processor (3010) can analyze the body composition together with the user's physical data (e.g., height, weight, gender, age) to measure body fat percentage, body water content, muscle mass, or body mass index (BMI). Optical skin sensors can estimate antioxidant levels through skin spectroscopy and fluorescence measurements. Spectroscopy is a technology that analyzes the spectrum of light absorbed or reflected by substances, allowing it to measure skin chemical composition, pigmentation, and moisture content. Fluorescence is a technology that detects the fluorescence emitted by substances within the skin after irradiating the skin with light of a specific wavelength. The pattern of fluorescence emission can be used to assess skin condition (damage, pigmentation, freckles). Optical skin sensors can also measure changes in skin elasticity, wrinkles, and pigmentation through skin spectroscopy, allowing them to estimate biological skin age.

[0100] The processor (3010) can check heart rate (HR), heart rate variability (HRV), body composition, respiratory rate, blood oxygen (SpO2), and stress index based on the biosignals acquired by the biosensor (3080). The processor (3010) can calculate maximum oxygen consumption (Vo2Max) during exercise, sleep stage analysis, or sleep quality evaluation based on sensor data acquired by the activity sensor (3070) and the biosensor (3080).

[0101] According to one embodiment, a processor (3010) may collect real-time exercise-related data (speed, posture, duration, intensity), health data (HR, HRV, Vo2Max, respiration rate), and surrounding environment information (e.g., temperature, humidity, altitude, indoor / outdoor status) of a user during exercise, and transmit the data to an exercise monitoring module (340) of an electronic device (e.g., electronic device (101) of FIG. 3).

[0102] The number of processors (3010) may be one or more. For example, the processor (120) may have a multi-core processor structure such as a dual core, quad core, or hexa core.

[0103] The processor (3010) can control the operations of the wearable electronic device (301) by executing instructions stored in the memory (3020). For example, the processor (3010) can correspond to multiple processors that divide multiple operations among the processors and perform them collectively (or collectively).

[0104] FIG. 5 is a flowchart illustrating a real-time exercise coaching monitoring method based on an exercise coaching guide level of an electronic device according to one embodiment.

[0105] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0106] According to one embodiment, operations 510 to 560 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1, electronic device (101) of FIG. 3).

[0107] An electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1, the electronic device (101) of FIG. 3) may determine an exercise coaching guide level based on the user's exercise purpose, condition score, and exercise performance level, and may monitor the user's exercise in real time while providing a coaching guide and feedback guide according to the exercise coaching guide level. Each operation of FIG. 5 may be described with reference to FIG. 3.

[0108] In operation 510, an electronic device (101) according to an embodiment may receive user input regarding an exercise purpose. For example, the electronic device (101) may receive the keywords "weight loss" and "strength training" as input by the user. Based on the received keywords, the purpose management module (321) of the electronic device (101) may set the user's exercise purpose to weight loss and strength training.

[0109] In operation 520, an electronic device (101) according to an embodiment may collect data for exercise coaching monitoring based on user information, and analyze the collected data to determine an exercise coaching guide level. The user information may include user health information (311) and a personalized exercise performance model (312). The data collection module (320) of the electronic device (101) may confirm the user's exercise purpose, calculate the current user's condition score, and analyze the user's exercise performance ability. The condition score module (322) may calculate an energy score based on the user's recent sleep information and activity level stored in the user health information (311), and may determine the condition score by further considering additional information (e.g., weights for detailed items of the energy score). The user exercise performance ability analysis module (323) may determine the current exercise performance ability level using the personalized exercise performance model (312) in which exercise patterns are learned based on user data.

[0110] In operation 530, an electronic device (101) according to an embodiment may determine a coaching guide level using a rule-based learning model based on analysis results, i.e., the user's exercise purpose, current condition score, and the user's exercise performance level. The coaching guide level is an indicator indicating the directionality of exercise coaching, and the electronic device (101) may generate a coaching guide and feedback guide based on the coaching guide level.

[0111] In operation 540, an electronic device (101) according to an embodiment may provide coaching content based on the coaching guide level during exercise. The coaching content may include at least one of a coaching guide and a feedback guide. Multiple coaching content may be generated corresponding to one or more points throughout the exercise process.

[0112] In operation 550, an electronic device (101) according to an embodiment can monitor a user's exercise performance motion in real time during exercise, and analyze the real-time exercise performance process based on a coaching guide level. To monitor the user's exercise performance motion, a camera or a sensor of the electronic device (101) can be used, and a wearable electronic device (e.g., wearable electronic devices (301, 302, 303) of FIG. 3) worn by the user can be used. The electronic device (101) can check whether the user is carrying the electronic device (101), whether an image of the user's movement can be obtained through a camera, whether the user's wearable electronic device (301, 302, 303) is being worn, whether a communication connection is established with the wearable electronic device, and determine a target device (e.g., a camera, a sensor, a wearable electronic device) for monitoring the user's movement in real time. In one embodiment, when a user wears a watch-type wearable electronic device (301) and a TWS earphone electronic device (302) and performs exercise, the electronic device (101) determines the watch-type wearable electronic device (301) and the TWS earphone electronic device (302) as target devices to be monitored, and can receive real-time sensor data (e.g., sensor signals acquired by the activity sensor (3070) and the biometric sensor (3080) of FIG. 4) and voice data (e.g., voice signals acquired by the microphone of the TWS earphone electronic device (302) of FIG. 3) from the watch-type wearable electronic device (301) and the TWS earphone electronic device (302).

[0113] In operation 560, the electronic device (101) according to one embodiment can determine whether the exercise performance being monitored in real time is suitable for the coaching guide level. For example, the electronic device (101) can determine whether the exercise posture is correct and whether the exercise intensity is suitable for the coaching guide level based on the user's movement information. In response to determining that the current coaching guide level is suitable, the electronic device (101) can perform operation 540 to maintain the guide level. In response to determining that the current coaching guide level is not suitable, the electronic device (101) can change the guide level by performing operation 530. The electronic device (101) can continuously change the coaching content to be optimized for the individual user by reflecting the real-time monitoring results.

