Training load adjustment method, apparatus, device, medium, and intelligent fitness equipment

Abstract

The application discloses a training load adjustment method and device, equipment, medium and intelligent fitness equipment, and relates to the technical field of fitness. The method comprises the following steps: acquiring training characteristic data of each group of training in a plurality of groups of training of a target training unit; determining a training compliance state of the first N groups of training according to the training characteristic data of the first N groups of training, wherein N is a positive integer; and adjusting a training load of the N+1th group of training according to the training compliance state. The application realizes dynamic regulation and control of the training load of the subsequent training group based on the actual performance of the previous training group, so that the training load can be adaptively adjusted according to the real-time physical ability state of the user in the scene of the plurality of groups of training that are continuously executed once, and the real-time performance, flexibility and accuracy of the training load adjustment are improved.

Description

Technical Field

[0001] This application relates to the field of fitness technology, specifically to a method, device, equipment, medium, and intelligent fitness equipment for adjusting training load. Background Technology

[0002] In strength training using fitness equipment, training load directly affects muscle stimulation, strength gain efficiency, and exercise safety. Too low a load results in insufficient training effectiveness, while too high a load increases the risk of injury. Therefore, precise control of training load is crucial for strength training. In traditional training models, users typically adjust the training load manually based on fixed training plans or coaching experience, making it difficult to dynamically adapt to real-time training conditions. Summary of the Invention

[0003] This application provides a training load adjustment method, device, equipment, medium, and intelligent fitness equipment, which can improve the real-time performance, flexibility, and accuracy of training load adjustment.

[0004] In a first aspect, embodiments of this application provide a training load adjustment method, the method comprising: acquiring training feature data for each training session during multiple training sessions of a target training unit; determining the training achievement status of the first N training sessions based on the training feature data of the first N training sessions, wherein N is a positive integer; and adjusting the training load of the (N+1)th training session based on the training achievement status.

[0005] In some embodiments, the training feature data includes training completion data and training quality data; wherein the training quality data is determined based on at least one of the following: movement speed data, movement rhythm data, movement amplitude data, and left-right balance data; wherein the movement speed data is used to indicate the user's movement speed in a single movement or multiple movements, the movement rhythm data is used to indicate the periodicity of the user's movement during the execution of the movement, the movement amplitude data is used to indicate the amount of spatial position change achieved by the user during the execution of the movement, and the left-right balance data is used to indicate the degree of force balance between the left and right limbs in movements involving both limbs.

[0006] In some embodiments, the process of determining the training quality data includes: selecting any one dimension of data from the movement speed data, the movement rhythm data, the movement amplitude data, and the left-right balance data as the training quality data; or, selecting at least two dimensions of data from the movement speed data, the movement rhythm data, the movement amplitude data, and the left-right balance data, obtaining the weight values ​​corresponding to the at least two dimensions of data respectively, and performing a weighted summation of the at least two dimensions of data according to the weight values ​​corresponding to the at least two dimensions of data respectively to obtain the training quality data.

[0007] In some embodiments, determining the training attainment status of the first N training sessions based on the training feature data of the first N training sessions includes: determining the training attainment status as attainable when the training completion data of each training session in the first N training sessions meets preset completion conditions and the training quality data of each training session in the first N training sessions meets preset quality conditions; and determining the training attainment status as unattainable when the training completion data of any training session in the first N training sessions does not meet preset completion conditions or the training quality data of any training session in the first N training sessions does not meet preset quality conditions.

[0008] In some embodiments, adjusting the training load of the N+1th training group according to the training achievement status includes: increasing the training load of the N+1th training group when the training achievement status is achieved; and decreasing the training load of the N+1th training group when the training achievement status is not achieved.

[0009] In some embodiments, increasing the training load of the N+1th training group includes: adding a first number of training iterations based on the initial target number of training iterations for the N+1th training group; decreasing the training load of the N+1th training group includes: deducting a second number of training iterations based on the initial target number of training iterations for the N+1th training group; wherein the first number and the second number are both positive integers, and the first number and the second number may be the same or different.

[0010] In some embodiments, increasing the training load of the N+1th training group includes: determining the amount of increase in the training load based on the training achievement status, wherein the amount of increase is positively correlated with the degree of achievement indicated by the training achievement status; decreasing the training load of the N+1th training group includes: determining the amount of decrease in the training load based on the training achievement status, wherein the amount of decrease is positively correlated with the degree of non-achievement indicated by the training achievement status.

