KR102811720B1 - Method and Apparatus for workout guidance - Google Patents

Abstract

As a preferred embodiment of the present invention, the AI exercise guide device is characterized by including a PMW _estimation unit that estimates PMW of an exercise machine on which a user wishes to exercise based on an estimated muscle strength value calculated _based on user data; and a PMW guide unit that provides a PMW _individual for the exercise machine by supplementing an objectification index of each user to the PMW estimation.

Description

AI workout guidance device and method {Method and Apparatus for workout guidance}

The present invention relates to a method for automatically providing a target weight of an exercise machine by taking into account the personal characteristics of a user.

Weight training equipment is provided in various forms depending on the body part or purpose of use to increase muscle strength, and is mainly designed to train the upper and lower body using hands or feet. The user can perform exercise by moving the selected weight through the exercise structure of the exercise equipment.

However, there is a problem that it is difficult to confirm whether the user is using the exercise equipment appropriately according to his/her physical characteristics, exercise performance ability, or purpose of the exercise equipment.

KR 10-1968621 B1

As a preferred embodiment of the present invention, the AI exercise guide device provides an appropriate initial target weight of exercise equipment used by a user using only user data including the user's gender, age, weight, height, BMI, and body fat percentage.

As a preferred embodiment of the present invention, the AI exercise guide device automatically adjusts the target weight of the exercise equipment according to the user's exercise purpose.

In a preferred embodiment of the present invention, even when the same initial target weight is provided for each piece of exercise equipment to a first user and a second user who are the same in terms of gender, age, weight, height, BMI, body fat percentage, etc., a method is proposed in which a target weight suitable for each first user and a second user is newly set and provided for each piece of exercise equipment used by the first user and the second user by further reflecting a personal objectification index including the exercise records of the first user and the second user.

As a preferred embodiment of the present invention, the AI exercise guide device learns and analyzes the individual objectification index of each user to continuously update the target weight of exercise equipment differentiated for each user, thereby providing a method for the user to use the exercise equipment in an optimized manner.

As a preferred embodiment of the present invention, the AI exercise guide device includes a PMW _estimation unit which estimates PMW of an exercise equipment on which a user wishes to exercise based on an estimated muscle strength value calculated based on user data; and a PMW _guide unit which provides _{an individual} PMW for the exercise equipment by supplementing a user's personalized objectification index to the PMW estimation; wherein the user's personalized objectification index includes at least some of the regularities of the weight, number of repetitions (Reps), number of sets, exercise trajectory, movement speed, and number of repetitions (Reps) per set of the exercise equipment recognized when the user uses the exercise equipment for a preset period of time.

As a preferred embodiment of the present invention, the AI exercise guide device is characterized by further including an exercise target setting unit that automatically sets an initial target weight of an exercise device that the user wishes to use based on the PMW _estimation .

As a preferred embodiment of the present invention, the AI exercise guide device is characterized by further including an AI exercise target setting unit that automatically updates the target weight of the exercise equipment that the user wishes to use based on the PMW _individual .

As a preferred embodiment of the present invention, the PMW guide unit is characterized in that it includes a PMW update unit that updates _{the PMW individual to} a value greater than the PMW _estimation when the objectification index is greater than or equal to a first reference _value , and to a value less than the PMW _estimation when the objectification index is less than or equal to a second reference value. The PMW update unit is characterized in that it renews the updated PMW _individual based on the objectification index every preset period unit.

As a preferred embodiment of the present invention, the PMW guide unit is characterized by including a display unit that displays a target weight of the exercise equipment that is automatically updated based on a PMW _individual . The display unit is characterized by further displaying a change in the target weight of the exercise equipment during the preset period.

As a preferred embodiment of the present invention, the PMW guide section is characterized in that, when the motion trajectory is used as the objectification index, the completeness of the motion trajectory is determined by using the start time of ascent, start time of descent, average speed of the ascent section, average speed of the descent section, and height identified from the motion trajectory, and the degree of completeness of the motion trajectory is converted into a number and used as the objectification index.

As a preferred embodiment of the present invention, the PMW guide section is characterized in that, when the number of repetitions (Reps) is used as the objectification index, the completeness of the number of repetitions (Reps) is determined based on the regularity between the motion trajectories of each of the total number of repetitions constituting one set, and the degree of completeness of the number of repetitions (Reps) is converted into a numerical value and used as the objectification index.

As another preferred embodiment of the present invention, an AI exercise guide method includes the steps of: estimating PMW of an exercise equipment on which a user wishes to exercise based on an estimated muscle strength value calculated based on user data by a PMW _estimation unit; and providing _{an individual} PMW for the exercise equipment by supplementing a user's individual objectification index to the PMW _estimation by the PMW guide unit; wherein the user objectification index includes at least some of regularities of the weight, number of repetitions (Reps), number of sets, exercise trajectory, movement speed, and number of repetitions (Reps) per set of the exercise equipment recognized when the user uses the exercise equipment for a preset period of time.

As a preferred embodiment of the present invention, the AI exercise guide device has the effect of automatically setting a target weight suitable for the user for each exercise machine when user data including at least some of the user's gender, age, weight, height, BMI, and body fat is input.

As a preferred embodiment of the present invention, the AI exercise guide device learns and analyzes the user's exercise records to continuously update the target weight of the exercise equipment used by the user, thereby providing a method for the user to use the exercise equipment in an optimized manner.

