User-customized exercise recommendation method and device

Abstract

The present invention relates to a user-customized exercise recommendation method performed by a processor of an exercise recommendation device, the method comprising the steps of: identifying an exercise difficulty level of an exercise performed by a user; providing a user feedback list related to the result of performing the exercise; determining an exercise level of the user with respect to the exercise on the basis of any one user feedback selected from the user feedback list; and providing at least one exercise corresponding to the exercise level of the user.

Description

Customized exercise recommendation methods and devices

[0001] The present invention relates to a method and device for recommending user-tailored exercise.

[0002] While outdoor exercise and public gyms have returned to activity since the pandemic, people's interest in home workouts remains strong.

[0003] Typically, people who exercise at home refer to online workout videos or use workout apps. However, those unfamiliar with exercise often face various difficulties. For example, videos or pre-made workout routines don't take into account the individual body parts of the exerciser. While each exercise has a difficulty level, users are simply watching and following the videos, making it difficult to determine whether they are exercising with the appropriate form for the level of difficulty.

[0004] In particular, strength training that can progressively overload muscles is essential for muscle recovery or growth. However, conventional home training methods have limitations in effectively implementing strength training. For example, home training can pose a risk of injury for those with weak or inflexible muscles, while those with strong and flexible muscles may not be able to achieve the appropriate load.

[0005] The background technology of the invention has been prepared to facilitate a better understanding of the present invention. It should not be construed as an admission that the matters described in the background technology of the invention constitute prior art.

[0006] Accordingly, methods for providing personalized training plans have been proposed to allow users to perform exercises at an appropriate level of difficulty. However, these methods have the disadvantage of requiring separate equipment during exercise, as they adjust exercise intensity based on various sensors that can be attached to the user's body.

[0007] Accordingly, a method is required to provide exercise of appropriate difficulty level that can maximize the exercise effect without overexerting the user based only on the user's feedback.

[0008] As a result, the inventors of the present invention have constructed a method capable of determining the current exercise level of a user based on the user's exercise level and the difficulty level of the exercise performed by the user, and providing an exercise suitable for the user's exercise level.

[0009] In particular, the inventors of the present invention have devised a method to provide newly added exercises to appropriate subjects by determining the exercise difficulty based on feedback from users in addition to the users' exercise level.

[0010] In addition, the inventors of the present invention have devised a method to provide an exercise program similar to that managed by a professional trainer by providing exercise that takes into account the muscle strength and flexibility of each body part of the user.

[0011] The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

[0012] In order to solve the above-described problem, a user-customized exercise recommendation method according to one embodiment of the present invention is provided. The method is a user-customized exercise recommendation method performed by a processor of an exercise recommendation device, and is configured to include a step of confirming an exercise difficulty of an exercise performed by a user, a step of providing a user feedback list related to a result of performing the exercise, a step of determining an exercise level of the user for the exercise based on any one user feedback selected from the user feedback list, and a step of providing at least one exercise corresponding to the user's exercise level.

[0013] According to a feature of the present invention, the step of providing the user feedback list may be a step of providing items that allow the user to gradually select the perceived difficulty of the exercise as one of easy, normal, difficult, and painful.

[0014] According to a feature of the present invention, the step of determining the exercise level may be a step of determining the user's exercise level based on the user feedback on the confirmed exercise difficulty using a pre-learned level determination algorithm.

[0015] According to a feature of the present invention, after the step of providing the user feedback list, the step of replacing an item selected by the user with one of a win, a loss, and a draw targeting the user and the exercise, and the step of scoring the replaced win or loss result may be further included.

[0016] According to a feature of the present invention, the step of determining the exercise level may further include a step of correcting the exercise difficulty level together with the exercise level of the user using the pre-learned level determination algorithm.

[0017] According to a feature of the present invention, the step of providing the exercise may further include the step of checking user feedback from other users in the upper or lower ranks based on the exercise level of the user, and generating a list of recommendable exercises based on the checked user feedback.

[0018] According to a feature of the present invention, the step of checking the exercise difficulty may be a step of checking data that quantifies the degree of flexibility or muscle strength required for each movable body part applied to the exercise.

[0019] According to a feature of the present invention, prior to the step of confirming, a step of providing exercise content matching the exercise may be further included depending on whether the user has performed the exercise.

[0020] According to a feature of the present invention, prior to the step of confirming, the step of obtaining identification data including at least one of the type, intensity, time, frequency, duration, physical strength factor, and movable body part of the exercise may be further included, and the step of confirming the exercise difficulty may be a step of confirming the exercise difficulty matching each of a plurality of categories for one exercise based on the identification data.

[0021] According to a feature of the present invention, the step of providing the exercise may be a step of providing identification data for performing the exercise together with pre-stored exercise content or searched exercise content.

[0022] In order to solve the above-described problem, an exercise recommendation device according to another embodiment of the present invention is provided. The device includes a communication interface, a memory, and a processor operably connected to the communication interface and the memory, wherein the processor is configured to determine an exercise difficulty of an exercise performed by a user, provide a list of user feedback related to a result of performing the exercise, determine an exercise level of the user for the exercise based on one user feedback selected from the list of user feedback, and provide at least one exercise corresponding to the exercise level of the user.

[0023] Specific details of other embodiments are included in the detailed description and drawings.

[0024] The present invention allows users to easily determine and adjust their exercise level without requiring them to wear a separate device or have a trainer evaluate the exercise or the user. In particular, the present invention can provide users with exercises that provide appropriate stimulation for each body part by determining exercise levels for muscle strength and flexibility in each body part, which are difficult for users to perceive.