[0114] FIG. 6 is a flowchart illustrating a method for determining a coaching guide level of an electronic device according to one embodiment.

[0115] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0116] According to one embodiment, operations 610 to 660 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1, electronic device (101) of FIG. 3).

[0117] An electronic device according to one embodiment (e.g., electronic device (101) of FIG. 1, electronic device (101) of FIG. 3) can generate a coaching guide level based on the user's exercise purpose, condition score, and exercise performance ability of the user, and adaptively change the level based on the results of real-time exercise performance monitoring.

[0118] In operation 610, an electronic device (101) according to an embodiment may receive user input regarding an exercise purpose or type of exercise. The electronic device (101) may set a specific direction for exercise coaching based on the exercise purpose selected by the user. For example, if the exercise purpose is muscle strength improvement or body profile, the exercise coaching may have a "high intensity" direction. This directionality may affect whether the guidance level is determined to be in the High Level direction. The electronic device (101) may determine the coaching guidance level by reflecting the exercise purpose and type input by the user.

[0119] In operation 620, an electronic device (101) according to an embodiment can check user health data. The user health data can be read from a database containing information related to the user's health (e.g., user health information (311) of FIG. 3). For example, the electronic device (101) can check the user's body information (e.g., height, weight, body fat, muscle mass, age, and gender), the user's recent sleep data, and the user's recent activity data to check the current user's health data. If the user's health data does not exist or the latest data is required, the electronic device (101) can provide an interface through which the user can input information. For example, if the user's weight information has been updated for more than 3 months, the electronic device (101) can display a message on the display screen to prompt the user to input the latest weight.

[0120] In operation 630, an electronic device (101) according to an embodiment may calculate a current user condition score. The electronic device (101) may calculate an energy score and a condition score based on the user's health data. The energy score is a numerical value calculated based on the user's biometric information, such as recent sleep and activity levels, and the condition score may be determined by further considering additional information. The condition score may represent the expected level of condition for performing an exercise. For example, even if the energy score is calculated low due to the user's poor sleep quality over the past few days, the electronic device (101) may additionally consider the fact that the user has completed a final exam today to determine that the condition score is not low. Depending on various circumstances, the condition score may not be proportional to the energy score. Since the user's condition score is determined based on recent data, it may vary daily.

[0121] In one embodiment, the coaching guide level may be similar to a condition score. If the electronic device (101) determines that the user is in good condition, it may determine a level value closer to High Level to enable improved performance compared to the user's existing athletic ability. If the user is determined to be in poor condition, it may determine a value closer to Low Level to enable reduced performance compared to the user's existing athletic ability.

[0122] In operation 640, an electronic device (101) according to an embodiment can evaluate the current user's exercise performance ability. The electronic device (101) can analyze the user's exercise performance ability based on the user's exercise pattern and record information. The electronic device (101) can evaluate the current exercise performance ability using an artificial intelligence model (e.g., the personalized exercise performance model (312) of FIG. 3) learned from the user's previous exercise records and sensor data.

[0123] In operation 650, an electronic device (101) according to an embodiment may determine a coaching guidance level by considering at least a portion of the user's exercise purpose, exercise type, health data, condition score, or current exercise ability level using a rule-based learning model. The user's exercise purpose, exercise type, health data, condition score, or current exercise ability level may be input values ​​of the rule-based learning model.

[0124] In one embodiment, the coaching guide level may be categorized into low, medium, and high levels based on the user's usual exercise performance ability. The coaching direction and content may be determined based on the coaching guide level. The specific coaching items whose scope is adjusted based on the coaching guide level may vary depending on the exercise type, and the adjustment criteria may be determined in various ways, as shown in Table 2.

[0125] Variable range / Coaching guide level highmidlow Exercise intensity Increase total number of repetitions / Shorten rest time / Induce additional repetitions Maintain user's existing exercise performance range Decrease total number of repetitions / Increase rest time Posture accuracy Reduce error in accuracy judgment range Maintain user's existing exercise performance range Expand error in accuracy judgment range Exercise speed Shorten pace / Shorten execution time Maintain user's existing exercise performance range Extend pace / Extend execution time

[0126] In Table 2, when the coaching guidance level is high, the electronic device (101) monitors the user's exercise process, and the range of variation in exercise intensity can increase the total number of times performed, shorten the rest time, or induce additional performance. In operation 660, the electronic device (101) according to one embodiment can initiate exercise coaching. Exercise coaching can include providing coaching guidance and feedback guidance while monitoring the user's exercise according to a set exercise process.

[0127] FIG. 7 is a table illustrating exercise coaching guide levels of an electronic device according to one embodiment.

[0128] In one embodiment, the exercise coaching guide levels may be divided into low, medium, and high levels based on the user's usual exercise performance ability, and each level may be further subdivided into minus (-), medium, and plus (+) levels.

[0129] Referring to Figure 7, an example of an exercise coaching guide level can be divided into nine levels from low- to high+. Exercise types can include, for example, aerobic running, aerobic cycling, aerobic swimming, anaerobic sprinting, and anaerobic strength training. Exercise types can be added or deleted. Exercise goals can include breaking records, maintaining records, losing weight, maintaining weight, gaining weight, improving core balance, improving endurance, and strengthening muscles. Each exercise goal can be defined with a corresponding keyword. For example, weight loss can be defined by the keywords "lose weight" and "diet." The condition score is a percentile score and can be divided into five levels according to the score range. For example, as shown in Figure 7, it can be set to poor, low, moderate, high, and prime. The score distribution that distinguishes each level may vary for each user. In Figure 7, the best case is defined as 95 to 100 points, but some users may define it as 90 to 100 points. The motor skill assessment stages can be sequentially categorized into beginner, entry-level, intermediate, proficient, and professional (expert) levels. Even for the same user, motor skill assessments can vary depending on the type of exercise or exercise purpose.