As a preferred embodiment of the present invention, the AI exercise guide device has the effect of increasing the effect of exercise by suggesting a new method of using exercise equipment according to the user's exercise record and changed physical condition of the user.

As a preferred embodiment of the present invention, the AI exercise guide device also has the effect of automatically setting a target weight suitable for the user for each exercise device according to the user's exercise purpose.

FIG. 1 illustrates a smart gym system using an AI exercise guide device as a preferred embodiment of the present invention.
FIG. 2 illustrates an example of an exercise device in which an AI exercise guide method equipped in a smart gym is implemented, as a preferred embodiment of the present invention.
FIG. 3 is a diagram illustrating the internal configuration of an exercise machine and a smart gym server in which an AI exercise guide method is implemented in a smart gym system, as a preferred embodiment of the present invention.
FIG. 4 is a diagram showing the internal configuration of an AI exercise guide device as a preferred embodiment of the present invention.
FIG. 5 illustrates an example of a user interface of an AI exercise guide device as a preferred embodiment of the present invention.
FIG. 6 illustrates an example of a movement trajectory detected in an exercise device in which an AI exercise guide method is implemented, as a preferred embodiment of the present invention.
Figures 7 to 9 illustrate an example of analysis based on the number of repetitions in an objectification index calculation unit, as a preferred embodiment of the present invention.
Fig. 10 is a preferred embodiment of the present invention. In the machine learning processing unit An example of classifying exercise trajectory big data is shown.
FIG. 11 illustrates an example of measuring movement trajectories for a chest press exercise machine of two users as a preferred embodiment of the present invention.
Figure 12 illustrates a flow chart of an AI exercise guide method as a preferred embodiment of the present invention.

Hereinafter, various embodiments of the present invention will be described in detail with reference to the attached drawings so that a person having ordinary skill in the art to which the present invention pertains can easily practice the present invention.

FIG. 1 illustrates a smart gym system using an AI exercise guide device as a preferred embodiment of the present invention.

A smart gym system (100) includes a smart gym server (110), at least one exercise machine (100a, 100b, 100c, ..., 100n), at least one user terminal (120), and an administrator terminal (130).

In FIG. 1, a smart gym server (110) can communicate with a first smart gym (112), a second smart gym (114), and an nth smart gym (116) located at physically different locations, and can transmit and receive data with at least one exercise machine (100a, 100b) placed in the first smart gym (112), at least one exercise machine (100c) placed in the second smart gym (114), and at least one exercise machine (100n) placed in the nth smart gym (116).

As a preferred embodiment of the present invention, a smart gym refers to a physical space where a user provides exercise records using exercise equipment to a smart gym server (110), and the smart gym server (110) learns and analyzes the user's exercise records to provide an exercise prescription tailored to the user. A smart gym can be implemented as a fitness center, a health club, a space equipped with exercise equipment, etc.

Users who come to exercise at the smart gym (USER A, USER B, USER C, ..., USER N) can enter the smart gym after verifying their identity when entering. For example, the user can enter after verifying their membership by tagging their user terminal (120) to an unmanned terminal such as a kiosk at the entrance to the smart gym using NFC (Near Field Communication) or RFID (Radio Frequency IDentification), or can enter after verifying their membership through biometric information such as facial recognition at the unmanned terminal.

Information about a user whose membership has been verified can be transmitted from the smart gym server (200) to at least one of the exercise machines (100A, 100B, 100C, 100N) through the network. For example, the smart gym server (200) can transmit information about the user to the exercise machine to which the user has tagged the terminal (120). In a preferred embodiment of the present invention, information about the user is also referred to as user data and includes at least some or all of the user's gender, age, weight, height, BMI, and body fat percentage.

The smart gym server (110) can guide the first user (USER A) and the second user (USER B) who use at least one exercise machine (100a, 100b) placed in the smart gym (112) with an exercise method, exercise intensity, exercise sequence, etc. suitable for each user. In addition, the smart gym server (110) can provide values such as target weight and recommended usage speed of each exercise machine (100a, 100b). In addition, the smart gym server (110) can receive exercise records of the first user (USER A) and the second user (USER B) who use each exercise machine (100a, 100b). In addition, the smart gym server (110) can further receive health information such as the user's heart rate, blood pressure, pulse, etc., and log information, etc. from the user terminal (120).

The smart gym server (110) can be implemented in the form of a cloud server. The smart gym server (110) can integrate and manage information collected from each exercise machine in smart gym exercise centers at different locations. For example, the smart gym server (110) can integrate and manage the history of a first user using exercise machines at a smart gym (112) at a first location and the history of a first user using exercise machines at a smart gym (114) at a second location.

As a preferred embodiment of the present invention, at least one exercise device (100a, 100b, 100c, ..., 100n) may be a stretching exercise device, a weight exercise device, or an aerobic exercise device. The weight exercise device includes a free weight device and a machine device. At least one exercise device (100a, 100b, 100c, ..., 100n) provides an exercise guide suitable for the user through a display attached to the exercise device or a display capable of communicating with the exercise device via wired or wireless communication. For example, in the case of a stretching device, an exercise guide related to stretching to be used by the user is provided via a smart mirror capable of communicating with the stretching device via wired or wireless communication. However, the present invention is not limited thereto, and the exercise guide may be provided using various output methods such as a speaker and vibration.