[0025] The present invention can also determine a user's fitness level based on subjective user feedback regarding exercise. For example, the present invention determines a user's relative fitness level by synthesizing feedback from the user and other users regarding a specific exercise. This allows for the easy determination of fitness level, a vague and unmeasurable concept, without the need for expert diagnosis.

[0026] The present invention can determine a user's exercise level using an AI model trained based on the user's exercise video. For example, the present invention acquires a user's exercise video for a specific exercise and analyzes the video to determine the user's exercise level. This allows for accurate and simple determination of exercise level, a vague and unmeasurable concept.

[0027] The present invention can determine the difficulty of an exercise based on the user's exercise level and feedback. Furthermore, determining the exercise difficulty can provide an appropriate exercise that improves the user's physical abilities without putting too much strain on the body.

[0028] The effects according to the present invention are not limited to those exemplified above, and more diverse effects are included within the present invention.

[0029] FIG. 1 is a block diagram showing the configuration of a user-customized exercise recommendation system according to one embodiment of the present invention.

[0030] FIG. 2 is a block diagram showing the configuration of a user device according to one embodiment of the present invention.

[0031] FIG. 3 is a block diagram showing the configuration of a user-customized exercise recommendation device according to one embodiment of the present invention.

[0032] FIG. 4 is a schematic flowchart of a user-customized exercise recommendation method according to one embodiment of the present invention.

[0033] FIG. 5 is a schematic diagram illustrating a method for determining a user's exercise level according to one embodiment of the present invention.

[0034] The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms. These embodiments are provided solely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. In connection with the description of the drawings, similar reference numerals may be used for similar components.

[0035] In this document, the expressions "has," "may have," "includes," or "may include" indicate the presence of a feature (e.g., a number, function, operation, or component such as a part), but do not exclude the presence of additional features.

[0036] In this document, the expressions "A or B," "at least one of A and / or B," or "one or more of A or / and B" can include all possible combinations of the listed items. For example, "A or B," "at least one of A and B," or "at least one of A or B" can all refer to cases where (1) at least one A is included, (2) at least one B is included, or (3) at least one A and at least one B are included.

[0037] The terms "first," "second," "first," or "second," as used herein, may describe various components, regardless of order and / or importance, and are only used to distinguish one component from another, without limiting the components. For example, a first user device and a second user device may represent different user devices, regardless of order or importance. For example, without departing from the scope of the rights set forth in this document, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

[0038] When it is said that a component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the component is directly coupled to the other component, or can be connected via another component (e.g., a third component). Conversely, when it is said that a component (e.g., a first component) is "directly coupled to" or "directly connected to" another component (e.g., a second component), it should be understood that no other component (e.g., a third component) exists between the first component and the other component.

[0039] The expression "configured to" as used herein can be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean something is "specifically designed to" in hardware terms. Instead, in some contexts, the expression "a device configured to" can mean that the device, together with other devices or components, is "capable of." For example, the phrase "a processor configured (or set) to perform A, B, and C" may mean a dedicated processor (e.g., an embedded processor) for performing those operations, or a general-purpose processor (e.g., a CPU or application processor) that can perform those operations by executing one or more software programs stored in a memory device.

[0040] The terms used in this document are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this document. Terms defined in general dictionaries among the terms used in this document may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this document. In some cases, even if a term is defined in this document, it cannot be interpreted to exclude the embodiments of this document.

[0041] The individual features of the various embodiments of the present invention can be partially or wholly combined or combined with each other, and as can be fully understood by those skilled in the art, various technical connections and operations are possible, and each embodiment can be implemented independently of each other or can be implemented together in a related relationship.

[0042] For clarity in the interpretation of this specification, the terms used in this specification are defined below.

[0043] Hereinafter, the present invention will be described in detail by describing a preferred embodiment of the present invention with reference to the attached drawings.

[0044]

[0045] FIG. 1 is a block diagram showing the configuration of a user-customized exercise recommendation system according to one embodiment of the present invention.

[0046] Referring to FIG. 1, a user-customized exercise recommendation system (10) according to one embodiment of the present invention is a system that can suggest an exercise that matches the user's current exercise level, and may include a user device (100) and an exercise recommendation device (200).

[0047] The user device (100) is a device of a user who wishes to receive customized exercise, and may include a smartphone, a tablet PC (Personal Computer), a laptop, a PC, etc. The user device (100) may request an exercise recommendation service by installing or executing an application or program provided by the exercise recommendation device (200). To this end, the user device (100) may obtain user feedback on the exercise performed by the user. For example, the user device (100) may output a user feedback selection list (11) such as “easy / average / difficult / pain” along with the question “How difficult was the exercise?”, and may provide any one of the user feedbacks selected by the user to the exercise recommendation device (200).

[0048] The user device (100) can receive and output a list of exercises (12) of appropriate exercise difficulty for the user, determined based on user feedback from the exercise recommendation device (200). For example, the user device (100) can continuously collect user feedback and request an exercise management service based on the user feedback collected by the exercise recommendation device (200). In addition, for example, the user device (100) can transmit an exercise video captured of the user exercising to the exercise recommendation device (200), and the exercise recommendation device (200) can analyze the user's exercise posture in the collected exercise video and provide an exercise management service based on the same.

[0049] According to one embodiment, a user may select any one exercise included in the exercise list (12), and the user device (100) may provide the exercise by displaying information about the exercise in the form of text or images, or by playing video content corresponding to the exercise title when the exercise title is selected.

[0050] The exercise recommendation device (200) is a service provider's device that provides users with appropriate exercise by considering their exercise level and exercise difficulty, and may include a general-purpose computer, laptop, data server, etc. The exercise recommendation device (200) can perform the role of an exercise trainer by providing exercise suited to the exercise level of each body part, taking into account that each user has different levels of muscle strength and flexibility for each body part.