[0130] For example, an electronic device (101) according to one embodiment may determine a coaching level as mid when a user selects aerobic running, the exercise purpose is to improve endurance, the current condition score is high, and the exercise ability evaluation stage is beginner level.

[0131] FIG. 8 is a table illustrating a coaching guide and feedback guide of an electronic device according to one embodiment.

[0132] An electronic device (101) according to one embodiment can determine a coaching guide level based on an exercise purpose, exercise type, current condition score, and current exercise ability assessment, and can generate a coaching guide and feedback guide based on the coaching guide level using LLM. The exercise purpose, exercise type, current condition score, current exercise ability assessment, and coaching guide level can be input values ​​of LLM.

[0133] Figure 8 is a table showing the results of an electronic device (101) determining a coaching level and generating a coaching guide and feedback guide accordingly, through three examples.

[0134] In the first example, if an adult male selects a marathon running exercise, aims to break a record, has a high current condition score, and is analyzed to have a professional-level exercise ability, the electronic device (101) may determine the coaching level as high+. At this time, the electronic device (101) may analyze the user's previous exercise pattern (user data) of a resting heart rate of 55, a maximum heart rate of 195, a Vo2Max of 79, a cadence of 180, an average pace / speed of 3:35 min / km, and an average exercise distance of 10 km to evaluate the user's exercise performance ability. In response to the highest (high+) level of coaching level, the electronic device (101) may generate a coaching guide that increases the target values ​​for the cadence, pace, and exercise distance of the marathon run by 10%. The electronic device (101) may output a feedback guide such as "Do you think you can break your record today? Would you like to give it a try? I'll help you!" at the time of starting exercise coaching, in response to the highest coaching level. The electronic device (101) may monitor the user's movements and vital signals during exercise and output feedback guide messages such as "So far so good!", "You're getting close to your previous record!", "Should I pick up the pace a bit more?", "Your stride is a bit narrower than usual. Should I run a bit farther?", and "Let's maintain the pace for just 1 km more." The feedback guide message reflects the coaching guide, and the information that today's condition can break the record may be a part that presents the basis (condition score) for determining the coaching level. The message to challenge the record may be a part that reflects the basis (exercise purpose) for determining the coaching level.

[0135] In a second example, if an adult female chooses swimming, has an exercise goal of improving endurance, has a current condition score of average, and is analyzed as having a beginner level in swimming, the electronic device (101) may determine the coaching level as mid. In order to evaluate the user's exercise performance ability, the electronic device (101) may analyze the user's previous exercise pattern (user data) of maximum heart rate 180, resting heart rate 70, Vo2Max 40, average pace 31:10 min / km, total strokes 134, exercise distance 375 m, and average SWOLF (efficiency) 55. In response to the mid-level coaching level, the electronic device (101) may generate a coaching guide that maintains the user's usual exercise performance ability level (existing target value). The electronic device (101) may output a feedback guide such as "I support you for consistently challenging yourself. If you do as well as yesterday, you will be successful!" at the time of starting exercise coaching, in response to the coaching level being set to the normal level and the decision to maintain the existing target level. The electronic device (101) may monitor the user's movements and vital signals during exercise and output feedback guide messages such as "The left-right balance was off in the previous section. Should we adjust the tempo? One, two, one, two", "Your breathing is unstable. Let's catch your breath for a moment and start again", and "This is enough." In the feedback guide, "I support you for consistently challenging yourself" reflects the exercise purpose (improvement of endurance) as the basis for determining the coaching level. "This is enough" may reflect the result of the coaching guide that decided to maintain the target level.

[0136] In a third example, the electronic device (101) may determine the coaching level as low+ in response to the user selecting squats, determining muscle strengthening as the exercise goal, determining the current condition score as low, and determining the exercise performance ability evaluation level as intermediate. The electronic device (101) may analyze the user's previous exercise pattern (user data) of 50 repetitions, 3 sets, 2 minutes of rest, and 85% movement accuracy in order to evaluate the user's exercise performance ability. In response to the low (low+) level of coaching level, the electronic device (101) may determine to lower the user's usual exercise performance ability level (existing target value) by 20%, and specifically, may generate a coaching guide according to 40 repetitions, 3 sets, 70% movement accuracy, and 5 minutes of rest. The electronic device (101) may output a feedback guide such as “Your condition is not good. However, I support you for not stopping exercising. Let’s do something light today” at the time of starting exercise coaching in response to the decision to adjust the existing target value downward when the coaching level is low. The electronic device (101) may monitor the user’s movements and vital signals during exercise and output feedback guide messages such as “Good! You’re doing well this far” and “It’s time to rest after two more times” at a determined time. “Your condition is not good” is reflected in the condition score (low) as the basis for determining the coaching level.

[0137] An electronic device (101) according to one embodiment may set the determined coaching level and coaching guide as input values ​​of the LLM and request that a feedback guide message be output to include a description of the overall coaching level and detailed adjusted coaching content.

[0138] FIG. 9 is a flowchart illustrating a method for changing an exercise coaching guide level during real-time exercise monitoring of an electronic device according to one embodiment.

[0139] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0140] According to one embodiment, operations 910 to 960 may be understood to be performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1, electronic device (101) of FIG. 3).

[0141] An electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1, the electronic device (101) of FIG. 3) can determine whether a user's exercise performance process is suitable for the current coaching guide level during real-time exercise monitoring, and if not suitable, can change the coaching guide level.

[0142] In operation 910, an electronic device (101) according to an embodiment may collect sensor data related to real-time exercise performance. The electronic device (101) may analyze an image of the user's exercise performance motion captured by a camera, thereby analyzing the user's exercise performance process. The electronic device (101) may obtain a sensor value by the user's movement motion using an acceleration sensor or a gyro sensor, thereby analyzing the movement motion. When a user wears a wearable electronic device (e.g., the wearable electronic devices (301, 302, 303) of FIG. 3, or the wearable electronic device (301) of FIG. 4) and performs an exercise, the electronic device (101) may detect the user's movement or detect the user's biosignal using the sensors of the wearable electronic device (301, 302, 303). For example, the wearable electronic device (301) can collect sensor data on the user's movements by an activity sensor (e.g., an activity sensor (3070) of FIG. 3) and can collect sensor data detecting the user's biosignals by a biosensor (e.g., a biosensor (3080) of FIG. 3).

