Artificial intelligence training guidance device and method

Abstract

As a preferred embodiment of the present application, an artificial intelligence training guide device includes a storage unit that stores at least one muscle activated when a training machine is used, a contribution degree of each of the at least one muscle, and a training trajectory guide generated when the training machine is used according to a use standard, a sensing unit that detects a training trajectory corresponding to a movement of a user moving the training machine, an artificial intelligence processing unit that judges whether the training trajectory detected by the sensing unit and the training trajectory guide coincide when the training machine is moved in at least one direction, and a training guide unit that guides adjustment of a training load or a training posture of the training machine when a deviation between the detected training trajectory and the training trajectory guide is greater than a preset value.

Description

Technical Field

[0001] The present invention aims to provide users with information about muscle contraction and relaxation during training. Background Technology

[0002] Weight training machines are available in various forms to increase muscle strength in specific body parts or for specific purposes. They are primarily used to train the upper and lower body using the hands or feet. Users can perform training by moving the selected weight through the machine's motion components.

[0003] However, users may find it difficult to determine whether they are using the training machine appropriately based on their own physical characteristics, training performance capabilities, or the purpose of the training machine. Summary of the Invention

[0004] Technical issues

[0005] In a preferred embodiment of the present invention, the aim is to improve training effectiveness by providing real-time training guidance, which includes information on muscle contraction and relaxation when the user uses the training machine.

[0006] In one embodiment of the present invention, the aim is to improve training effectiveness by providing real-time training guidance, which includes breathing information of the user while training with the training machine.

[0007] Technical solution

[0008] As a preferred embodiment of the present invention, the artificial intelligence training guidance device includes: a storage unit that stores at least one muscle activated when using a training machine, the contribution of each of the at least one muscle, and training trajectory guidance generated when using the training machine according to usage standards; a sensing unit that detects the training trajectory corresponding to the user's movement of the training machine; an artificial intelligence processing unit that, when the training machine is moved in at least one direction, determines whether the training trajectory detected by the sensing unit and the training trajectory guidance are consistent; and a training guidance unit that, when the deviation between the detected training trajectory and the training trajectory guidance is greater than a preset value, guides the adjustment of the training load or training posture of the training machine.

[0009] Beneficial effects

[0010] In a preferred embodiment of the present invention, the artificial intelligence training guidance method can improve training effectiveness by providing training guidance in real time, the training guidance including information on muscle contraction and relaxation when the user uses the training machine for training.

[0011] In one embodiment of the present invention, the artificial intelligence training guidance method can improve the training effect by providing training guidance in real time, wherein the training guidance includes the breathing information of the user when training with the training machine.

[0012] In one embodiment of the present invention, when the user's training posture is incorrect or the weight of the training machine used by the user is not suitable for the user, the artificial intelligence training guidance method can provide training guidance based on the training trajectory information obtained when the user uses the training machine, thereby improving the training effect. Attached Figure Description

[0013] Figure 1 As a preferred embodiment of the present invention, an intelligent gym system utilizing an artificial intelligence training guidance device is shown.

[0014] Figure 2 As a preferred embodiment of the present invention, an example of a training machine equipped in a smart gym that implements an artificial intelligence training guidance method is shown.

[0015] Figure 3 As a preferred embodiment of the present invention, an internal configuration diagram of an intelligent gym system is shown.

[0016] Figure 4 As a preferred embodiment of the present invention, an example of classification training trajectory big data is shown.

[0017] Figure 5 As a preferred embodiment of the present invention, an example is shown in which at least one muscle activated during training and breathing instructions are displayed in the display unit.

[0018] Figure 6 As a preferred embodiment of the present invention, an example of a training trajectory detected from a training machine is shown.

[0019] Figure 7 As another preferred embodiment of the present invention, an example is shown in which at least one muscle activated during training and the cumulative training volume are displayed in real time in the display unit.

[0020] Best mode

[0021] As a preferred embodiment of the present invention, the artificial intelligence training guidance device includes: a storage unit that stores at least one muscle activated when using a training machine, the contribution of each of the at least one muscle, and training trajectory guidance generated when using the training machine according to usage standards; a sensing unit that detects the training trajectory corresponding to the user's movement of the training machine; an artificial intelligence processing unit that, when the training machine is moved in at least one direction, determines whether the training trajectory detected by the sensing unit and the training trajectory guidance are consistent; and a training guidance unit that, when the deviation between the detected training trajectory and the training trajectory guidance is greater than a preset value, guides the adjustment of the training load or training posture of the training machine.

[0022] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized by further including a display that displays the load applied to at least one muscle activated when the user uses the training machine based on contribution.

[0023] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized in that the training guidance unit further includes a display that displays in real time information about the contraction or relaxation state of at least one muscle activated when using the training machine.