[0051] In various embodiments, the exercise recommendation device (200) can determine the exercise level of the user among users who performed the exercise by matching the user's exercise level and exercise difficulty one-to-one. Based on the determined exercise level of the user, the exercise recommendation device (200) can identify other users with similar exercise levels to the user. The exercise recommendation device (200) can provide an exercise suitable for the user based on the user feedback of the identified other users and the exercise difficulty of pre-stored exercises. For example, the exercise recommendation device (200) can provide the user device (100) with a link to exercise content produced by a service provider or exercise content searched online.

[0052] So far, a user-tailored exercise recommendation system (10) according to one embodiment of the present invention has been described. According to the present invention, an appropriate exercise can be recommended to a user based solely on the perceived difficulty level of the user performing the exercise, without the need for expert feedback.

[0053] Hereinafter, with reference to FIG. 2, a user device (100) that uses an exercise recommendation service will be described.

[0054] FIG. 2 is a block diagram showing the configuration of a user device according to one embodiment of the present invention.

[0055] Referring to FIG. 2, the user device (100) may include a memory interface (110), one or more processors (120), and a peripheral interface (130). Various components within the user device (100) may be connected by one or more communication buses or signal lines.

[0056] The memory interface (110) is connected to the memory (150) and can transmit various data to the processor (120). Here, the memory (150) can include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and blockchain database.

[0057] In various embodiments, the memory (150) may store user identification data, identification data for exercises performed by the user, user feedback entered by the user, exercise levels for the exercises, and elements of a service screen for displaying user feedback and the exercises to be performed. For example, the user identification data may include the user's gender, age, and basic body measurements (height, weight, waist circumference, etc.).

[0058] In various embodiments, the memory (150) may store at least one of an operating system (151), a communication module (152), a graphical user interface module (GUI) (153), a sensor processing module (154), a telephone module (155), and an application module (156). Specifically, the operating system (151) may include instructions for processing basic system services and instructions for performing hardware operations. The communication module (152) may communicate with at least one of one or more other devices, computers, and servers. The graphical user interface module (GUI) (153) may process a graphical user interface. The sensor processing module (154) may process sensor-related functions (e.g., processing voice input received through one or more microphones (192). The telephone module (155) may process telephone-related functions. The application module (156) may perform various functions of a user application, such as electronic messaging, web browsing, media processing, navigation, imaging, and other processing functions. Additionally, the user device (100) can store one or more software applications (156-1, 156-2) associated with a type of service (e.g., an application for an exercise recommendation service) in the memory (150).

[0059] In various embodiments, the memory (150) may store a digital assistant client module (157) (hereinafter, DA client module), and accordingly, may store commands for performing client-side functions of the digital assistant and various user data (158) (e.g., user-customized vocabulary data, preference data, other data such as the user's electronic address book, etc.).

[0060] Meanwhile, the DA client module (157) can obtain the user's voice input, text input, touch input, and / or gesture input through various user interfaces (e.g., I / O subsystem (140)) provided in the user device (100).

[0061] Additionally, the DA client module (157) can output data in audiovisual and tactile forms. For example, the DA client module (157) can output data consisting of a combination of at least two or more of voice, sound, notification, text message, menu, graphic, video, animation, and vibration. In addition, the DA client module (157) can communicate with a digital assistant server (not shown) using a communication subsystem (180).

[0062] In various embodiments, the DA client module (157) may collect additional information about the surroundings of the user device (100) from various sensors, subsystems, and peripheral devices to construct a context associated with the user input. For example, the DA client module (157) may provide context information along with the user input to a digital assistant server to infer the user's intent. Here, the context information that may accompany the user input may include sensor information, such as lighting, ambient noise, ambient temperature, images of the surroundings, videos, etc. As another example, the context information may include the physical state of the user device (100) (e.g., device orientation, device position, device temperature, power level, speed, acceleration, motion patterns, cellular signal strength, etc.). As yet another example, the context information may include information related to the software state of the user device (100) (e.g., processes running on the user device (100), installed programs, past and present network activity, background services, error logs, resource usage, etc.).

[0063] In various embodiments, the memory (150) may include added or deleted instructions. Furthermore, the user device (100) may also include additional configurations other than those illustrated in FIG. 2, or may exclude some configurations.

[0064] The processor (120) can control the overall operation of the user device (100) and execute various commands to provide exercise corresponding to the user's exercise level by running an application or program stored in the memory (150).

[0065] The processor (120) may correspond to a computing device such as a CPU (Central Processing Unit) or an AP (Application Processor). In addition, the processor (120) may be implemented in the form of an integrated chip (IC), such as a SoC (System on Chip) that integrates various computing devices that perform machine learning, such as an NPU (Neural Processing Unit).

[0066] In various embodiments, the processor (120) may recommend customized exercises to the user in place of the function of the exercise recommendation device (200). According to one embodiment, the processor (120) may determine the exercise difficulty of the exercise performed by the user.

[0067] For example, the processor (120) may provide a list of user feedback related to the results of an exercise performance, and may determine the user's exercise level for the exercise based on any one user feedback selected from the list of user feedback. The processor (120) may provide at least one exercise corresponding to the user's exercise level.

[0068] For example, the processor (120) may obtain an exercise video of a user performing a provided exercise, and obtain exercise performance information such as the user's exercise performance ability, exercise performance accuracy, and exercise performance speed based on the obtained exercise video, and determine the user's exercise level based on the exercise performance information. The processor (120) may provide at least one exercise corresponding to the user's exercise level. According to one embodiment, the processor (120) may use an exercise level determination model stored in the memory (150) to determine the user's exercise level. For example, the processor (120) may determine the user's exercise level by using an exercise level determination model, which is an artificial intelligence model trained to receive an exercise video of the user and analyze the user's exercise posture in the exercise video to determine the user's exercise level.