At least one exercise machine (100a, 100b, 100c, ..., 100n) can perform wired or wireless communication with a smart gym server (110), a user terminal (120), and an administrator terminal (130).

As a preferred embodiment of the present invention, the user terminal (120) may be implemented in the form of a smart phone, a smart watch, a handheld device, a wearable device, etc. In addition, the user terminal (120) may install an application for using a smart gym system, etc. The user terminal (120) may receive exercise sequence information, etc. from the smart gym server (120). An exercise sequence refers to an exercise plan planned in consideration of the user's physical strength and exercise ability. The exercise sequence includes information such as a list of exercise equipment to be used by the user, target weight of each exercise equipment, and number of times of use.

When a user uses at least one exercise machine (100a, 100b, 100c, ..., 100n) in a smart gym system (100), the user can perform communication through tagging such as NFC or RFID using a terminal (120) or perform identity verification using the user's physical characteristics. When the user's identity verification is completed, the smart gym server (110) can transmit user data to the exercise machine tagged by the user.

FIG. 3 is a diagram illustrating the internal configuration of an exercise machine and a smart gym server in which an AI exercise guide method is implemented in a smart gym system, as a preferred embodiment of the present invention.

As a preferred embodiment of the present invention, exercise equipment (300) in a smart gym can communicate with a smart gym server (380), a user terminal (390), and an external server (388).

As a preferred embodiment of the present invention, the exercise device (300) includes a processor (310), a sensing unit (320), a communication unit (340), an exercise guide unit (360), and a display (370). In addition, the device may further include a camera unit (330) and an image processing unit (350). The processor (310) may further include an AI processing unit (312) as needed.

Referring further to Fig. 2, the shoulder press (200) represents an example of an exercise device (300) to which an AI exercise guide method used in a smart gym is applied. The exercise device (300) will be described with reference to Figs. 2 and 3.

The sensing unit (220) may be installed in the frame structure (213) of the exercise body (210). The frame structure (213) includes a base frame (231a), a guide rail (231b), and a connecting line (231c). The sensing unit (220) irradiates a laser beam toward the pin structure (215), receives the reflected laser beam, and measures the distance (D) (S220) from the sensing unit (220) to the pin structure (215) in real time or in a preset t time unit. Through this, the sensing unit (220) can detect at least one of the position, movement speed, and movement direction of the weight member (211) selected by the pin structure (215) in real time. In addition, when the user pushes the handle (212) of the exercise equipment (200) to move the weight plate, the sensing unit (220) can measure the distance (D) (S220) to the pin structure (215) inserted into the weight plate and detect the movement trajectory based on this.

The communication unit (340) can receive user input through the display unit (230) or send and receive user data from the user DB (382) of the smart gym server (380). The communication unit (340) can also communicate with an external server (388).

The exercise guide unit (360) can provide the user with information such as user data received from the smart gym server (380), target weight of the exercise equipment, movement speed guide of the exercise equipment, breathing guide when using the exercise equipment, and exercise sequence. An example of providing the movement speed guide of the exercise equipment to the user in the exercise guide unit (360) is described with reference to FIGS. 5 and 10.

The graph of Fig. 10 shows an example of classifying the movement trajectories for a specific exercise machine acquired from the population by the machine learning processing unit (384) into 7 patterns (1010 to 1070). The population is initially targeted at a preset number of n people, but data from users of the smart gym can be continuously accumulated and used.

The machine learning processing unit (384) can classify the movement trajectory patterns of the population and determine the proportion of the population belonging to each pattern. The machine learning processing unit selects the movement trajectory with the highest movement effect among the seven analyzed movement trajectory patterns. In this case, the machine learning processing unit selects the second movement trajectory (1020) and the sixth movement trajectory (1060) with the smallest deviation from the preset reference value trajectory (1012) with the highest movement effect. The second movement trajectory (1020) corresponds to 21.7% of the population, and the sixth movement trajectory (1060) corresponds to 23.1% of the population.

The exercise guide processing unit (386) can determine which pattern the detected user's exercise trajectory belongs to. In addition, the change in the user's exercise trajectory can be determined according to the exercise load, the number of times of exercise, and the time. For example, when the first user uses the chest press with 60 kg, the exercise trajectory belongs to the second exercise trajectory (1020), but when the first user uses the chest press with 70 kg, the exercise trajectory belongs to the first exercise trajectory (1010), the exercise guide processing unit (386) can determine that the load suitable for the first user is 60 kg.

The exercise guide processing unit (386) provides the user with a movement speed guide VG1 (Fig. 5, 530) of exercise equipment suitable for the user through the exercise guide unit (360). The movement speed guide VG1 (530) means a movement speed suitable for the user to obtain an effect suitable for the exercise purpose when using the exercise equipment. For example, when the user pushes the shoulder press in accordance with the movement of the movement speed guide VG1 (530), the measured speed V1 (520) at which the user pushes the shoulder press is displayed together on the reference line (510).

The smart gym server (380) can calculate an estimated muscle strength value of a specific muscle strength based on user data. Then, it determines the PMW _estimate of the exercise equipment to be used by the user based on the estimated muscle strength value, and automatically sets the initial target weight of the exercise equipment to be used by the user based on the user's exercise purpose and the PMW _estimate . In a preferred embodiment of the present invention, PMW (Personal Maximum Weight) refers to the muscle strength that an individual can exert against the resistance of a weight with maximum effort. Examples of PMW include 1RM, 4RM, etc. The PMW _estimate represents a value that estimates the user's PMW based on the estimated muscle strength value, and the smart gym server (380) can determine the PMW _estimate for each exercise equipment.