[0024] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized in that, based on the training trajectory detected by the sensing unit and the pre-stored training trajectory guidance, it displays contraction guidance or relaxation guidance in real time for the main muscles activated when the user uses the training machine.

[0025] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized in that the training guidance unit further includes a display, which displays an indicator showing exhalation in the direction of contraction of the main muscle in at least one muscle activated when using the training machine, and inhalation in the direction of relaxation of the main muscle.

[0026] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized in that the sensing unit detects the angle of the joints when the user moves the training machine.

[0027] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized in that the training guidance unit includes a display that displays information in real time about the contraction or relaxation state of at least one muscle activated when using the training machine, based on the detected joint angle.

[0028] As a preferred embodiment of the present invention, the artificial intelligence training guidance device is characterized in that when the shape of the training trajectory corresponding to the joint angle within the predetermined interval detected by the sensing unit is different from the shape of the training trajectory guided by the pre-stored training trajectory, the training guidance unit guides the adjustment of the training posture.

[0029] As a preferred embodiment of the present invention, the artificial intelligence training guidance method is characterized by comprising: a sensing unit detecting a training trajectory corresponding to the movement of a user moving a training machine; an artificial intelligence processing unit determining whether the training trajectory detected by the sensing unit when the training machine is moved in at least one direction is consistent with the training trajectory guidance pre-stored in the storage unit generated when the training machine is used according to the usage standard; and when the deviation between the detected training trajectory and the training trajectory guidance is greater than a preset value, the training guidance unit guiding the adjustment of the training load or training posture of the training machine.

[0030] As a preferred embodiment of the present invention, the artificial intelligence training guidance method is characterized by including: displaying on a display the load applied to at least one muscle activated when the user uses the training machine based on the contribution.

[0031] As a preferred embodiment of the present invention, the artificial intelligence training guidance method is characterized by including: displaying in real time on a display information about the contraction or relaxation state of at least one muscle activated when using a training machine.

[0032] As a preferred embodiment of the present invention, the artificial intelligence training guidance method is characterized by including: exhaling in the direction of contraction of the main muscle in at least one muscle activated when using a training machine, as indicated by an indicator on a display, and inhaling in the direction of relaxation of the main muscle.

[0033] As a preferred embodiment of the present invention, the artificial intelligence training guidance method is characterized by including: a sensing unit further detecting the angle of the joint when the user moves the training machine, and a display showing information in real time about the contraction or relaxation state of at least one muscle activated when using the training machine based on the detected joint angle. Detailed Implementation

[0034] Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings, so that those skilled in the art can readily implement the present invention.

[0035] Figure 1 As a preferred embodiment of the present invention, an intelligent gym system utilizing an artificial intelligence training guidance device is shown.

[0036] The intelligent gym system (100) includes an intelligent gym server (110), at least one training machine (100a, 100b, 100c, ..., 100n), at least one user terminal (120), and an administrator terminal (130).

[0037] exist Figure 1 In this system, the smart gym server (110) can communicate with the first smart gym (112), the second smart gym (114), and the nth smart gym (116) located in different physical locations, and can transmit and receive data with at least one training machine (100a, 100b) arranged in the first smart gym (112), at least one training machine (100c) arranged in the second smart gym (114), and at least one training machine (100n) arranged in the nth smart gym (116).

[0038] In a preferred embodiment of the present invention, a smart gym refers to a physical space in which a user's training records using a training machine are provided to a smart gym server (110), and the smart gym server (110) provides a training prescription suitable for the user by learning and analyzing the user's training records. A smart gym can be implemented in a fitness center, gym, or space equipped with training machines, etc.

[0039] Users (User A, User B, User C, ..., User N) can enter the smart gym after identity verification. For example, users can verify their membership by tagging themselves with NFC (Near Field Communication) or RFID (Radio Frequency Identification) tags on drone terminals such as self-service kiosks at the entrance and exit of the smart gym, or by verifying their membership with biometric information such as facial recognition on drone terminals.

[0040] User information that has been verified as a member can be transmitted via network from the smart gym server (200) to at least one of the training machines (100A, 100B, 100C, ..., 100N). For example, the smart gym server (200) can transmit information about the user to the training machine where the user has tagged their terminal (120). In a preferred embodiment of the invention, the information about the user is also utilized in the term user data, which includes at least some or all of the user's gender, age, weight, height, BMI, and body fat percentage.