[0069] The peripheral interface (130) can be connected to various sensors, subsystems, and peripheral devices to provide data so that the user device (100) can perform various functions. Here, the function performed by the user device (100) can be understood as being performed by the processor (120).

[0070] The peripheral interface (130) can receive data from a motion sensor (160), a light sensor (light sensor) (161), and a proximity sensor (162), through which the user device (100) can perform orientation, light, and proximity detection functions, etc. For another example, the peripheral interface (130) can receive data from other sensors (163) (positioning system - GPS receiver, temperature sensor, biometric sensor), through which the user device (100) can perform functions related to the other sensors (163).

[0071] According to various embodiments, the user device (100) may be worn on at least a portion of the user's body to obtain various biometric data. For example, the user device (100) may obtain various biometric data values, such as the user's heart rate, muscle oxygen saturation, blood sugar, and body temperature, through other sensors (163). For example, the user device (100) may be worn on at least a portion of the user's body while performing a specified exercise to obtain the biometric data values.

[0072] According to various embodiments, the user device (100) may provide the biometric data value so that the biometric data value is used to determine the user's exercise level.

[0073] In various embodiments, the user device (100) may include a camera subsystem (170) connected to a peripheral interface (130) and an optical sensor (171) connected thereto, through which the user device (100) may perform various photographing functions such as taking pictures and recording video clips. For example, the camera subsystem (170) may perform a function of taking pictures of a user performing an exercise in a specified posture. For example, the user device (100) may obtain an image (e.g., an RGB-D image) of the user performing an exercise through the camera subsystem (170) and the optical sensor (171), and may provide the obtained exercise image of the user to be used to determine the user's exercise level.

[0074] In various embodiments, the user device (100) may include a communication subsystem (180) connected to a peripheral interface (130). The communication subsystem (180) may be comprised of one or more wired / wireless networks and may include various communication ports, radio frequency transceivers, and optical transceivers.

[0075] In various embodiments, the user device (100) includes an audio subsystem (190) connected to a peripheral interface (130), the audio subsystem (190) including one or more speakers (191) and one or more microphones (192), such that the user device (100) can perform voice-activated functions, such as voice recognition, voice replication, digital recording, and telephony functions.

[0076] In various embodiments, the user device (100) may include an I / O subsystem (140) connected to a peripheral interface (130). For example, the I / O subsystem (140) may control a touch screen (143) included in the user device (100) via a touch screen controller (141).

[0077] For example, the touch screen controller (141) may detect a user's contact and movement or cessation of contact and movement using any one of a plurality of touch sensing technologies, such as capacitive, resistive, infrared, surface acoustic wave technology, proximity sensor array, etc. In another example, the I / O subsystem (140) may control other input / control devices (144) included in the user device (100) via other input controller(s) (142). As an example, the other input controller(s) (142) may control one or more buttons, rocker switches, thumb wheels, infrared ports, USB ports, and pointer devices, such as a stylus.

[0078] The user device (100) according to one embodiment of the present invention has been described so far. According to the present invention, the user device (100) can determine a user's exercise level solely based on user feedback, without the need to collect user biometric data via sensors. In particular, by utilizing exercise difficulty to objectively compensate for subjective user feedback, the reliability of recommended exercises can be increased.

[0079] Hereinafter, with reference to FIG. 3, an exercise recommendation device (200) that provides an exercise recommendation service will be described.

[0080] Referring to FIG. 3, the exercise recommendation device (200) may include a communication interface (210), a memory (220), an I / O interface (230), and a processor (240), and each component may communicate with each other through one or more communication buses or signal lines.

[0081] The communication interface (210) can be connected to the user device (100) via a wired / wireless communication network to exchange data. For example, the communication interface (210) can receive user feedback on exercise and exercise performed by the user from the user device (100). For example, the communication interface (210) can receive exercise images related to the user performing the exercise from the user device (100). In addition, for example, the communication interface (210) can transmit an appropriate exercise to the user based on the user's exercise level.

[0082] Meanwhile, the communication interface (210) that enables transmission and reception of such data includes a wired communication port (211) and a wireless circuit (212), wherein the wired communication port (211) may include one or more wired interfaces, for example, Ethernet, Universal Serial Bus (USB), FireWire, etc. In addition, the wireless circuit (212) may transmit and receive data with an external device via an RF signal or an optical signal. In addition, the wireless communication may use at least one of a plurality of communication standards, protocols, and technologies, for example, GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol.

[0083] The memory (220) can store various data used in the exercise recommendation device (200). For example, the memory (220) can store user identification data using the exercise recommendation service, identification data of the user device (100), identification data of various exercises that can be provided to the user, exercise difficulty, body parts used in exercise, exercise content, links for using exercise content, exercise images of the user (e.g., exercise images obtained from the user device (100), etc. For example, the memory (220) can store a level determination algorithm that can determine the user's exercise level based on user feedback on exercise difficulty, and can store data used when executing the algorithm. For example, the memory (220) can store a learned artificial intelligence model (e.g., exercise level determination model) that can determine the user's exercise level based on an exercise image, and can store learning data thereof.