The smart gym server (380) can provide the initial target weight of the exercise equipment to be used by the user to the exercise guide unit (360) of the exercise device (300), and the exercise guide unit (360) can display the initial target weight of the exercise equipment to be used by the user on the display (370). An example of presenting the initial target weight (FIGS. 5 and 550) of the exercise equipment to be used by the user is shown in FIG. 5.

The smart gym server (380) can also predict PMW _individual , which is a maximum strength value that supplements the user's individual objectification index to the PMW _estimation . In this case, the smart gym server (380) can update the initial target weight of the exercise equipment set based on the PMW _estimation to provide a new target weight that additionally reflects the user's individual characteristics. An example of the objectification index is an exercise record, and includes the weight of the exercise equipment, the number of repetitions (Reps), the number of sets, the exercise trajectory, the movement speed, and the regularity of the number of repetitions (Reps) per set, which are identified when using the exercise equipment.

The camera unit (330) is built into the exercise device (300) or can communicate with the exercise device (300) via wired or wireless communication, and can capture the user's exercise posture. The image processing unit (350) can analyze the user's exercise posture captured by the camera unit (330) through the processor (310). In addition, the AI processing unit (312) can learn the image processing results of the exercise posture captured when the user exercises according to the target weight of the exercise device, and transmit the learning results to the smart gym server (380). The AI processing unit (312) can also process or learn the user's objectification index.

The smart gym server (380) includes a user DB (382), a machine learning processing unit (384), and an exercise guide processing unit (386). The user DB (382) stores and manages user data. The user data includes the user's gender, age, weight, height, BMI, and body fat percentage.

The machine learning processing unit (384) learns and processes an objectification index that includes exercise records of exercise equipment used by the user in the smart gym. For examples of learning the objectification index in the machine learning processing unit (384), refer to FIGS. 6 to 11.

The machine learning processing unit (384) can update the PMW _estimation to the PMW _individual based on the objectification index of the exercise equipment used by the user in the smart gym for a certain period of time. If the objectification index is equal to or greater than the first reference value, the machine learning processing unit (384) can update the PMW _individual to a value greater than the PMW _estimation , and if the objectification index is equal to or less than the second reference value, _{the PMW individual to} a value less than the PMW _estimation .

The machine learning processing unit (384) may _reset the user's maximum strength value to PMW individual greater than the PMW _estimate based on the objectification index determined based on the user's exercise record, etc., if it is determined that the user's exercise ability is greater than the PMW estimate estimated from the _user 's specific muscle strength. On the other hand, if it is determined that the user's exercise ability is less than the PMW _estimate estimated from the user's specific muscle strength based on the objectification index determined based on the user's exercise record, etc., it may reset the user's maximum strength value to PMW _individual less than the PMW _estimate .

Through this, even if the PMW _estimates of the first and second users who have the same user gender, age, weight, height, BMI, and body fat percentage are estimated to be the same, the machine learning processing unit (84) can learn and predict PMW _individuals suitable for the first and second users for each exercise equipment used by the first and second users by further reflecting the individual objectification index including the exercise records of the first and second users.

In other words, even if the user data related to physical conditions such as the user's gender, age, weight, height, BMI, and body fat percentage are the same, the machine learning processing unit (284) can learn and predict the PMW _individual , which is the maximum muscle strength value that further reflects the individual objectification index that varies depending on the individual user's muscle development status, range of motion, body proportions, exercise habits, exercise achievement rate, etc.

The sensing unit (320) can also identify the movement trajectory based on the distance information sensed while the user is using the shoulder press. The machine learning processing unit (384) can determine the completeness of the movement trajectory by using at least some of the rising start time (611), the falling start time (613), the rising section speed V1 (S610), the falling section speed V2 (S620), the rising section average speed, the falling section average speed, and the height H (612) identified from the movement trajectory detected while the user is using the shoulder press, and can convert the degree of completeness of the movement trajectory into a number and use it as an objectification index.

As another preferred embodiment of the present invention, when the machine learning processing unit (384) uses the number of repetitions (Reps) as an objectification index, the completeness of the number of repetitions (Reps) can be determined based on the regularity between the movement trajectories of each of the total number of repetitions constituting one set, and the degree of completeness of the number of repetitions (Reps) can be converted into a numerical value and used.

The exercise guide processing unit (386) can also provide updated target weights of exercise equipment based on the PMW _individual received from the machine learning processing unit (384).

Fig. 4 is a diagram showing the internal configuration of an AI exercise guide device as a preferred embodiment of the present invention. The AI exercise guide device (400) includes a smart gym server or terminal.

The AI exercise guide device (400) includes a PMW estimation unit (410), a PMW guide unit (420), an exercise target setting unit (430), an AI exercise target setting unit (440), and a display unit (450). The PMW estimation unit (410) further includes a muscle strength estimation unit (412) and a detection unit (414). The PMW guide unit (420) further includes an objectification index calculation unit (422) and a PMW update unit (424).

The muscle strength estimation unit (412) estimates an estimated muscle strength value for a specific muscle strength of the user based on the user data. The muscle strength estimation unit (412) calculates an estimated muscle strength value for a specific muscle strength of the user as in one embodiment of mathematical expression 1 using the user's gender, BMI, body fat percentage, and age information. If the user's gender, BMI, body fat percentage, and age information are all the same, the same estimated muscle strength value is calculated. An example of the specific muscle strength may be grip strength.