[0041] The smart gym server 110 can provide training guidance, such as training methods, intensity, breathing techniques, and postures, to a first user (user A) and a second user (user B), each utilizing at least one training machine (100a, 100b) arranged in the smart gym (112). Furthermore, the smart gym server (110) can provide target weights, recommended usage rates, and other values ​​for each training machine (100a, 100b). Additionally, the smart gym server (110) can receive training records from the first user (user A) and the second user (user B) using each training machine (100a, 100b). Furthermore, it can receive health information such as heart rate, blood pressure, and pulse, or log information from the user terminal (120).

[0042] The smart gym server (110) can be implemented as a cloud server. The smart gym server (110) can integrate and manage information received from each training machine in a smart gym training center located in different locations. For example, the smart gym server (110) can integrate and manage the details of a first user's use of a training machine in a first-location smart gym (112) and the details of their use of a training machine in a second-location smart gym (114).

[0043] In a preferred embodiment of the present invention, at least one training machine (100a, 100b, 100c, ..., 100n) can be a stretching training machine, a weight training machine, or an aerobic training machine. At least one training machine (100a, 100b, 100c, ..., 100n) provides training guidance suitable for the user through a display unit attached to the training machine or a display unit capable of wired or wireless communication with the training machine. For example, taking a stretching machine as an example, training guidance about the stretching machine that the user will use is provided through a smart mirror capable of wired or wireless communication with the stretching machine. However, this is not a limitation; training guidance can be provided through various output methods such as speakers and vibration.

[0044] At least one training machine (100a, 100b, 100c, ..., 100n) can communicate with the smart gym server (110), user terminal (120), and administrator terminal (130) via wired or wireless communication.

[0045] In a preferred embodiment of the present invention, the user terminal (120) can be implemented in the form of a smartphone, smartwatch, handheld device, wearable device, etc. Furthermore, the user terminal (120) can install applications for using the smart gym system. The user terminal (120) can receive training sequence information from the smart gym server (110). The training sequence refers to a training plan designed after considering the user's physical strength and training ability. The training sequence includes information such as the catalog of training machines suitable for the user, the target weight for each training machine, and the number of uses.

[0046] When using at least one training machine (100a, 100b, 100c, ..., 100n) within the smart gym system (100), the user communicates using a terminal (120) via tags such as NFC or RFID, or authenticates their identity using their physical characteristics. After the user's identity is verified, the smart gym server (110) can transmit the user data to the training machine tagged by the user.

[0047] Figure 3As a preferred embodiment of the present invention, an internal configuration diagram of an intelligent gym system with implemented artificial intelligence training guidance is shown. The intelligent gym system includes an artificial intelligence training guidance device (300) and an intelligent gym server (380).

[0048] The AI ​​training guidance device (300) can communicate with the smart gym server (380), the user terminal (390), and the external server (388). The AI ​​training guidance method can be implemented in the training machine in the smart gym or in the smart gym server (380).

[0049] In a preferred embodiment of the present invention, the artificial intelligence training guidance device (300) includes a processor (310), a sensing unit (320), a communication unit (340), a training guidance unit (360), and a display (370). Furthermore, it may further include a storage unit (not shown), a camera unit (330), and an image processing unit (350). If necessary, the processor (310) may further include an artificial intelligence processing unit (312). The artificial intelligence processing unit (312) can detect training trajectories based on data sensed by the sensing unit (320) and analyze the differences between the detected training trajectory and the training trajectory guidance. In a preferred embodiment of the present invention, the function of the artificial intelligence processing unit (312) can also be implemented in the training guidance processing unit (386) of the smart gym server (380). The storage unit can receive and store the required data through communication with the smart gym server (380), a user terminal (390), or an external server (388). In addition, the artificial intelligence training guidance device (300) can store in the storage unit or receive, through communication with the smart gym server (380), at least one muscle activated when using the training machine, the contribution of each of the at least one muscle, and training trajectory guidance generated when using the training machine in the correct posture.

[0050] Figure 2 A shoulder pressure machine (200) is shown as an example of a training machine equipped with an artificial intelligence training guidance device.

[0051] The sensing unit (220) can be mounted on the frame structure (213) of the training machine body (210). The frame structure (213) includes a base frame (213a), a guide rail (213b), and a connecting line (213c). The sensing unit (220) irradiates a laser beam onto the pin structure (215) and receives the reflected laser beam, thereby measuring the distance (D) from the sensing unit (220) to the pin structure (215) in real time or in units of a preset time t (S220). Thus, the sensing unit (220) can detect in real time at least one of the position, movement rate, and movement direction of the weight component (211) selected by the pin structure (215). Furthermore, when the weight plate moves due to the user pushing the handle (212) of the training machine (200), the sensing unit (220) can detect the distance (D) up to the pin structure (215) inserted into the weight plate (S220) and detect the training trajectory based on this. The sensing unit (220) can also be attached to the training machine to detect the angle of the joint used by the user when using the training machine. In this case, markings such as reference points can be attached to the user's joints. The sensing unit (220) can detect the angle of the joint in real time by sensing the markings attached to the joint. However, it should be noted that this is only an example and various modifications can be made. The display (230) can display the contraction or relaxation state of at least one muscle activated when the user uses the shoulder press machine (200), and can also display the load applied to at least one muscle. The display (230) can also display contraction or relaxation guidance in real time for the main muscles activated when the user uses the shoulder press machine (200). In addition, breathing guidance can also be displayed.