[0143] In operation 920, the electronic device (101) according to one embodiment may collect data related to a real-time user's behavioral response in response to a coaching guide or feedback guide being provided during exercise. The electronic device (101) may detect the user's speech through a microphone and recognize the user's verbal response to the coaching guide. The electronic device (101) may recognize whether sensor data acquired by the activity sensor (3070) of the wearable electronic device (301) changes at the time the coaching guide is provided. For example, the electronic device (101) may collect values ​​of the activity sensor (3070) of the wearable electronic device (301) related to the accuracy of the user's exercise motion at the time when the coaching guide for increasing the number of exercises is provided.

[0144] In operation 930, the electronic device (101) according to an embodiment may analyze the exercise performance process based on the collected data. After exercise coaching generated based on the current coaching guide level begins, the electronic device (101) receives real-time exercise sensor data from the wearable electronic device (301) and begins monitoring the exercise performance process. The electronic device (101) may analyze whether the exercise type according to the coaching is performed, whether the intensity of the exercise and the accuracy of the movement, whether the numerical records (speed, distance, number of times) are made within the range of the coaching guide level, and whether consistent movement is maintained. For example, in the case of running, which is an aerobic exercise, the electronic device (101) may analyze movement related to the exercise, such as whether the user runs at a constant speed (constant speed), the degree of elasticity (stiffness) that the user touches the ground, the time spent in the air (air time), the time spent in contact with the ground, and the degree of balance of the two feet (left-right balance) based on the above indicators. The electronic device (101) can collect numerical records related to running distance and speed, and health information such as maximum heart rate, calories, and Vo2Max, and analyze whether the level is appropriate according to the coaching guide level. In the case of repetitive exercise such as strength training, the electronic device (101) can estimate the user's movement using the activity sensor (3070). In the case of squats, which are repetitive up-and-down exercises, the electronic device (101) can analyze the user's movement pattern according to the gravity direction axis of the acceleration sensor of the wearable electronic device (301) to check whether the movement is performed correctly and measure the number of times. At this time, the electronic device (101) can be operated to measure each number of times according to the learning model for each exercise, and determine whether to perform the movement depending on the degree of agreement between the movement signal detected by the activity sensor (3070) and the learning model. The number of times the movement is performed can vary by adjusting the sensitivity of the degree of agreement.

[0145] In one embodiment, the exercise motion can be analyzed for repetitive patterns by collecting motion information through sensor data of the wearable electronic device (301), and the accuracy of the posture can be measured through image analysis using the camera of the electronic device (101). The electronic device (101) can also obtain numerical data through an external device linked to the exercise equipment. After monitoring, the electronic device (101) can generate coaching content based on analysis information (performance level) of the exercise motion and deliver it to the user.

[0146] In one embodiment, the electronic device (101) can classify a user's behavioral response as a positive or negative response. For example, Table 3 provides an example of classifying a user's behavioral response into a positive or negative response for analyzing coaching suitability.

[0147] Positive behavioral responseNegative behavioral responsePerforming a consistent movementPerforming an unbalanced movementAppropriate breathingExcessive breathingAccuracy or timing within toleranceAccuracy or timing outside tolerance

[0148] If the electronic device (101) detects a behavioral response corresponding to a positive behavioral response, it may determine that the coaching guide level is appropriate. Conversely, if the electronic device (101) detects a behavioral response corresponding to a negative behavioral response, it may determine that the coaching guide level is not appropriate. In operation 940, the electronic device (101) according to one embodiment may determine whether the current coaching guide level is appropriate based on the results of analyzing the exercise performance process. The electronic device (101) may observe the user's exercise performance and behavioral responses (verbal and nonverbal expressions) in response to the provided coaching, and determine whether the current coaching guide level is appropriate. If the electronic device (101) determines that the user's breathing rate and movement accuracy improve after the coaching guide is provided, and that the user is performing the exercise well according to the coaching guide, it may determine that the coach's direction is appropriate, and may guide subsequent movements according to the guidance level. The coaching guide level may be readjusted based on the results of the determination of appropriateness. The electronic device (101) can determine whether to adjust the guide level based on feedback information, exercise goals, and the degree of the guide level. The electronic device (101) can continue real-time monitoring while maintaining the current coaching guide level by repeating operations 910 to 940 while determining that the current coaching guide level is appropriate.

[0149] In operation 950, the electronic device (101) according to one embodiment may request a coaching guide level adjustment in response to determining that the current coaching guide level is not appropriate.

[0150] In operation 960, the electronic device (101) according to one embodiment can change the coaching guide level using a rule-based learning model based on the analyzed real-time exercise performance level of the user.

[0151] FIG. 10 is a table illustrating a feedback guide generated according to a changed exercise coaching guide level of an electronic device according to one embodiment.

[0152] An electronic device (101) according to one embodiment can adjust the coaching guide level based on the result of monitoring the exercise performance while providing coaching guide and feedback guide according to the current coaching level.

[0153] FIG. 10 is a table showing an example of adjusting a coaching level based on real-time monitoring results while an electronic device (101) provides a coaching guide and feedback guide according to the current coaching level, through the three examples described in FIG. 8.