In mathematical expression 1, A, B, C, D, and E represent preset values.

The detection unit (414) detects a percentile value to which the estimated muscle strength value belongs from the preset adult muscle strength percentile values obtained from an external server (Fig. 3, 388) or as shown in Tables 1 and 2. Table 1 shows the percentile of adult relative grip strength for men, and Table 2 shows the percentile of adult relative grip strength for women.

Percentile years 19-29 30-39 40-49 50-59 60-69 90 **.* ... **.* ... 50 57.2 56.1 **.* **.* 40 **.* 55.9 **.* 53.8 49.2 ... 10 **.* ... **.*

Percentile years 19-29 30-39 40-49 50-59 60-69 90 **.* ... 47.5 ... 50 **.* 46.3 43.8 **.* **.* 40 40.3 **.* **.* **.* 34.1 ... 10 31.7 ... **.*

For example, if the estimated muscle strength value of a 32-year-old male is calculated as 55.9 in the muscle strength estimation unit (412), the detection unit (414) detects the percentile number 40, to which the estimated muscle strength value of a 32-year-old male is 55.9, from the preset adult muscle strength percentile values as shown in Table 1.

The PMW estimation unit (410) _estimates the PMW of the exercise equipment that the user wants to use by using the PMW _estimation percentile value that matches the percentile value of the estimated muscle strength value detected by the detection unit (414). In a preferred embodiment of the present invention, the PMW estimation unit (410) may store the PMW _estimation percentile value of the exercise equipment obtained from the population that uses the exercise equipment or download it from the smart gym server.

The smart gym server stores a mapping table that stores PMW _estimated percentiles for each piece of exercise equipment, and the PMW _estimated percentiles can be updated at preset intervals by further reflecting data of users using each piece of exercise equipment in the smart gym. In more detail, the machine learning processing unit (384) of the smart gym server (380) initially generates a matching table including PMW _estimated percentiles based on PMW data acquired from a preset population. Thereafter, the machine learning processing unit (384) continuously collects PMW data of users using exercise equipment provided in the smart gym, and can update the matching table, which provides PMW _estimated percentiles generated based on PMW data acquired from the preset population, at preset intervals.

Tables 3 to 5 illustrate an example of a mapping table used in the PMW estimation unit (410). In Tables 3 to 5, only some of the PMW10 percentile values and the PMW90 percentile values are displayed for convenience of explanation, and it should be noted that the values described are an example to help understanding of the invention.

As a preferred embodiment of the present invention, an example of a PMW percentile value and matching table of exercise equipment obtained from a population for chest press exercise equipment in the PMW estimation unit (410) is as shown in Table 3.

PMW percentile Initial population PMW (kg) Updated population PMW (kg) PMW90 102.7 107.8 ... PMW50 67.2 67.8 PMW40 65.1 64.7 ... PMW10 24.6 23.9

As a preferred embodiment of the present invention, an example of a PMW percentile value and matching table of exercise equipment obtained from a population for leg extension exercise equipment in the PMW estimation unit (410) is as shown in Table 4.

PMW _Estimated Percentiles Initial population PMW _estimate (kg) Updated population PMW _estimate (kg) PMW90 103.3 107.8 ... ... ... PMW50 67.3 69.2 PMW40 66.5 66.8 ... ... ... PMW10 24.6 24.9

As a preferred embodiment of the present invention, an example of a matching table that provides PMW _estimation percentile values of exercise equipment obtained from a population for shoulder press exercise equipment in the PMW estimation unit (410) is as shown in Table 5.

PMW percentile Initial population PMW (kg) Updated population PMW (kg) PMW90 64.5 65.5 ... ... ... PMW50 43.3 43.2 PMW40 41.2 40.2 ... ... ... PMW10 16.1 16.3

When the PMW estimation unit (410) detects the percentile 40 to which the estimated muscle strength value of 55.9 for a 32-year-old male belongs among the preset adult muscle strength percentiles as shown in Table 1, it estimates the PMW of the exercise equipment corresponding to the percentile 40.

Referring to Tables 3 to 5, the PMW estimation unit (430) _estimates the PMW of the chest press exercise machine as 65.1 kg corresponding to the PMW40 percentile based on the 'initial population PMW (kg)'. The PMW _estimation of the leg extension exercise machine is estimated as 66.5 kg corresponding to the PMW40 percentile. And, the PMW _estimation of the shoulder press exercise machine is estimated as 41.2 kg corresponding to the PMW40 percentile.

In another preferred embodiment of the present invention, if big data of users using exercise equipment in a smart gym is further collected in addition to PMW data of an initially preset population, the PMW estimation unit (430) may use updated PMW data such as “updated population PMW (kg)” of Tables 3 to 5. In this case, the PMW _estimation of the chest press exercise equipment may be updated to 64.7 kg corresponding to the PMW 40 percentile. The PMW _estimation of the leg extension exercise equipment may be updated to 66.8 kg corresponding to the PMW 40 percentile. In addition, the PMW _estimation of the shoulder press exercise equipment may be updated to 40.2 kg corresponding to the PMW 40 percentile.