[0084] According to one embodiment, the exercise level determination model may be a model trained to receive a user's exercise video as input and determine the user's exercise level. For example, the exercise level determination model may receive a user's exercise video performing a specified exercise movement, analyze the user's exercise posture in the exercise video, and analyze the user's exercise performance ability. For example, the exercise level determination model may be a model trained to obtain various exercise performance information, such as the accuracy of the user's exercise posture, exercise speed, exercise amount, and the user's expression, through the user's exercise video, and determine the user's exercise level based on the exercise performance information. For example, the exercise level determination model may detect at least one exercise specified in the user's exercise video, and obtain various exercise performance information, such as the accuracy of the posture of the at least one detected exercise, the speed, the user's expression, and the number of times. For example, the exercise level determination model may obtain various information about the user's exercise performance through techniques such as segmentation, bounding box, key-point extraction, object tracking, and similarity comparison with a reference image for the user in the exercise video. Additionally, for example, the exercise level determination model can obtain various information about the exercise performance through scene understanding of the exercise video.

[0085] According to one embodiment, the exercise level determination model may determine the user's exercise level based on the exercise performance information. That is, the exercise level determination model may be a model trained to receive an exercise video of the user, analyze the user's exercise performance within the exercise video, and output the user's exercise level.

[0086] For convenience of explanation, the explanation focuses on the input and output values ​​of the exercise level determination model, but various network structures and learning methods that output data based on image analysis can be applied to the exercise level determination model.

[0087] In various embodiments, the memory (220) may include a volatile or non-volatile storage medium capable of storing various data, commands, and information. For example, the memory (220) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., an SD or XD memory, etc.), RAM, SRAM, ROM, EEPROM, PROM, network storage, cloud, and a blockchain database.

[0088] In various embodiments, the memory (220) may store configurations of at least one of an operating system (221), a communication module (222), a user interface module (223), and one or more applications (224).

[0089] An operating system (221) (e.g., embedded operating systems such as LINUX, UNIX, MAC OS, WINDOWS, VxWorks, etc.) may include various software components and drivers to control and manage general system operations (e.g., memory management, storage device control, power management, etc.) and may support communication between various hardware, firmware, and software components.

[0090] The communication module (223) can support communication with other devices through the communication interface (210). The communication module (220) can include various software components for processing data received by the wired communication port (211) or wireless circuit (212) of the communication interface (210).

[0091] The user interface module (223) can receive a user's request or input from a keyboard, touch screen, microphone, etc. through an I / O interface (230) and provide a user interface on the display.

[0092] The application (224) may include a program or module configured to be executed by one or more processors (240). Here, the application for providing user-customized exercise may be on a server farm.

[0093] The I / O interface (230) can connect at least one of input / output devices (not shown) of the exercise recommendation device (200), such as a display, a keyboard, a touch screen, and a microphone, to the user interface module (223). The I / O interface (230) can receive user input (e.g., voice input, keyboard input, touch input, etc.) together with the user interface module (223) and process commands according to the received input.

[0094] The processor (240) is connected to a communication interface (210), a memory (220), and an I / O interface (230) and can control the overall operation of the exercise recommendation device (200). The processor (240) can execute various commands to provide appropriate exercise to multiple users according to their physical abilities through an application or program stored in the memory (220).

[0095] The processor (240) may correspond to a computing device such as a Central Processing Unit (CPU) or an Application Processor (AP). Furthermore, the processor (240) may be implemented in the form of an integrated chip (IC), such as a System on Chip (SoC) in which various computing devices are integrated. Alternatively, the processor (240) may include a module for calculating an artificial neural network model, such as a Neural Processing Unit (NPU).

[0096] Below, a method for the processor (240) to provide exercise of appropriate difficulty level for each user will be described.

[0097] Figure 4 is a schematic flowchart of a user-customized exercise recommendation method according to one embodiment of the present invention.

[0098] Referring to FIG. 4, the processor (240) can determine the exercise difficulty of the exercise (S110). Specifically, the initial exercise difficulty may be pre-specified by the service provider and expressed numerically. If the exercise difficulty is not specified, the processor (240) can determine the exercise difficulty performed by the user based on the exercise identification data. In addition, for example, the processor (240) can use a learned artificial intelligence model to determine the exercise difficulty performed by the user based on the exercise identification data. Specifically, the processor (240) can obtain identification data including at least one of the type, intensity, time, frequency, duration, physical strength factor, and movable body part of the exercise performed by the user. Here, the physical strength factor may include the explosiveness, coordination, agility, balance, and speed required for the exercise. The processor (240) can determine the exercise difficulty using a learned artificial intelligence model that outputs the exercise difficulty based on the identification data.

[0099] In various embodiments, the processor (240) may determine the difficulty of an exercise by gender and age group based on identification data expressed in numbers, such as intensity, time, frequency, and duration of the exercise. In addition, the processor (240) may check the exercise difficulty matching each of a plurality of categories for one exercise based on the identification data. Specifically, the processor (240) may check the exercise difficulty by physical strength factor and by movable body part. For example, the processor (240) may specifically check the exercise difficulty for explosiveness (a measure indicating the level of explosiveness required) for a sprinting exercise, and the exercise difficulty for the abdominal muscles, thighs (quadriceps femoris, biceps femoris), and calves (tibialis anterior, triceps femoris) (a measure indicating the level of muscle strength required in the corresponding body part) for the abdominal muscles, thighs (quadriceps femoris, biceps femoris), and calves (tibialis anterior, triceps femoris) for the sprinting exercise. As another example, the processor (240) may specifically check the exercise difficulty for thigh flexibility for a sprinting exercise.