[0154] In the first example, the electronic device (101) may collect sensor data of a maximum heart rate of 205 (increased heart rate rise), a 30% decrease in cadence, an average pace / speed of 4:25 min / km, and a current exercise distance of 2.5 km while an adult male is monitoring a marathon running workout according to a high+ coaching level. Based on the collected sensor data, the electronic device (101) may determine that the user's exercise performance is not suitable for the current coaching guide level, and may determine to change the level and adjust the coaching guide level to high- using a learning model. The electronic device (101) may generate a coaching guide to decrease the exercise record by 30% and the exercise intensity by 20% compared to the target according to the adjusted coaching level (high-). Specifically, the electronic device (101) may determine to decrease the cadence by 20% and the pace / speed by 20%, and may determine to increase the coaching level again depending on whether the performance ability has decreased by 20%. The electronic device (101) can generate a feedback message such as "It seems like you're too eager. If you push yourself too hard, you might get hurt, so let's find our pace again. Let's catch our breath and find a comfortable stride again" at a time when the level is changed according to the adjusted coaching guide. The electronic device (101) can output a voice signal of "One, two, one, two" at a lowered tempo. When the user performs the exercise according to the lowered guide, the electronic device (101) can generate a feedback message such as "Okay, let's maintain this pace. When your balance is sufficiently maintained and your body is ready, you can challenge yourself again with the original goal, so let's keep going like this for now."

[0155] In a second example, the electronic device (101) may collect sensor data of a maximum heart rate of 180, an average pace of 25:10 min / km, a current stroke of 42, a current exercise distance of 155 m, and an average SWOLF (efficiency) of 50 while monitoring an adult female's swimming according to a mid coaching level. Based on the collected sensor data, the electronic device (101) may determine that the user's exercise performance process is not suitable for the current coaching guide level, and may determine to change the level and adjust the coaching guide level to mid+ using a learning model. The electronic device (101) may generate a coaching guide for a 10% increase in exercise ability and a 5% increase in target distance compared to the target according to the adjusted coaching level (mid+). When the level is changed according to the adjusted coaching guide, the electronic device (101) may generate and provide a feedback guide such as "Your skills have improved. Should I be a little more ambitious today?" to the user. The electronic device (101) can output a screen that changes the target distance, while outputting a feedback guide as a voice signal, such as, "Your skills will improve when you take one more step! Let's go around one more time." In response to detecting that the stroke is getting faster, the electronic device (101) can generate and output a feedback guide, such as, "Good! Don't rush too much and keep a steady tempo."

[0156] In a third example, the electronic device (101) may analyze sensor data, based on a low+ coaching level, that 1 set of 40 repetitions has been completed, an accuracy boundary of 70% has been reached, the user's movements have slowed down in the latter half of the count, and a rest period is in progress, while monitoring a squat exercise. The electronic device (101) may determine to lower the level to a low level in response to determining that the current coaching guide level is higher than the user's exercise performance level. The electronic device (101) may generate a coaching guide according to the adjusted low coaching level, such as a 5% decrease in exercise ability compared to the target, maintaining the target, reducing the number of repetitions if accuracy drops, and switching to a posture hold. The electronic device (101) may generate and output a feedback guide, such as "You completed 1 set well. Take a deep breath for the 2nd set, and do some thigh stretching?" at the time the level is changed, according to the adjusted coaching guide. In response to detecting a decrease in squat posture accuracy, the electronic device (101) can generate and output feedback guides such as “It’s okay so far. Let’s try two more times?” or “Just one more time! If it’s difficult, let’s try holding here for 5 seconds?”

[0157] In one embodiment, the electronic device (101) can observe the exercise performance process through a sensor to see if the current coaching level is being properly performed, and if adjustment of the coaching level is required, input the changed level and coaching guide into the LLM, and generate a message notifying the user that the coaching level has changed, a description of the overall coaching guide level, and a description of the changed parts in detail, and provide the user with the information.

[0158] FIGS. 11A and 11B are examples of a user data input screen of an electronic device according to one embodiment.

[0159] According to one embodiment, the electronic device (101) may receive user input regarding exercise purpose (target) or exercise type.

[0160] Figure 11a illustrates an example of a user interface screen where a user determines an exercise goal. The exercise goal (1110) can be selected by selecting at least one of the presented keywords (1111) or directly entered (1112) via text or voice. The electronic device (101) can suggest recommended keywords based on collected user data. For example, if the user is a woman in her 20s, the keyword "weight loss," which is most frequently selected by women in their 20s, may be recommended at the top. Multiple exercise goals can be set.

[0161] Figure 11b illustrates an example of a user interface screen where a user determines the type of exercise. The type of exercise (1120) can be selected by selecting at least one of the presented keywords (1121) or directly input via text or voice (1122). The electronic device (101) can extract recommended keywords based on collected user data and display them as recommended keywords. Multiple types of exercise can be set.

[0162] FIGS. 11c and 11d are examples of screens displaying user movement data of an electronic device according to one embodiment.

[0163] An electronic device (101) according to one embodiment may store exercise records as a result of monitoring a user's exercise and provide the user with information about the exercise records. FIG. 11c is an example of a user interface screen that provides information about all exercises (1130) performed during a certain period. In response to a user input selecting a specific period, the electronic device (101) may display the type of exercise performed during the period and details of the exercise (1131).

[0164] Figure 11d is an example of a user interface screen that provides the results (1140) of analyzing exercise records performed over a certain period. In response to a user input selecting a specific period (e.g., May 12-18), the electronic device (101) may provide activity details (1141) and weekly trends (1142) as analysis results.

[0165] FIGS. 12a, 12b, and 12c are examples of exercise coaching guide screens of an electronic device according to one embodiment.

[0166] An electronic device (101) according to one embodiment may provide a user with information including at least one of a coaching guide or a feedback guide according to an exercise coaching guide level. For example, the electronic device (101) may output a screen including a message corresponding to a feedback guide according to the current exercise coaching guide level at the time of initiating exercise coaching.

[0167] FIG. 12A is an example of a screen (1210) providing exercise coaching. In response to the coaching level being determined as high, it may display "high level" and a feedback guide message such as "Your energy score was high today. I think it's because you got enough rest yesterday. With this good condition, you should try to break your record." The feedback guide message may be generated by including a specific basis for determining the coaching level (e.g., condition score (good condition), exercise purpose (record breaking)). The exercise coaching screen (1210) may display a squat movement process as an exercise process (1212) for performing real-time monitoring. The electronic device (101) may monitor whether the user's exercise is performed according to the exercise process (1212) using a sensor of the wearable electronic device.