[0052] In a preferred embodiment of the invention, the contraction or relaxation state of at least one muscle activated when the user uses the shoulder press machine (200) refers to the contraction or relaxation state of the user's muscles detected by the sensing unit (220). In a preferred embodiment of the invention, contraction guidance or relaxation guidance refers to the contracted muscles and contraction time, and the relaxed muscles and relaxation time, when the user uses the shoulder press machine (200) in the correct posture according to the usage standards.

[0053] The artificial intelligence processing unit (312) determines whether the training trajectory detected by the sensing unit (320) is consistent with the training trajectory guidance received by the smart gym server. Furthermore, the artificial intelligence processing unit (312) determines whether the training trajectory corresponding to the joint angle is consistent with the training trajectory guidance. (See training trajectory for details.) Figure 4 The description in the text.

[0054] For example, determine whether the training trajectory and the training trajectory guidance are consistent when the user uses the seated leg curl machine with a knee angle of 0-4°. See Table 5; the 0-4° knee angle range is where the gastrocnemius muscle is activated. Additionally, determine whether the training trajectory and the training trajectory guidance are consistent when the user uses the seated leg curl machine with a knee angle of 5-90°. See Table 5; the 5-90° knee angle range is where the biceps femoris, semitendinosus, and semimembranosus muscles are activated.

[0055] When the shape of the training trajectory corresponding to the joint angle in the predetermined range detected by the sensing unit differs from the shape of the training trajectory guidance, the artificial intelligence processing unit (312) determines that the training posture needs to be adjusted. In this case, the artificial intelligence processing unit (312) can also refer to the user's training posture detected by the image processing unit (350).

[0056] For example, when inconsistencies occur in the 0-4° range of the knee joint, the AI ​​processing unit (312) determines that the user has a problem with the gastrocnemius muscle or a problem with the training posture related to the gastrocnemius muscle. When inconsistencies occur in the 5-90° range of the knee joint, the AI ​​processing unit (312) determines that the biceps femoris, semitendinosus, and semimembranosus muscles have problems or a problem with the training posture related to the biceps femoris, semitendinosus, and semimembranosus muscles.

[0057] When the deviation between the movement displacement of the training trajectory corresponding to the joint angle within the predetermined range detected by the sensing unit and the height or width movement displacement of the training trajectory guidance received from the smart gym server exceeds a preset value, the artificial intelligence processing unit (312) determines that the training load needs to be adjusted. For example, refer to... Figure 6 When the height H (612) of the user training trajectory detected by the sensing unit (320) is lower than the value of the pre-stored training trajectory height h by a preset ratio, it determines that the training load needs to be reduced.

[0058] The communication unit (340) can receive user input via a display (230) or transmit and receive user data with the user database (382) of the smart gym server (380). The communication unit (340) can also communicate with an external server (388).

[0059] The training guidance unit (360) can provide users with user data received from the smart gym server (380), the target weight of the training machine, training trajectory guidance, movement speed guidance of the training machine, breathing guidance, and information on the contraction or relaxation of the main muscles activated when using the training machine.

[0060] The training guidance unit (360) can provide training guidance based on the judgment results of the artificial intelligence processing unit (312). When the artificial intelligence processing unit (312) determines that the deviation between the training trajectory detected by the sensing unit (320) and the training trajectory guidance is greater than a preset value, the training guidance unit (360) can guide the training machine to reduce or increase the training load. In addition, when the artificial intelligence processing unit (312) determines that the shape of the training trajectory detected by the sensing unit (320) is different from the shape of the training trajectory guidance, the training guidance unit (360) can guide the need to change the training posture.

[0061] The smart gym server (380) includes a user database (382), a machine learning processing unit (384), and a training guidance processing unit (386). The user database (382) stores and manages user data. User data includes the user's gender, age, weight, height, BMI, body fat percentage, etc. The machine learning processing unit (384) analyzes, accumulates, learns, and processes big data, including user data obtained from the user database and training records from the training machines used by users in the smart gym.