The exercise goal setting unit (430) sets the initial target weight of each exercise device based on the PMW _estimation of each exercise device estimated by the PMW estimation unit (410). The exercise goal setting unit (430) can set the initial target value of each exercise device by further reflecting the user's exercise purpose received through the user interface.

The exercise goal setting unit (430) can set different initial target values for each exercise device depending on whether the user's exercise purpose is free exercise (541), standard exercise (542), muscle strengthening (543), or conditioning (544).

In the case of free exercise (541), the initial target value of the exercise equipment can be set to PMW _estimation *P _Free (%). In the case of standard exercise (542), the initial target value of the exercise equipment can be set to PMW _estimation *P _Standard (%). In the case of muscle enhancement (543), the initial target value of the exercise equipment can be set to PMW _estimation *P _{Muscle Enhancement} (%). In addition, in the case of conditioning (544), the initial target value of the exercise equipment can be set to PMW _estimation *P _Conditioning (%).

As a preferred embodiment of the present invention, P _{muscle gain} (%) may be set to 65 to 85%, and the number of repetitions may be set to 6 to 12 times. As a preferred embodiment of the present invention, if the exercise purpose is muscle gain, the reflected weight P _{muscle gain} (%) may use a preset value. In addition, the weight P _{muscle gain} (%) may be readjusted by receiving objective index feedback, such as the completeness of the user's exercise trajectory for the initial target weight suggested to the user, the user's exercise trajectory by the number of exercise repetitions, etc.

Assuming that the user selects the exercise purpose as standard (542) through the user interface provided on the display (500), the exercise goal setting unit can set 25 kg as the initial target weight for the user after reflecting P _standard (%) = 60 when the PMW _estimate of the shoulder press exercise machine is 40.2 kg. 40.2 kg * 60% = 24.12 kg, and the closest 25 kg among the weights supported by the exercise machine can be set as the initial target weight.

As a preferred embodiment of the present invention, the PMW guide unit (420) provides a PMW _individual for the exercise equipment by supplementing the PMW _estimate estimated by the PMW estimation unit (410) with an objectification index for each user. The PMW guide unit (420) provides a PMW _individual suitable for each user by reflecting the exercise records of each user for different users who have the same PMW _estimate for the same exercise equipment. Even when the same user uses the same exercise equipment and the PMW _estimate is estimated identically, the PMW guide unit (420) provides a PMW _individual suitable for the user at the present time by reflecting the user's exercise records for a certain period of time. The PMW guide unit (420) can continuously provide an exercise program suitable for the user by using the PMW _individual that reflects the user's physical condition, stamina, and exercise log.

The PMW guide unit (420) can display at least one of the muscles activated when the user uses the exercise equipment selected by the user on the display unit (450), the PMW _individual , or the target weight calculated based on the PMW _individual .

The PMW guide unit (420) includes an objectification index calculation unit (422) and a PMW update unit (424). The objectification index calculation unit (422) calculates an objectification index by using at least some of the weight, repetitions (Reps), number of sets, movement trajectory, movement speed, and regularities of repetitions (Reps) per set of the exercise equipment identified when the user uses the exercise equipment for a preset period of time.

The PMW update unit (424) updates the PMW _individual to a value greater than the PMW _estimate if the objectification index calculated by the objectification index calculation unit (422) is greater than or equal to the first reference value, and updates the PMW _individual to a value less than the _{PMW estimate} if the objectification index is less than or equal to the second reference value. The PMW update unit (424) can renew the PMW _individual updated based on the objectification index at preset intervals.

The AI exercise goal setting unit (440) updates the target weight of each exercise equipment based on the PMW _individual calculated by the PMW guide unit (420). In addition, the AI exercise goal setting unit (440) can set the initial target value of each exercise equipment by further reflecting the user's exercise purpose received through the user interface. The target weight of each exercise equipment is updated differently depending on whether the user's exercise purpose is free exercise (541), standard exercise (542), muscle strengthening (543), or conditioning (544).

As a preferred embodiment of the present invention, a case where the objectification index calculation unit (422) uses the motion trajectory as an objectification index will be described with reference to Fig. 6. The objectification index calculation unit (422) determines the completeness of the motion trajectory using the ascent start time (611), the descent start time (613), the ascent section speed V1 (S610), the descent section speed V2 (S620), the ascent section average speed, the descent section average speed, and the height H (612), and converts the degree of completeness of the motion trajectory into a number and uses it as an objectification index.

For example, the objectification index calculation unit (422) determines that the starting point of ascent (611) is appropriate if it is between 0 and t _a seconds according to preset criteria, and that it is late if it exceeds t _a . In addition, the completeness can be given a score of upper, middle, lower, or in units of 1 to 10 points according to preset criteria for the appropriate starting point of ascent (611). Similarly, the rising section speed V1 (S610) can be determined to be appropriate if it is between Va and Vb according to preset criteria, and can be determined to be fast if it exceeds Vb, and slow if it is less than Va, and the judgment results of appropriate, fast, and slow can be given a score of upper, middle, lower, or in units of 1 to 10 points, respectively.

In the same manner, the objectification index calculation unit (422) determines the completeness of the movement trajectory detected when the user uses the exercise equipment by using at least some of the ascent start time (611), the descent start time (613), the ascent section speed V1 (S610), the descent section speed V2 (S620), the ascent section average speed, the descent section average speed, and the height H (612).