[0168] FIG. 12B illustrates a squat exercise screen (1220) as an example of an exercise process. The squat exercise screen (1220) may include a section (1221) displaying a coaching level, a section (1222) displaying the user's exercise performance steps (e.g., set 1 / 3) and the degree of performance (e.g., set time) for an exercise process currently in progress in real time, reflecting the exercise performance. The electronic device (101) may display data (e.g., heart rate, number of exercises, exercise duration) on the screen to provide the user with analyzed data regarding the user's exercise performance process based on real-time sensor data.

[0169] FIG. 12C illustrates an example screen in which the coaching level is changed at the time the monitored exercise process is completed. The electronic device (101) may display a squat exercise screen (1230) and, at the time the squat exercise process is completed, display information (1232) regarding the completed exercise. The electronic device (101) may change the coaching level based on the results of monitoring the user's exercise performance. The electronic device (101) may determine the level change and display new coaching level information (1231). The electronic device (101) may output a feedback message generated according to the changed coaching level. Referring to FIG. 12C, the electronic device (101) may generate various types of feedback messages (1233) and provide them to the user by outputting them as voice.

[0170] FIGS. 13A and 13B are examples of exercise monitoring screens of a wearable electronic device according to one embodiment.

[0171] A wearable electronic device according to one embodiment (e.g., a watch-type wearable electronic device (301) of FIG. 3, a wearable electronic device (301) of FIG. 4) can output a monitoring screen through a display while monitoring a user's movement in real time.

[0172] Referring to FIG. 13A, a guide level (1310) may be displayed along with exercise performance information (e.g., squat exercise, number of repetitions, set information) during exercise through the display of a wearable electronic device (301). The guide level (1310) may be displayed at a point where the currently determined guide level (1310) is located among the entire guide level classification. For example, when the guide level classification is sequentially divided into a first level (1311), a second level (1312), a third level (1313), a fourth level (1314), and a fifth level (1315) from the lowest level, the guide levels may be displayed in different colors (e.g., a first level (1311) - red, a second level (1312) - orange, a third level (1313) - yellow, a fourth level (1314) - green, a fifth level (1315) - blue). The currently determined guide level (1310) is included in the fourth step (1314).

[0173] The wearable electronic device (301) can display the details of the exercise adjusted according to the current guide level in the color of the guide level (1320, 1330). For example, if the current guide level is green (e.g., the fourth stage (1314) - green), if the number of squat repetitions and sets are adjusted compared to the user's usual exercise level according to the current guide level, 100 reps 3 sets (1320) can be displayed in green to indicate that today's exercise coaching guide level has been reflected. The wearable electronic device (301) can display colors up to a part of the fourth stage (1321, 1322, 1323, 1324) among the five stages of guide level classification (1321, 1322, 1323, 1324, 1325) so that the user can visually check whether the goal suggested by the guide level is met according to the user's exercise performance. The wearable electronic device (301) may display the performance level of the currently performed exercise as a progress bar (1331). At this time, the progress bar (1331) may be displayed in the color of the current guide level (e.g., green).

[0174] Referring to FIG. 13B, the wearable electronic device (301) can visually display whether the user's exercise performance is meeting the target suggested by the guide level. For example, the wearable electronic device (301) can display a graph filled in (1341) so that the graph gets closer to a high level color as the user approaches the target number of times performed. For example, when performing a squat movement, the wearable electronic device (301) can display a graph filled in (1342) depending on the degree of sitting, and when the graph is filled all the way, it can be determined that the correct posture has been met and count the number of times.

[0175] FIG. 14 is an example of an exercise coaching guide screen of a wearable electronic device according to one embodiment.

[0176] According to one embodiment, a wearable electronic device (e.g., a watch-type wearable electronic device (301) of FIG. 3, a wearable electronic device (301) of FIG. 4) may receive a coaching guide or feedback guide generated according to a coaching guide level from an electronic device (101) and output the same to a display screen or a speaker. For example, the wearable electronic device (301) may output a message including feedback content including a current guide level and coaching content changed according to the guide level.

[0177] Referring to FIG. 14, the wearable electronic device (301) can output a feedback guide message (1410) that induces goal achievement by adjusting exercise intensity (weight). The wearable electronic device (301) can output a feedback guide message (1420) that induces goal achievement by adjusting exercise intensity (posture). The wearable electronic device (301) can output a feedback guide message (1430) that induces goal achievement by adjusting rest time. The wearable electronic device (301) can output a feedback guide message (1440) that induces accurate goal achievement by adjusting to a proper posture. FIG. 14 is an example, and an appropriate user screen or interface can be output according to the generated feedback guide message.

[0178] FIG. 15 is an example of a screen for changing the exercise coaching guide level of a wearable electronic device according to one embodiment.

[0179] According to one embodiment, a wearable electronic device (e.g., a watch-type wearable electronic device (301) of FIG. 3, a wearable electronic device (301) of FIG. 4) may output a user interface for changing an exercise coaching guide level.

[0180] Referring to FIG. 15, the wearable electronic device (301) may display the current exercise coaching guide level and provide a user interface that allows the guide level to be increased or decreased by an up or down swipe input (1511). The on-screen guide level may be changed by a user input (1511), and if a user desires to change the current guide level displayed on the screen, the wearable electronic device (301) may receive a user input for a complete button (1510).

[0181] FIG. 16 is an example of an exercise completion feedback screen of a wearable electronic device according to one embodiment.

[0182] According to one embodiment, a wearable electronic device (e.g., a watch-type wearable electronic device (301) of FIG. 3, a wearable electronic device (301) of FIG. 4) may output a screen for feedback information when exercise is completed.

[0183] Referring to FIG. 16, the wearable electronic device (301) may output final feedback (summary) information regarding the provided coaching on the display screen (1610) after the end of exercise. The wearable electronic device (301) may output a section (1610) including the type of exercise and the details of the exercise completed, a section (1620) explaining the coaching guide level information and whether it has been achieved, and a section (1630) displaying the most recent coaching guide level information including the currently completed exercise. Such result data (Result) may be stored as an exercise record and may be further reflected in the next exercise coaching.