[0062] In a preferred embodiment of the present invention, the intelligent gym server (380) provides an artificial intelligence training guidance method by receiving data from sensing units installed on the training machine. The intelligent gym server (380) stores at least one muscle activated when using the training machine, the contribution of each of the at least one muscle, and training trajectory guidance generated when using the training machine according to usage standards in a storage unit (not shown). Furthermore, after determining whether the training trajectory obtained from the sensing data received from the training guidance processing unit (386) matches the training trajectory guidance, the user can be guided to adjust the training load or training posture of the training machine being used.

[0063] As another preferred embodiment of the present invention, the smart gym server (380) is equipped with PMW storage. 预测 The percentile information mapping table, the PMW 预测 Percentile information is generated based on the PMW (Personal Maximum Weight) data obtained from the population for each training machine, as shown in Table 3. Table 1 shows the PMW for the seated leg extension trainer. 预测 Percentile information.

[0064] [Table 1]

[0065] PMW90 103.3 … … PMW50 67.3 PMW40 66.5 … … PMW10 24.6

[0066] In a preferred embodiment of the present invention, PMW (Personal Maximum Weight) refers to the muscle strength a person can exert by resisting the resistance of their own weight with maximum effort. Examples of PMW include 1RM, 4RM, etc. 预测 This indicates that the user's PMW (Progressive Muscle Strength) value is predicted based on the predicted muscle strength value calculated using mathematical formula 1. The intelligent gym server (380) can determine the PMW for each training machine. 预测 The intelligent gym server (380) is based on predicted muscle strength and PMW. 预测 Percentile information determines the PMW of the training machine that the user will use. 预测 Furthermore, based on PMW 预测 Automatically sets the initial target weight for the training machine the user will use.

[0067] For example, when a 32-year-old male has a predicted muscle strength of 55.9 and a percentile of 40, his corresponding PMW (predicted muscle strength) will be... 预测 The percentile value of 40 (i.e., 66.5 kg) predicts the PMW of a 32-year-old male using the seated leg extension machine. As a preferred embodiment of the invention, the smart gym server (380) pre-stores the PMW for each machine. 预测 Percentile information is shown in Table 1.

[0068] The training instruction processing unit (386) is based on PMW. 预测 Set the initial target weight for each training machine. In this case, the training guidance processing unit (386) can set the initial target weight according to the training intensity or training purpose.

[0069] The training instruction processing unit (386) can set the weight to PMW when the training intensity is low. 预测 a%, when the training intensity is moderate, the weight is set to PMW. 预测 b%, when the training intensity is high, the weight is set to PMW. 预测 c%. For example, a can be set to 20 to 40, b to 40 to 60, c to 60 to 80, etc. However, it should be noted that this is just an example and various modifications can be made.

[0070] The training guidance processing unit (386) can provide the training guidance unit (360) of the training machine (300) with the initial target weight of the training machine that the user will use, and the training guidance unit (360) can display the initial target weight of the training machine that the user will use on the display (370). The display unit (370) includes a display.

[0071] In another embodiment of the invention, the smart gym server (380) can predict the maximum muscle strength value (PMW) that reflects the user's individual objectivity index.个体 Furthermore, the smart gym server (380) can base its performance on predicted PMW. 个体 Update the target weight on the training machine. More specifically, the smart gym server (380) is based on PMW. 预测 The initial target weight of the training machine is set, and after acquiring the individual objectivity index of each user within a preset time, the PMW is predicted by reflecting the individual objectivity index of each user. 个体 Then, based on PMW 个体 Update the target weight on the training machine. The training guidance processing unit (386) can display the PMW-based weight on the training machine that the user will be using. 个体 Updated target weight.

[0072] Examples of objectification indices can be found in training records, which include data such as the weight of the training machine, number of repetitions (Reps), number of sets, training trajectory, movement speed, and regularity of repetitions per set unit (Reps) as observed when using the training machine.

[0073] The machine learning processing unit (384) learns and processes an objectification index, which includes training records of the user using a training machine in the smart gym. The machine learning processing unit (384) can, based on the objectification index of the training machine used by the user in the smart gym over a certain period, convert the PMW (Physical Motion) data into a PMW (Physical Motion) value. 预测 Updated to PMW 个体 The machine learning processing unit (384) can adjust the PMW when the objectification index is greater than or equal to the first baseline value. 个体 Updated to be better than PMW 预测 A larger value will result in PMW when the objectification index is less than or equal to the second benchmark value. 个体 Updated to be better than PMW 预测 Smaller values.

[0074] Therefore, the machine learning processing unit (384) can process the PMW of the first and second users even if they have the same gender, age, weight, height, BMI, and body fat percentage. 预测 When predicted to be the same, further objectification indices reflecting individual user objective records, such as those of user 1 and user 2, can be used to learn and predict the appropriate PMW for each training machine used by user 1 and user 2. 个体 .