When the PMW update unit (424) uses the completeness value of the motion trajectory as an objectification index, if the objectification index is equal to or greater than the first reference value, for example, 8 points, _{the PMW individual is} updated to a value greater than the PMW _estimate . For example, if the user's objectification index is 9 points and the first reference value is 8 points, the PMW _individual can be updated to a value that is n% (where n is a natural number) higher than the PMW _estimate . In addition, if the objectification index is equal to or less than the second reference value, for example, 6 points, _the PMW _individual is updated to a value smaller than the PMW _estimate . In addition, if the objectification index exceeds the second reference value and is less than the first reference value, the PMW _individual is maintained as the PMW _estimate value.

As another preferred embodiment of the present invention, a case where the number of repetitions (Reps) is used as an objectification index in the objectification index calculation unit (422) will be described with reference to FIGS. 7 to 9. The objectification index calculation unit (422) determines the completeness of the number of repetitions (Reps) based on the regularity between the movement trajectories of each of the total number of repetitions constituting one set, and converts the degree of completeness of the number of repetitions (Reps) into a numerical value and uses it as an objectification index.

Figures 7 to 9 illustrate examples of motion trajectories detected while the first to third users performed the city drag press 12 times in one set. In Figures 7 to 9, the x-axis represents time and the y-axis represents the displacement of the exercise equipment.

The objectification index calculation unit (422) determines whether all repetitions in one set have been completed. It determines whether all 12 repetitions have been performed or whether some repetitions were given up and determined. Then, the objectification index calculation unit (422) determines the completeness of the repetitions (Reps) based on the regularity between the movement trajectories of the first user's 12 repetitions (711~714, 721~724, 731~734), the second user's 12 repetitions (811~814, 821~824, 831~834), and the third user's 12 repetitions (911~914, 921~924, 931~934). In this case, it can be determined by dividing into early regularity, middle regularity, and late regularity.

For example, the initial regularity of the 1st to 4th times (711 to 744, 911 to 914) of the 1st user of Fig. 7 and the 3rd user of Fig. 9 is high because the four motion trajectories are almost constant. In this case, the initial regularity can be awarded 4 points. The motion trajectories of the 2nd user of Fig. 8 are constant for the 1st to 3rd times (811 to 813), but the motion trajectory of the 4th time (814) deviates significantly, making it difficult to view the initial regularity as high. In this case, the initial regularity can be awarded 3 points. However, this is only an example of assigning a numerical value by judging whether the motion trajectories match in order to judge the initial regularity, and various methods can be used to judge the regularity based on the distance between the motion trajectories, the length in the time series, etc.

The objectification index calculation unit (422) can determine that the first user has high regularity in the number of repetitions of 12, the second user has low regularity in the number of repetitions of 4 to 7, i.e. in the middle, and the third user has low regularity in the number of repetitions of 10 and 12, i.e. in the latter half, and thus can assign scores to each user.

The objectification index calculation unit (422) can also determine the standard deviation of the start of the ascent, the standard deviation of the start of the descent, the standard deviation of the height, the standard deviation of the ascent section speed, the standard deviation of the descent section speed, etc. for each movement trajectory of each of the 12 repetitions for each user and assign a score according to the preset criteria.

In addition, the objectification index calculation unit (422) can calculate the objectification index by further referring to the execution time for performing all the repetitions that constitute one set.

Fig. 11 shows an example of detecting motion trajectories for repetitions of a first user and a second user with the same PMW _estimate value for a chest press exercise machine, as a preferred embodiment of the present invention. In Fig. 11, the x-axis represents time, and the y-axis represents displacement.

The first user (1120) and the second user (1130) can initially be provided with the same exercise program based on the same PMW _estimation . The exercise program for the chest press exercise machine can include an initial target weight, number of repetitions, movement speed guide, breathing method guide, etc. of the exercise machine suitable for the user to perform the exercise with the optimal exercise trajectory (1110).

Referring to Figure 11, it can be confirmed that the first user (1120) has a higher displacement than the optimal motion trajectory (1110), but the start time of ascent, the start time of descent, the average speed of the ascent section, and the average speed of the descent section are similar. In addition, it can be confirmed that the deviation (1120a) between the 11 motion trajectories is small.

The second user (1130) can confirm that the displacement is high and that the start of descent and the average speed during the descent section are too fast. In addition, the deviation (1120a) between the 11 movement trajectories is large.

The PMW guide unit can increase the PMW _individual value of the first user (1120) and decrease the PMW _individual value of the second user (1130).

Figure 12 illustrates a flow chart of an AI exercise guide method as a preferred embodiment of the present invention.

The PMW estimation unit estimates the _PMW of the exercise equipment that the user wishes to exercise on based on the estimated muscle strength value calculated based on user data (S1210). The exercise target setting unit automatically sets the initial target weight of the exercise equipment based on the PMW _estimation (S1220).

The PMW guide section provides a PMW _individual for the exercise equipment by supplementing the PMW _estimation with an objectification index for each user, including exercise records based on the initial target weight for a certain period of time (S1230). The AI exercise goal setting section automatically updates the target weight of the exercise equipment based on the PMW _individual (S1240).

The methods according to the embodiments of the present invention may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the medium may be those specifically designed and configured for the present invention or may be those known to and usable by those skilled in the art of computer software.

Although the present invention has been described above by means of limited embodiments and drawings, the present invention is not limited to the above embodiments, and those skilled in the art to which the present invention pertains can make various modifications and variations based on this description.