[0184] An electronic device according to one embodiment of the present disclosure includes: a camera; at least one sensor for detecting a biosignal or movement; a microphone; a speaker; a display; a communication circuit; a memory; and at least one processor including a processing circuit; The memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: determine a first exercise coaching guide level for monitoring the user's exercise based on a rule-based machine learning model learned to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance ability level; output at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the determined exercise process as input while providing an exercise process determined according to a type of exercise selected by the user; monitor the user's exercise motion according to the progress of the exercise process, receive sensor data detecting the user's movement or biosignal from a wearable electronic device worn by the user, and analyze the received sensor data to cause the electronic device to monitor the user's exercise motion while maintaining the first exercise coaching guide level while determining that the user's exercise performance process is suitable for the first exercise coaching guide level.

[0185] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: determine, based on sensor data received from the wearable electronic device, whether the user's exercise performance process is suitable for the first exercise coaching guide level.

[0186] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: generate a second exercise coaching guide level based on the rule-based learning model at a first time point in response to determining that the user's exercise performance process is not suitable for the first exercise coaching guide level, and output at least one coaching content newly generated using the LLM in response to the second exercise coaching guide level after the first time point in accordance with the progress of the exercise process.

[0187] According to one embodiment, the memory, when individually or collectively executed by the at least one processor, causes the electronic device to: the coaching content includes at least a portion of a coaching guide or coaching feedback, the coaching guide being generated with respect to details of an exercise process including at least a portion of an exercise performance range, an exercise intensity, or an exercise posture accuracy, and the coaching feedback may include a feedback message generated based on the LLM.

[0188] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to generate the feedback message using the LLM to include: an exercise coaching guide level, a basis item for determining the exercise coaching guide level, or coaching content changed according to the guide level.

[0189] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: receive at least one text or voice data including a keyword relating to the exercise purpose by user input, and set the exercise purpose based on the at least one text or voice data.

[0190] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: calculate a current energy score based on the user's body data, previous exercise history, and sensor information about the body condition; and determine the condition score in response to the current energy score.

[0191] In one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: determine the condition score by taking into account weightings assigned to specific items of the body data, previous exercise history, or sensor information regarding the body condition.

[0192] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: determine a level of exercise performance using a personalized exercise performance model in which exercise patterns are learned based on the user's previous exercise history.

[0193] In one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the electronic device to: relearn the personalized exercise performance model based on sensor data received from the wearable electronic device while monitoring the user's exercise movements.

[0194] According to another embodiment of the present disclosure, a wearable electronic device includes an activity sensor for detecting movement of the wearable electronic device; a biosensor for detecting a biosignal; a speaker; a display; a communication circuit; a memory; and at least one processor including a processing circuit; The memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: receive exercise process information determined according to a type of exercise selected by a user input from the electronic device through the communication circuit, output a first screen providing the exercise process through the display based on the exercise process information, detect a movement or a biosignal of the user using at least one of the activity sensor or the biosensor, collect sensor data, and transmit the sensor data to the electronic device, receive, from the electronic device, through the communication circuit, first exercise coaching guide level information and at least one coaching content generated using a large language model (LLM) according to the first exercise coaching guide level, generate a second screen reflecting the first exercise coaching guide level information or the at least one coaching content, and output the second screen through the display.

[0195] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: generate the third screen and output it through the display in response to receiving second exercise coaching guide level information and at least one coaching content generated according to the second exercise coaching guide level from the electronic device.

[0196] According to one embodiment, the memory, when individually or collectively executed by the at least one processor, causes the wearable electronic device to: the coaching content includes at least a portion of a coaching guide or coaching feedback, the coaching guide being generated with respect to details of an exercise process including at least a portion of an exercise performance range, an exercise intensity, or an exercise posture accuracy, and the coaching feedback may include a feedback message generated based on the LLM.

[0197] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to receive the feedback message generated using the LLM to include: an exercise coaching guide level, a basis item for determining the exercise coaching guide level, or coaching content changed according to the guide level.

[0198] According to one embodiment, the first exercise coaching guide level may be determined based on a rule-based machine learning model that is trained to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance level.

[0199] According to one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: receive at least one text or voice data including a keyword relating to the exercise purpose by a user input; transmit the at least one text or voice data to the electronic device; and cause the exercise purpose to be set based on the at least one text or voice data.

[0200] In one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: determine the condition score in response to a current energy score, and calculate the current energy score based on the user's body data, previous exercise history, and sensor information regarding the body condition.

[0201] In one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: determine the condition score by taking into account weightings assigned to specific items of the body data, previous exercise history, or sensor information regarding the body condition.

[0202] In one embodiment, the memory may store instructions that, when individually or collectively executed by the at least one processor, cause the wearable electronic device to: determine the exercise performance level based on a personalized exercise performance model in which exercise patterns are learned based on the user's previous exercise history.

[0203] According to another embodiment of the present disclosure, a non-volatile computer-readable storage medium having instructions recorded thereon may include, when executed by one or more processors, causing the one or more processors to: determine a first exercise coaching guide level for monitoring a user's exercise based on a rule-based machine learning model learned to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance ability level; output at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the determined exercise process as input while providing an exercise process determined according to a type of exercise selected by a user input; monitor the user's exercise motion according to the progress of the exercise process and receive sensor data detecting the user's movement or biosignal from a wearable electronic device worn by the user; and monitor the user's exercise motion while maintaining the first exercise coaching guide level while analyzing the received sensor data and determining that the user's exercise performance process is suitable for the first exercise coaching guide level.