[0075] In another preferred embodiment of the present invention, the machine learning processing unit (384) learns and processes the training trajectory detected from the training machine. (See reference...) Figure 6The machine learning processing unit (384) can determine the integrity of the training trajectory by using at least a portion of the following parameters identified through the training trajectory detected by the user during training: the starting point of ascent (611), the starting point of descent (613), the ascent interval rate V1 (S610), the descent interval rate V2 (S620), the average rate of ascent interval, the average rate of descent interval, and the height H (612). The integrity level of the training trajectory is then converted into an objectification index after numerical conversion. For example, when the starting point of ascent is from 0 to t... a The time frame is considered moderate if it exceeds t. a The time is judged as delayed. In addition, the completeness can be assigned a score of upper, middle, lower or 1 to 10 points based on the preset standard for the moderate starting point item. Similarly, when the rising interval rate V1 is between Va and Vb according to the preset standard, it is judged as moderate, when it exceeds Vb, it is judged as too fast, and when it is less than Va, it is judged as too slow, and a score of upper, middle, lower or 1 to 10 points can be assigned according to the judgment result of moderate, too fast, and too slow. The machine learning processing unit (384) generates an objectification index from the user's training records by means of the method described above.

[0076] As a preferred embodiment of the present invention, when the number of repetitions (Reps) is used as an objectification index, the machine learning processing unit (384) judges the integrity of the number of repetitions based on the regularity between the training trajectories of each of the total number of repetitions (Reps) constituting a group and the time for executing all the repetitions constituting the group, and uses the integrity level of the number of repetitions as an objectification index after numerical conversion.

[0077] In another preferred embodiment of the present invention, the machine learning processing unit (384) can provide optimized training trajectory guidance for each user by classifying large amounts of training trajectory data. (See reference...) Figure 4 Describe it.

[0078] Figure 4 An example is shown where training trajectories for a specific training machine, obtained from the population by the machine learning processing unit (384), are classified into seven patterns (410 to 470). The x-axis represents time, and the y-axis represents the standardized movement displacement. Initially, the population can be based on a preset number of n people, but can be used by continuously accumulating data from users of the smart gym.

[0079] The machine learning processing unit (384) can classify the overall training trajectory patterns and determine the proportion of each pattern in the overall population. The machine learning processing unit (384) selects a training trajectory guide from the seven analyzed training trajectory patterns (410 to 470). In this case, the machine learning processing unit selects the second training trajectory pattern (420) and the sixth training trajectory pattern (460), which have the smallest deviation from the preset baseline trajectory (412) with the best training effect, as training trajectory guides. The machine learning processing unit (384) considers the differences in training trajectories caused by different heights and physical conditions of each user, and selects at least one as a training trajectory guide (420, 460). The second training trajectory pattern (420) accounts for 21.7% of the overall total, and the sixth training trajectory pattern (460) accounts for 23.1% of the overall total.

[0080] The training guidance processing unit (386) selects the training trajectory guidance whose detected user training trajectory belongs to the pattern closest to at least one training trajectory guidance (420, 460) obtained from the machine learning processing unit (384). For example, when the displacement of the user's training trajectory is less than 0.5, the second training trajectory pattern (420) is selected and provided to the user as the training trajectory guidance. Alternatively, when the displacement of the user's training trajectory is approximately 0.6, the sixth training trajectory pattern (460) is selected and provided to the user as the training trajectory guidance.

[0081] Furthermore, the training guidance processing unit (386) can determine changes in the user's training trajectory based on the training load, number of training sessions, and time. For example, when the first user uses the chest press machine at 60 kg, the training trajectory belongs to the second training trajectory pattern (420), but when the first user uses the chest press machine at 70 kg, the training trajectory belongs to the first training trajectory pattern (410), the training guidance processing unit (386) can determine that the suitable load for the first user is 60 kg. In this case, the training guidance processing unit (386) can instruct the training guidance unit (360) to adjust the size of the training load. The configuration of the training guidance processing unit (386) can also be implemented in the artificial intelligence processing unit (312).

[0082] As another preferred embodiment of the present invention, the intelligent gym server (380) stores information on the training machines corresponding to each body part, the joints used by each training machine, and the muscles in the storage unit, as shown in the example in Table 2. Table 2 shows an example of the joint and muscle data of each training machine for the "lower body" in the corresponding body part.

[0083] [Table 2]

[0084]

[0085] The smart gym server (380) also stores information about at least one muscle that is activated when using the training machine and the contribution of each of the at least one muscle, as shown in Tables 3 and 4.

[0086] [Table 3]

[0087]

[0088] [Table 4]

[0089]

[0090] The intelligent gym server (380) also stores information about at least one muscle used with each joint range of motion for each training machine, as shown in Table 5. Furthermore, it stores training trajectories generated when using the training machine according to standard usage guidelines, and provides these training trajectories as training trajectory guidance to the user, based on the range of motion of each joint. Training trajectory guidance refers to the training trajectory generated when using the training machine accurately with the correct posture.