[0011] In some embodiments, adjusting the training load of the N+1th training group according to the training achievement status includes: adjusting the training load of the N+1th training group according to the training achievement status when the current completion amount of the N+1th training group reaches the reference completion amount.

[0012] In some embodiments, the method further includes: determining the completion base of the N+1th training group based on the completion difference of the first N training groups, wherein the completion difference is used to indicate the degree of dispersion between the actual completion amounts of each training group in the first N training groups; and determining the reference completion amount of the N+1th training group based on a preset progress ratio and the completion base of the N+1th training group.

[0013] In some embodiments, the preset progress ratio is greater than 50% to trigger training load adjustment in the middle and later stages of the N+1th training group.

[0014] In some embodiments, determining the completion base of the (N+1)th training group based on the completion difference of the first N training groups includes: if the completion difference of the first N training groups is less than or equal to a preset difference threshold, using the target completion amount of the (N+1)th training group as the completion base of the (N+1)th training group; if the completion difference of the first N training groups is greater than the preset difference threshold, determining the completion base of the (N+1)th training group based on the actual completion amount of the first N training groups.

[0015] In some embodiments, determining the completion base of the N+1th training group based on the actual completion amount of the first N training groups includes: taking the average, weighted average, maximum, minimum, or median of the actual completion amount of the first N training groups to obtain the completion base of the N+1th training group.

[0016] In some embodiments, the method further includes: performing a load alert operation; wherein the load alert operation is used to alert that the training load of the N+1th training group has changed.

[0017] Secondly, embodiments of this application provide a training load adjustment device, the device comprising: a data acquisition module, configured to acquire training feature data of each training session during multiple training sessions of a target training unit; a target achievement detection module, configured to determine the training achievement status of the first N training sessions based on the training feature data of the first N training sessions, wherein N is a positive integer; and a load adjustment module, configured to adjust the training load of the (N+1)th training session based on the training achievement status.

[0018] Thirdly, embodiments of this application provide an electronic device, including: a memory storing computer programs or instructions thereon; and a processor for executing the computer programs or instructions in the memory to implement the training load adjustment method as described above.

[0019] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions, when executed by a processor, implement the training load adjustment method as described above.

[0020] Fifthly, embodiments of this application provide an intelligent fitness device, comprising: a device body; a sensing unit for collecting motion signals; and, as described above, a training load adjustment device, or as described above, an electronic device.

[0021] Sixthly, embodiments of this application provide a terminal device, including the training load adjustment device as described above, or including the electronic device as described above.

[0022] In summary, the technical solution provided in this application obtains the training feature data of the first N training sessions of the target training unit, determines the training achievement status of the first N training sessions based on this data, and adaptively adjusts the training load of the N+1th training session. Compared with the traditional solution of manually adjusting the training load based on a fixed training plan or coach experience, this application embodiment realizes dynamic adjustment of the training load of subsequent training groups based on the actual performance of the preceding training groups. This allows the training load to be adaptively adjusted according to the user's real-time physical condition in a single continuous multi-set training scenario, improving the real-time performance, flexibility, and accuracy of training load adjustment. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a training load adjustment method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating a method for dividing training achievement states according to an embodiment of this application; Figure 3 This is a flowchart of another training load adjustment method provided in the embodiments of this application; Figure 4 This is a flowchart of another training load adjustment method provided in the embodiments of this application; Figure 5 This is a schematic diagram of a training load adjustment device provided in an embodiment of this application; Figure 6 This is a schematic diagram of another training load adjustment device provided in the embodiments of this application; Figure 7 This is a schematic diagram of a tension-velocity curve provided in an embodiment of this application; Figure 8 This is a schematic diagram of a length-tension curve provided in an embodiment of this application. Detailed Implementation

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified. Furthermore, "A and / or B" includes three cases: only A, only B, and a combination of A and B.

[0027] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" also implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0028] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0029] Please see Figure 1 , Figure 1 This is a flowchart of a training load adjustment method provided in an embodiment of this application. Figure 1 As shown, the training load adjustment method may include the following steps S100 to S300.

[0030] Step S100: During the multiple training sessions of the target training unit, acquire the training feature data for each training session.

[0031] A target training unit (TBU) refers to any training task that can be performed continuously, encompassing various training scenarios. For example, a TBU can be a single exercise, such as a dumbbell squat; or it can be a compound exercise, such as combining a dumbbell squat with a dumbbell press into a single TBU; or it can be a superset, circuit training, or interval training. TBUs are also compatible with various smart fitness equipment, including but not limited to smart dumbbells, smart barbells, smart kettlebells, and multi-strength training machines.