[0204] The embodiments of this document and the terminology used herein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0205] The term "module" used in the embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0206] One embodiment of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0207] According to one embodiment, the method according to one embodiment disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0208] According to one embodiment, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to one embodiment, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to one embodiment, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In electronic devices, camera; At least one sensor that detects biosignals or movement; mike; speaker; display; communication circuit; memory; and At least one processor comprising a processing circuit; The memory, when executed individually or collectively by the at least one processor, causes the electronic device to: Determine a first exercise coaching guide level for monitoring the user's exercise based on a rule-based machine learning model that is trained to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance level, and While providing a set exercise process according to the type of exercise selected by the user input, outputting at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the set exercise process as input, As the above exercise process progresses, the user's exercise motion is monitored, and sensor data detecting the user's movement or bio-signals is received from a wearable electronic device worn by the user, and An electronic device that analyzes the sensor data and stores instructions that cause the user's exercise performance to be monitored while maintaining the first exercise coaching guide level while determining that the user's exercise performance process is suitable for the first exercise coaching guide level.

2. In paragraph 1, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: An electronic device storing commands that cause the user to determine whether the user's exercise performance process is suitable for the first exercise coaching guide level based on sensor data received from the wearable electronic device.

3. In paragraph 1, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: In response to determining that the user's exercise performance process is not suitable for the first exercise coaching guide level, a second exercise coaching guide level is generated based on the rule-based learning model at a first point in time, and An electronic device that stores commands that cause at least one newly generated coaching content to be outputted using the LLM according to the progress of the exercise process, corresponding to the second exercise coaching guide level, after the first point in time.

4. In paragraph 1, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: The above coaching content includes at least part of the coaching guide or coaching feedback, The above coaching guide is generated with respect to the details of the exercise process, including at least some of the exercise performance range, exercise intensity, or exercise form accuracy. An electronic device wherein the coaching feedback comprises a feedback message generated based on the LLM.

5. In paragraph 1 or paragraph 4, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: An electronic device storing commands that cause the LLM to generate the feedback message, including the exercise coaching guide level, the basis for determining the exercise coaching guide level, or the coaching content changed according to the guide level.

6. In paragraph 1, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: Based on the user's body data, previous exercise records, and sensor information about body condition, the current energy score is calculated, and An electronic device storing instructions that cause the condition score to be determined in response to the current energy score.

7. In paragraph 1 or paragraph 6, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: An electronic device storing commands that cause the condition score to be determined by considering weights set for the details of the above body data, previous exercise records, or sensor information regarding the body condition.

8. In paragraph 1, The memory, when individually or collectively executed by the at least one processor, causes the electronic device to: An electronic device storing commands that cause the user to determine a level of exercise performance using a personalized exercise performance model in which exercise patterns are learned based on the user's previous exercise records.

9. In wearable electronic devices, An activity sensor that detects movement of the wearable electronic device; A biosensor that detects biological signals; speaker; display; communication circuit; memory; and At least one processor comprising a processing circuit; The memory, when executed individually or collectively by the at least one processor, causes the wearable electronic device to: Receive exercise process information determined according to the type of exercise selected by user input from the electronic device through the above communication circuit, Based on the above exercise process information, a first screen providing the exercise process is output through the display, By detecting the user's movement or biometric signal using at least one of the above activity sensor or the above biometric sensor, sensor data is collected, Transmitting the above sensor data to the electronic device, From the electronic device, at least one coaching content generated using a large language model (LLM) according to first exercise coaching guide level information and the first exercise coaching guide level is received through the communication circuit, A wearable electronic device that stores instructions that cause a second screen to be generated by reflecting the first exercise coaching guide level information or the at least one coaching content and to be output through the display.

10. In paragraph 9, The memory, when individually or collectively executed by the at least one processor, causes the wearable electronic device to: A wearable electronic device storing commands that cause a third screen to be generated and output through the display in response to receiving second exercise coaching guide level information and at least one coaching content generated according to the second exercise coaching guide level from the electronic device.

11. In paragraph 9 or 10, The memory, when individually or collectively executed by the at least one processor, causes the wearable electronic device to: The above coaching content includes at least part of the coaching guide or coaching feedback, The above coaching guide is generated with respect to the details of the exercise process, including at least some of the exercise performance range, exercise intensity, or exercise form accuracy. A wearable electronic device, wherein the coaching feedback includes a feedback message generated based on the LLM.

12. In paragraph 9, The memory, when individually or collectively executed by the at least one processor, causes the wearable electronic device to: Receiving at least one text or voice data containing a keyword related to the exercise purpose by user input, transmitting at least one text or voice data to the electronic device; A wearable electronic device storing commands that cause the above exercise goal to be set based on at least one text or voice data.

13. In paragraph 9 or paragraph 12, The memory, when individually or collectively executed by the at least one processor, causes the wearable electronic device to: The above condition score is determined in response to the current energy score, and A wearable electronic device storing instructions that cause the current energy score to be calculated based on the user's body data, previous exercise records, and sensor information about the user's body condition.

14. In paragraph 9 or paragraph 13, The memory, when individually or collectively executed by the at least one processor, causes the wearable electronic device to: A wearable electronic device storing commands that cause the condition score to be determined by considering weights set for the details of the above-mentioned body data, previous exercise records, or sensor information regarding the body condition.

15. A non-volatile computer-readable storage medium that records commands, The above instructions, when executed by one or more processors, cause the one or more processors to: An action of determining a first exercise coaching guide level for monitoring the user's exercise based on a rule-based machine learning model that is trained to generate an exercise coaching guide level based on at least one of the user's exercise purpose, condition score, or exercise performance level; An operation of outputting at least one coaching content generated using a large language model (LLM) with the first exercise coaching guide level and the determined exercise process as input while providing an exercise process determined according to the type of exercise selected by the user input; An action of monitoring the user's exercise motion according to the progress of the above exercise process and receiving sensor data detecting the user's movement or bio-signal from a wearable electronic device worn by the user; and A non-transitory computer-readable storage medium comprising an operation of monitoring the user's exercise motion while maintaining the first exercise coaching guide level, while analyzing the sensor data to determine that the user's exercise performance process is suitable for the first exercise coaching guide level.

Images