[0100] That is, the processor (240) can check the data that quantifies the degree of flexibility or muscle strength required for each movable body part applied to the exercise as the exercise difficulty. In various embodiments, the processor (240) can obtain a selection of an exercise to be performed by the user. Specifically, the processor (240) can obtain a selection of an exercise to be performed by the user from the user device (100) or obtain a selection of an exercise performed by the user. For example, in order to obtain a selection of an exercise to be performed by the user, the processor (240) can provide a list of exercises segmented by category to the user device (100). As another example, the processor (240) can recommend an exercise that the user can perform based on the user's gender, age, basic body data, presence or absence of a disease, etc. The processor (240) can provide at least one exercise to be performed by the user using user identification data based on a pre-learned algorithm. The processor (240) can stream at least one exercise content selected by the user or provide an external link that can stream the exercise content. Here, exercise content may include various visual and auditory content, such as videos, programs produced in slide format, and online video communications providing exercise lectures. For another example, to obtain user selections regarding the exercise performed, the processor (240) may provide the user device (100) with only a list of exercises segmented by category.

[0101] In this way, the processor (240) provides exercise content that matches the exercise depending on whether the exercise is performed, thereby omitting the cumbersome process of having to search for the exercise the user wants to do one by one and increasing user convenience.

[0102] After step S110, the processor (240) may provide a list of user feedback related to the results of the exercise (S120). Specifically, the processor (240) may provide the user device (100) with items that allow the user to select the perceived difficulty of the exercise in stages from among easy, normal, difficult, and painful. Meanwhile, the step-by-step selection items for dividing the perceived difficulty are not limited thereto, and may be set and classified in detail and with different names at the request of the service provider or user. For example, the items for dividing the perceived difficulty may be set with different names depending on the type of exercise.

[0103] In various embodiments, the processor (240) may provide multiple user feedback lists, each for a specific body part to which the exercise applies. For example, to facilitate understanding even for users new to the exercise, the processor (240) may provide an image visualizing the body part to which the exercise applies, along with the user feedback list.

[0104] In various embodiments, the processor (240) may replace the item selected by the user with one of a win, loss, or draw for the user and the exercise. For example, if the user feedback is "easy," the processor (240) may replace the win / loss for the user and the exercise with a win. Furthermore, if the user feedback is "average," the processor (240) may replace the win / loss for the user and the exercise with a draw. Furthermore, if the user feedback is "difficult" or "painful," the processor (240) may replace the win / loss for the user and the exercise with a loss. The processor (240) may score the replaced win / loss results to use the user feedback as a value for determining the user's exercise level. For example, the processor (240) may convert the user feedback to 1 point if the user wins, 0 points if the user loses, and 0.5 points if the user draws.

[0105] In various embodiments, the processor (240) may obtain an exercise image of the user who performed the provided exercise after step S110. For example, the processor (240) may obtain an exercise image of the user captured by a photographing device (e.g., a camera included in the user device (100) or the exercise recommendation device (200). In addition, in one embodiment, the processor (240) may input the obtained exercise image of the user into the exercise level determination model described with reference to FIG. 3 to obtain data on the user's exercise level. For example, the processor (240) may obtain an exercise image of the user who performed the exercise provided in step S110, input the exercise image into the exercise level determination model, and obtain one of win, loss, and draw as a value for determining the user's exercise level. For example, the processor (240) may input the exercise image of the user into the exercise level determination model to analyze exercise performance information such as the degree of exercise performance, speed, accuracy, number of times, and facial expression of the user.

[0106] In one embodiment, the exercise level determination model may output data indicating that the user won the exercise competition if, based on the analysis results, it is determined that the user performed the exercise easily and accurately. The exercise level determination model may output data indicating that the user lost the exercise competition if, based on the analysis results, it is determined that the user did not perform the exercise accurately or performed the exercise with difficulty. Furthermore, the exercise level determination model may output data indicating that the user drew the exercise competition if, based on the analysis results, it is determined that the user performed the exercise appropriately.

[0107] However, without being limited to the above-described example, the processor (240) may directly obtain the user's exercise level through the exercise level determination model. That is, the exercise level determination model may output win / loss data converted into win / loss data targeting exercise by taking the user's exercise video as an input value, or output the user's exercise level determined based on the exercise video. In addition, the exercise level determination model may output various data that can be used to determine the user's exercise level, and the format or type of the data is not limited.

[0108] According to various embodiments, the processor (240) may determine the user's exercise level based on various biometric data acquired from the user device (100). For example, the processor (240) may determine the user's exercise level based on various biometric data values, such as the user's heart rate, muscle oxygen saturation, blood sugar, and body temperature, acquired through other sensors (163) of the user device (100). For example, the processor (240) may compare biometric data values, such as the heart rate, muscle oxygen saturation, blood sugar, and body temperature, of a user performing a specified exercise with specified data to acquire win / loss data of the user performing the specified exercise. For example, if at least one of the heart rate, muscle oxygen saturation, and body temperature of a user performing the specified exercise rises above a specified value, the processor (240) may determine that the user has lost the exercise and output the win / loss data.

[0109] After step S120, the processor (240) may determine the user's exercise level for the exercise based on any one of the user feedbacks selected from the user feedback list (S130). Specifically, the processor (240) may determine the user's exercise level based on the user feedback on the exercise difficulty identified in step S110 using a preset level determination algorithm. In other words, the processor (240) may determine the user's exercise level based on how the user performed the exercise, which is considered difficult or easy, and the results thereof. Additionally, depending on the embodiment, the exercise level may be determined by including multiple other users who performed the exercise.

[0110] In various embodiments, the level determination algorithm may be designed to determine the user's exercise level using both the user's exercise level and the exercise difficulty level. The processor (240) may determine the user's exercise level for a given exercise based on user feedback, with the outcome predicted based on the user's exercise level and the exercise difficulty level, which have been previously set to default values ​​or have already been quantified.

[0111] In various embodiments, the processor (240) may determine the user's exercise level for exercise based on data (e.g., win / loss data or the user's exercise level information) output using the exercise level determination model. Furthermore, the processor (240) may determine the user's exercise level using data related to the user's exercise level output through the exercise level determination model and the level determination algorithm.