[0091] [Table 5]

[0092]

[0093] Figure 5 As a preferred embodiment of the present invention, an example is shown in which at least one muscle activated during training and breathing instructions are displayed in the display unit.

[0094] Figure 5 This illustration shows an example of a user performing biceps training with dumbbells. The display unit shows, in real time, information about the contraction (510a) or relaxation (520a) state of the biceps brachii (500) activated when using dumbbells, based on the joint angle detected by the sensing unit. When the sensing unit detects the elbow joint angle and the movement of curling the arm, the display unit shows the contraction (510a) of the biceps brachii (500) based on the joint angle and displays the required breathing guidance with an indicator (510b). Furthermore, when the sensing unit detects the elbow joint angle and the movement of returning the arm to its original position after curling the arm, the display unit shows the relaxation (520a) of the biceps brachii (500) based on the joint angle and displays the required breathing guidance with an indicator (520b).

[0095] Breathing guidance can be provided in various ways depending on the training machine or method. For example, exhalation (510b) can be provided as breathing guidance when the load is applied to the user's muscles, and inhalation (520b) can be provided as breathing guidance when the load applied to the muscles is reduced. Whether the load is applied to the user's muscles can be determined based on the training trajectory.

[0096] In another embodiment of the invention, when the training trajectory detected by the user during biceps training with dumbbells is inconsistent with the training trajectory guidance, the artificial intelligence processing unit can determine that the user's elbow joint is injured or has a problem. In this case, the training guidance unit can guide the user on a training method that supports the dumbbell weight without using the elbow joint (530).

[0097] Figure 7 As another preferred embodiment of the present invention, an example is shown in which at least one muscle activated during training and the cumulative training volume are displayed in real time in the display unit.

[0098] This example assumes a user using a seated leg extension machine (700) with an initial target weight of 20 kg, 20 repetitions, and 1 reps. The AI ​​processing unit can calculate the training volume in real time based on the contribution of each of at least one muscle activated during training. The display can show the training volume applied to at least one muscle or the cumulative training volume.

[0099] For example, taking 20 kg and 2 repetitions as an example, the AI ​​processing unit calculates the cumulative training volume of the rectus femoris as 20 kg * 2 * 20% = 8 kg within the range of the user's knee joint angle of 90-81° (740b). In this case, the "rectus femoris (730a)" as the activated muscle is displayed in color or shadow on the display unit (710). The display unit (710) can display the activated muscle in two or three dimensions. The user can intuitively understand the currently activated muscle by viewing the display unit (710). In addition, within the range of the user's knee joint angle of 80-5°, the cumulative training volume of the vastus lateralis, vastus medialis, and vastus intermedius is calculated as 20 kg * 2 * 80%. Furthermore, if the user fails to complete the entire training sequence, the AI ​​processing unit calculates the remaining training volume, which represents the difference between the target training volume of the target muscle and the cumulative training volume of the target muscle. See also Figure 7In this case, the display unit (710) can display the training progress status (740). The training progress status (740) includes at least one of the target training volume (740a), cumulative training volume (740b), and remaining training volume (740c). The display unit (710) displays in real time, numerically, at least one muscle (730a, 730b, 730c, 730d) activated during training and the cumulative training volume (740b). In another preferred embodiment of the invention, the display unit (720) can display at least one activated muscle and the cumulative training volume of each of the at least one muscle on the character. Furthermore, by further displaying the training progress status (740) on the character, it is possible to display in numerical terms the at least one muscle activated during training and the cumulative training volume of each of the at least one muscle on the character.

[0100] The method according to embodiments of the present invention can be implemented in the form of program instructions executable by various computer means, and thus written to a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., individually or in combination. The program instructions recorded on the medium may be specifically designed and configured for the present invention, or may be known and available to those skilled in the art of computer software.

[0101] The present invention has been described above with reference to limited embodiments and accompanying drawings, but the present invention is not limited thereto, and those skilled in the art can make various modifications and variations based on it.