Claims (17)

A PMW _estimation unit that estimates the PMW of an exercise machine that a user wishes to exercise on based on an estimated muscle strength value calculated based on user data;
A PMW guide section that provides a PMW _individual for the exercise equipment by supplementing the user's individual objectification index to the above PMW _estimation ; and
It includes an exercise target setting unit that automatically sets the initial target weight of the exercise equipment that the user wants to use based on the above PMW _estimation ;
An AI exercise guide device characterized in that PMW (Personal Maximum Weight) represents the muscle strength that an individual can exert against the resistance of a weight with maximum effort, and the user objectification index includes at least some of the weight, repetitions (Reps), number of sets, exercise trajectory, movement speed, and regularity of repetitions (Reps) per set of the exercise equipment identified when the user uses the exercise equipment for a preset period of time. delete In paragraph 1,
An AI exercise guide device further comprising an AI exercise goal setting unit that automatically updates the target weight of the exercise equipment the user wishes to use based on the PMW _individual . In the first paragraph, the PMW guide part
An AI exercise guide device characterized by including a PMW update unit that updates _{the PMW individual to} a value greater than the PMW _estimate when the objectification index is greater than or equal to the first reference value, and to a value less than the PMW _estimate when the objectification index is less than or equal to the _second reference value. In the fourth paragraph, the PMW update unit
An AI exercise guide device characterized in that the above-mentioned updated PMW _individual is newly updated based on the above-mentioned objectification index at each preset period. In the first paragraph, the PMW guide part
An AI exercise guide device characterized by including a display unit that automatically displays the target weight of the exercise equipment updated based on the PMW _individual . In the first paragraph, the PMW guide part
When the above movement trajectory is used as the above objectification index,
An AI exercise guide device characterized in that it determines the completeness of the exercise trajectory by using the start time of ascent, start time of descent, average speed of the ascent section, average speed of the descent section, and height identified from the exercise trajectory, and converts the degree of completeness of the exercise trajectory into a number and uses it as the objectification index. In the first paragraph, the PMW guide part
An AI exercise guide device characterized in that, when the above number of repetitions (Reps) is used as the above objectification index, the completeness of the number of repetitions (Reps) is judged based on the regularity between the movement trajectories of each of the total number of repetitions constituting one set and the execution time for performing all of the total number of repetitions constituting one set, and the degree of completeness of the number of repetitions (Reps) is converted into a number and used as the above objectification index. The PMW estimation unit is a step for _estimating the PMW of the exercise equipment that the user wishes to exercise on based on the estimated muscle strength value calculated based on user data;
The PMW guide section provides a PMW _individual for the exercise equipment by supplementing the PMW _estimation with a user-specific objectification index; and
The exercise target setting unit includes a step of automatically setting the initial target weight of the exercise equipment based on the PMW _estimation ;
An AI exercise guide method, characterized in that the user objectification index includes at least some of the regularities of the weight, number of repetitions (Reps), number of sets, exercise trajectory, movement speed, and number of repetitions (Reps) per set of the exercise equipment identified when the user uses the exercise equipment for a preset period of time. delete In Article 9,
An AI exercise guide method, characterized in that it further includes a step of automatically updating the target weight of the exercise equipment based on the PMW _individual . In the 9th paragraph, the step of providing the PMW _individual
An AI exercise guide method, characterized in that it includes a step of updating the PMW _individual to a value greater than the PMW _estimation when the objectification index in the PMW update unit is greater than or equal to the first _reference value, and updating the _{PMW individual to} a value less than the PMW estimation when the objectification index is less than or equal to the second reference value. In the 12th paragraph, the step of providing the PMW _individual
An AI exercise guide method characterized in that the updated PMW _individual is renewed at each preset period based on the above objectification index. In the 9th paragraph, the step of providing the PMW _individual
An AI exercise guide method, characterized in that it further includes a step of displaying a PMW _individual through a display unit or displaying a change in the maximum weight that can be lifted when using the exercise equipment. In Article 9,
When the above movement trajectory is used as the above objectification index,
An AI exercise guide method characterized in that the completeness of the exercise trajectory is determined by using the start time of ascent, start time of descent, average speed of the ascent section, average speed of the descent section, and height identified from the exercise trajectory, and the degree of completeness of the exercise trajectory is converted into a number and used as the objectification index. In Article 9,
An AI exercise guide method characterized in that, when the above number of repetitions (Reps) is used as the above objectification index, the completeness of the above number of repetitions (Reps) is judged based on the regularity between the movement trajectories of each of the total number of repetitions constituting one set, and the degree of completeness of the above number of repetitions (Reps) is converted into a number and used as the above objectification index. As a computer-readable recording medium,
The above computer-readable recording medium stores instructions that cause a computing device to perform the following steps, the steps being:
The PMW estimation unit is a step for _estimating the PMW of the exercise equipment that the user wishes to exercise on based on the estimated muscle strength value calculated based on user data;
The PMW guide section provides a PMW _individual for the exercise equipment by supplementing the PMW _estimation with a user-specific objectification index; and
The exercise target setting unit includes a step of automatically setting the initial target weight of the exercise equipment based on the PMW _estimation ;
A computer-readable recording medium characterized in that the user objectification index includes at least some of the regularities of the weight, number of repetitions (Reps), number of sets, movement trajectory, movement speed, and number of repetitions (Reps) per set of the exercise equipment identified when the user uses the exercise equipment for a preset period of time.

Images