[0112] According to various embodiments, the processor (240) may obtain the user's win / loss data for the exercise based on the biometric data values ​​of the user performing the specified exercise, and determine the user's exercise level using the level determination algorithm based on the win / loss data.

[0113] In various embodiments, the processor (240) may use a level determination algorithm to adjust the exercise difficulty along with the user's exercise level.

[0114] According to one embodiment, for an exercise with a high exercise difficulty, if a user whose exercise level is not high reports that the exercise was easy through user feedback (or, if the user is determined to have performed the exercise easily as a result of analysis using the exercise level determination model), the exercise difficulty of the exercise may be set incorrectly. Accordingly, the processor (240) may determine whether the exercise difficulty needs to be corrected based on the user feedback (or, data related to the exercise level output by the exercise level determination model), and may correct the exercise difficulty using a preset level determination algorithm based on the determination result. Accordingly, the processor (240) may more accurately set the exercise difficulty based on user feedback from many people performing the exercise, and, through this, the user's exercise level determined using the exercise difficulty may also be determined to a reasonable value.

[0115] For example, the leveling algorithm can be designed similarly to rating systems such as the Elo rating system, the Glicko rating system, or TrueSkill. Furthermore, exercise difficulty and the user's fitness level can be determined in various ways, without limitation. For example, a user's fitness level and fitness difficulty could each be determined using different leveling algorithms.

[0116] According to various embodiments, the processor (240) may determine the user's exercise level by using the user's feedback and the user's exercise level obtained through the exercise level determination model. For example, the processor (240) may check the user's feedback to obtain the user's perceived exercise level, input the user's exercise image into the exercise level determination model to obtain the user's exercise level based on an objective value obtained, and determine the user's exercise level by considering the exercise level felt and input by the user and the exercise level determined through the exercise level determination model.

[0117] In relation to the preset level algorithm, FIG. 5 is a schematic diagram illustrating a method for determining a user's exercise level according to one embodiment of the present invention.

[0118] Referring to FIG. 5, the processor (240) can determine a score of user A according to the perceived difficulty of multiple exercises performed by user A. For example, if the user's perceived difficulty for exercise A is easy, the processor (240) can give a score of 1 point, if the user's perceived difficulty for exercise B is average, the processor (240) can give a score of 0.5 point, and if the user's perceived difficulty for exercise C is difficult, the processor (240) can predict user feedback for each exercise, considering the current exercise level of user A and the difficulty of each exercise. The processor (240) can obtain user feedback with the predicted result, and adjust the exercise level and exercise difficulty of user A for each exercise according to the user feedback.

[0119] In various embodiments, the above-described operation of checking the user's feedback may be replaced with an operation of obtaining data on the user's exercise level using the exercise level determination model via the processor (240). For example, the processor (240) may predict user feedback for each exercise by considering the current exercise level of user A and the difficulty level of each exercise, and may input the user's exercise video for the exercise into the exercise level determination model to adjust the exercise level and exercise difficulty of user A based on the obtained user exercise level.

[0120] In various embodiments, since exercise difficulty is data that quantifies the degree of flexibility or strength required for each body part, the user's exercise level can also be determined for flexibility and strength for each body part. That is, the processor (240) can determine exercise levels for multiple categories for a user who performed one exercise. For example, the processor (240) can determine the exercise level of user A for the strength of a first body part used in exercise B, the exercise level of user A for the strength of a second body part used in exercise B, and the exercise level of user A for the flexibility of a body part used in exercise B, for one exercise B. In addition, the processor (240) can determine the exercise level for one body part through multiple exercises. For example, if the first body part used in exercise C is the same as the first body part used in exercise B, the processor (240) can determine the user's exercise level for one body part through another exercise.

[0121] Referring again to FIG. 4, the processor (240) can provide at least one exercise corresponding to the user's exercise level (S140). Specifically, the processor (240) can provide various types of exercises that can exercise flexibility or muscle strength for each body part of the user.

[0122] In various embodiments, the processor (240) may provide identification data for performing an exercise along with pre-stored or retrieved exercise content. For example, the processor (240) may provide identification data for the exercise along with a link for playing the exercise content. Considering that the user may be performing the provided exercise for the first time, the processor (240) may assist the user in performing the exercise correctly by providing identification data for the exercise.

[0123] In various embodiments, the processor (240) may check user feedback from other users at a high or low level based on the user's exercise level, and generate a list of recommended exercises based on the checked user feedback. For example, the processor (240) may collect a plurality of exercises that may be rated as "average" or "difficult" based on user feedback from other users. In another example, the processor (240) may use a pre-learned exercise recommendation algorithm based on user feedback by exercise difficulty to determine an exercise that may be rated as "average" or "difficult" based on the user's exercise level. Here, the criteria for determining "average" or "difficult" may vary depending on the user's exercise goal. For example, before providing an exercise, the processor (240) may provide the user device (100) with a question regarding whether the exercise goal is recovery or ability improvement.

[0124] In various embodiments, the above-described operation of checking the user's feedback may be replaced with an operation of obtaining data on the user's exercise level using an exercise level determination model via the processor (240). For example, the processor (240) may input exercise videos of other users in the upper or lower exercise levels of the user into the exercise level determination model to obtain data on the user's exercise level, and may generate a list of recommended exercises for the user based on the obtained data. For example, the processor (240) may collect a plurality of exercises that may be rated as “average” or “difficult” in the determination of user exercise levels by other users. As another example, the processor (240) may determine an exercise that may result in user feedback of “average” or “difficult” based on the user’s exercise level by using a pre-learned exercise recommendation algorithm for the exercise level output through the exercise level determination model according to exercise difficulty. Here, the criteria for determining “average” or “difficult” may vary depending on the user’s exercise goal. For example, before providing an exercise, the processor (240) may provide a question to the user device (100) as to whether the exercise goal is recovery or ability improvement.