Claims

1. A training guidance device, characterized in that, include: A storage unit that stores at least one muscle activated when using the training machine, the contribution of each of the at least one muscle, and training trajectory guidance generated when the training machine is used accurately in the correct posture. The sensing unit detects the training trajectory corresponding to the user's movement of the training device; The artificial intelligence processing unit is configured as follows: When the training machine is moved in at least one direction, it is determined whether the training trajectory detected by the sensing unit corresponding to the joint angle is consistent with the training trajectory guidance. When the shape of the training trajectory corresponding to the joint angle in the predetermined interval detected by the sensing unit is different from the shape guided by the training trajectory, it is determined that the training posture needs to be adjusted. When the deviation between the movement displacement of the training trajectory corresponding to the joint angle of the predetermined interval detected by the sensing unit and the movement displacement of the height or width guided by the training trajectory is greater than a preset value, it is determined that the size of the training load needs to be adjusted. as well as When the height of the user's training trajectory detected by the sensing unit is lower than the height guided by the training trajectory by a preset ratio, it is determined that the training load needs to be reduced. as well as The training guidance unit is configured to provide training guidance based on the determination results of the artificial intelligence processing unit. When the artificial intelligence processing unit determines that the size of the training load needs to be adjusted, it guides the training machine to reduce or increase the training load. And when the artificial intelligence processing unit determines that the training posture needs to be adjusted, it guides the adjustment of the training posture.

2. The training guidance device according to claim 1, characterized in that, include: The display unit displays the load applied to at least one muscle that is activated when the user uses the training machine, based on the contribution.

3. The training guidance device according to claim 1, characterized in that, include: The display unit displays information in real time about the contraction or relaxation state of at least one muscle that is activated when using the training machine.

4. The training guidance device according to claim 3, characterized in that, include: The display unit, based on the training trajectory detected by the sensing unit and the pre-stored training trajectory guidance, displays contraction or relaxation guidance in real time for the main muscles activated when the user uses the training machine.

5. The training guidance device according to claim 1, characterized in that, include: The display unit shows breathing instructions via indicators based on the contraction or relaxation of the major muscle in at least one muscle activated when using the training machine.

6. The training guidance device according to claim 1, characterized in that, The sensing unit is mounted on the frame structure of the training machine; The frame structure includes a base frame, guide rails, and connecting lines; The sensing unit irradiates a laser beam onto the pin structure, receives the reflected laser beam, and measures the distance from the sensing unit to the pin structure in real time or in units of a preset time t. The sensing unit detects in real time at least one of the position, moving speed, and moving direction of the weight component selected by the pin structure; as well as The sensing unit detects the training trajectory based on the distance.

7. The training guidance device according to claim 6, characterized in that, include: The display unit displays information in real time about the contraction or relaxation state of at least one muscle activated when using the training machine, based on the joint angle detected by the sensing unit.

8. The training guidance device according to claim 1, characterized in that, The training trajectory guidance is generated by analyzing user big data in the machine learning processing unit.

9. A training guidance method, characterized in that, include: The sensing unit detects the training trajectory corresponding to the user's movement of the training device; When the training machine is moved in at least one direction, the artificial intelligence processing unit determines whether the training trajectory corresponding to the joint angle detected by the sensing unit is consistent with the training trajectory guidance pre-stored in the storage unit, wherein the training trajectory guidance is generated when the training machine is used in accordance with the usage standard; When the shape of the training trajectory corresponding to the joint angle in the predetermined interval detected by the sensing unit is different from the shape guided by the training trajectory, the artificial intelligence processing unit determines that the training posture needs to be adjusted. When the deviation between the displacement of the training trajectory corresponding to the joint angle within the predetermined interval, detected by the sensing unit, and the displacement of the height or width guided by the training trajectory, exceeds a preset value, the artificial intelligence processing unit determines that the training load needs to be adjusted; and When the height of the user's training trajectory detected by the sensing unit is lower than the height guided by the training trajectory by a preset ratio, the artificial intelligence processing unit determines that the training load needs to be reduced. Based on the determination result of the artificial intelligence processing unit, when the artificial intelligence processing unit determines that the training load needs to be adjusted, the training guidance unit instructs the training machine to reduce or increase the training load. Based on the determination result of the artificial intelligence processing unit, when the artificial intelligence processing unit determines that the training posture needs to be adjusted, the training guidance unit guides the adjustment of the training posture.

10. The training guidance method according to claim 9, characterized in that, include: Based on the contribution of each of the one or more muscles activated when the user uses the training machine, the load applied to each of the one or more muscles is displayed in the display unit.

11. The training guidance method according to claim 9, characterized in that, include: The display unit displays information in real time about the contraction or relaxation state of at least one muscle that is activated when using the training machine.

12. The training guidance method according to claim 9, characterized in that, include: The direction of contraction of the primary muscle in at least one muscle activated when using the training machine is displayed in the display unit by an indicator, and inhalation is performed in the direction of relaxation of the primary muscle.

13. The training guidance method according to claim 9, characterized in that, include: Based on the detected joint angle, the display unit displays in real time information about the contraction or relaxation state of at least one muscle that is activated when using the training machine.

14. A computer-readable recording medium, characterized in that, Its storage enables the computing device to execute the instructions of the training guidance method as described in claim 9.

Images