[0125] So far, an exercise recommendation device (200) according to one embodiment of the present invention has been described. According to the present invention, by dividing the user's exercise level into detailed categories such as flexibility or muscle strength for each body part, exercise with an appropriate load can be provided according to the user's physical ability.

[0126] Although the embodiments of the present invention have been described in more detail with reference to the attached drawings, the present invention is not necessarily limited to these embodiments, and various modifications may be implemented without departing from the technical spirit of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain it, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, it should be understood that the embodiments described above are illustrative in all aspects and not restrictive. The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of the rights of the present invention.

[0127]

[0128] [Explanation of symbols]

[0129] 10: Customized Exercise Recommendation System

[0130] 100: User Device

[0131] 110: Memory interface 120: Processor

[0132] 130: Peripheral Interface 140: I / O Subsystem

[0133] 141: Touch screen controller 142: Other input controllers

[0134] 143: Touch screen

[0135] 144: Other input control devices

[0136] 150: Memory 151: Operating System

[0137] 152: Communication Module 153: GUI Module

[0138] 154: Sensor processing module 155: Phone module

[0139] 156: Applications

[0140] 156-1, 156-2: Applications

[0141] 157: Digital Assistant Client Module

[0142] 158: User data

[0143] 160: Motion sensor 161: Light sensor

[0144] 162: Proximity sensor 163: Other sensors

[0145] 170: Camera subsystem 171: Optical sensor

[0146] 180: Communication Subsystem

[0147] 190: Audio subsystem

[0148] 191: Speaker 192: Microphone

[0149] 200: Exercise Recommendation Device

[0150] 210: Communication Interface

[0151] 211: Wired communication port 212: Wireless circuit

[0152] 220: Memory

[0153] 221: Operating System 222: Communication Module

[0154] 223: User Interface Module 224: Application

[0155] 230: I / O interface 240: Processor

Claims

1. A method for recommending customized exercise performed by a processor of an exercise recommendation device, A step for checking the exercise difficulty of the exercise performed by the user; A step of providing a list of user feedback related to the performance results of the above exercise; determining a user's exercise level for said exercise based on any one user feedback selected from the above user feedback list; and A method for recommending customized exercise to a user, comprising: providing at least one exercise corresponding to the exercise level of the user.

2. In paragraph 1, The steps to provide the above list of user feedback are: A method for recommending customized exercises, which is a step that provides items that allow the user to gradually select the perceived difficulty of the above exercise as one of easy, normal, hard, and painful.

3. In paragraph 2, The steps for determining the above exercise level are: A method for recommending a customized exercise, the method comprising: a step of determining a user's exercise level based on the user feedback on the confirmed exercise difficulty level using a pre-learned level determination algorithm.

4. In paragraph 3, After the step of providing the above list of user feedback, A step of replacing an item selected by the user with one of win, loss and draw targeting the user and the exercise; and A method for recommending customized exercises, further comprising: a step of scoring the substituted win-loss result; 5. In paragraph 3, The steps for determining the above exercise level are: A method for recommending a customized exercise, further comprising: a step of correcting the exercise difficulty level together with the exercise level of the user using the pre-learned level determination algorithm.

6. In paragraph 3, The steps for providing the above exercise are: A method for recommending customized exercises, further comprising: a step of checking user feedback of other users in the upper or lower tier based on the user's exercise level, and generating a list of recommendable exercises based on the checked user feedback; 7. In paragraph 1, The steps to check the difficulty of the above exercise are: A method for recommending customized exercises, which is a step for checking data that quantifies the level of flexibility or strength required for each body part applied to the above exercise.

8. In paragraph 1, Before the above verification step, A method for recommending a customized exercise to a user, further comprising a step of providing exercise content matching the exercise, depending on whether the user performs the exercise.

9. In paragraph 1, Before the above verification step, A step of obtaining identification data including at least one of the type, intensity, time, frequency, duration, physical strength factor and movable body part of the above exercise is further included, The steps to check the difficulty of the above exercise are: A method for recommending customized exercise, the method comprising: a step of checking the exercise difficulty level matching each of multiple categories for one exercise based on the above identification data.

10. In paragraph 1, The steps for providing the above exercise are: A method for recommending customized exercises, the method comprising: providing identification data for performing an exercise together with pre-saved exercise content or searched exercise content.

11. Communication interface; memory; and a processor operably connected to the communication interface and the memory; The above processor, An exercise recommendation device configured to determine an exercise difficulty of an exercise performed by a user, provide a list of user feedback related to a result of performing the exercise, determine an exercise level of the user for the exercise based on one user feedback selected from the list of user feedback, and provide at least one exercise corresponding to the exercise level of the user.

12. In paragraph 11, The above processor, An exercise recommendation device configured to provide items that allow the user to gradually select the perceived difficulty level of the above exercise as one of easy, normal, hard, and painful.

13. In paragraph 12, The above processor, An exercise recommendation device configured to determine a user's exercise level based on the user feedback on the above-determined exercise difficulty using a pre-learned level determination algorithm.

14. In paragraph 13, The above processor, After providing the above list of user feedback, An exercise recommendation device further configured to substitute an item selected by a user with one of a win, a loss, and a draw targeting the user and the exercise, and score the substituted win / loss result.

15. In paragraph 13, The above processor, An exercise recommendation device further configured to correct the exercise difficulty level together with the exercise level of the user using the above-mentioned pre-learned level determination algorithm.

Images