[0032] Multiple sets of training refers to repeatedly executing the same training unit for a preset number of sets. Within a training unit, there is typically a short rest period (e.g., 30 seconds to 3 minutes) between adjacent sets. For example, in a single-movement multiple-set training scenario, a user sequentially performs sets 1, 2, 3, etc., of dumbbell curls, resting between sets before immediately starting the next set, until all sets are completed. This application does not limit the specific number of sets for multiple sets; in practical applications, it can be flexibly set according to needs, such as 3, 5, or 6 sets. In response to a user-initiated training start operation, training parameters for the multiple sets of the target training unit, such as target completion amount and training load, can be loaded.

[0033] Training feature data refers to the set of data collected and recorded by sensors during training that reflects the user's training performance. These sensors can be built into smart fitness equipment, such as an IMU (Inertial Measurement Unit) or a motor resistance sensing module (e.g., a motor with a digital encoder and its associated resistance output mechanism, such as a cable traction system); or they can be other sensing modules independent of the smart fitness equipment, such as a camera used to capture the user's training movements and facial expressions. Taking an IMU as an example, an IMU includes an accelerometer and a gyroscope. The accelerometer measures acceleration information in three spatial directions (which can be mapped to data such as movement speed), and the gyroscope measures rotational angular velocity information (which can be mapped to data such as movement amplitude and trajectory). Through this sensing mechanism, corresponding training feature data can be acquired during each training session of the target training unit.

[0034] Step S200: Determine the training achievement status of the first N training sessions based on the training feature data of the first N training sessions; where N is a positive integer.

[0035] In this embodiment, N is the number of pre-training sets used to determine whether to trigger the load adjustment function. N is a positive integer and can be flexibly set arbitrarily based on the total number of sets in the target training unit and other requirements, such as 2, 3, or 4. It should be understood that the value of N is less than the total number of sets in the target training unit. Furthermore, this embodiment can also set scenario conditions for the load adjustment function. For example, when the total number of sets in the target training unit is less than or equal to K (K is a positive integer, such as K being 2 or 3), the load adjustment function is not enabled; when the total number of sets in the target training unit is greater than K, the load adjustment function can be enabled, thereby triggering the training achievement status judgment of the previous N sets of training when N sets of training are completed. It should be understood that the values ​​of K and N can be the same, such as both being 2; or they can be different, such as K being 2 and N being 3, or K being 3 and N being 2.

[0036] The training achievement status of the first N training sessions refers to the classification result obtained after comprehensively evaluating the training feature data of the first N training sessions, used to indicate whether the user's previous training performance meets the preset standard. For example, a comprehensive score can be calculated based on the training feature data of the first N training sessions, and then the training achievement status can be divided based on the comprehensive score and the preset score range; or, the user performance level can be divided separately for the training feature data of the first N training sessions, and then the training achievement status can be divided based on the user performance level corresponding to different training feature data. The specific type of training achievement status is not limited in the embodiments of this application. In practical applications, it can be flexibly set according to needs, for example, the training achievement status can include achieving or not achieving the standard, or it can include exceeding the standard, achieving the standard or not achieving the standard, or it can be directly in the form of a score, etc.

[0037] Step S300: Adjust the training load of the N+1th training group based on the training achievement status of the first N training groups.

[0038] Based on the training achievement status of the first N training sessions, corresponding load adjustment instructions can be generated to adjust the training load of the (N+1)th training session. Generally, for training achievement statuses of "achieved" or above, the training load of the (N+1)th training session can be increased; for training achievement statuses below "achieved," the training load of the (N+1)th training session can be decreased. This application embodiment does not limit the specific type of training load adjusted. In practical applications, it can be flexibly set according to the action type and requirements of the target training unit. For example, the training load may include, but is not limited to, at least one of the following: training repetitions, training weight, and training volume. This application embodiment does not limit the timing of training load adjustment. In practical applications, the training load can be adjusted at any time during the (N+1)th training session, such as at the start, the beginning of training, the middle of training, or the later stages of training.

[0039] In summary, the technical solution provided in this application obtains the training feature data of the first N training sessions of the target training unit, determines the training achievement status of the first N training sessions based on this data, and adaptively adjusts the training load of the N+1th training session. Compared with the traditional solution of manually adjusting the training load based on a fixed training plan or coach experience, this application embodiment realizes dynamic adjustment of the training load of subsequent training groups based on the actual performance of the preceding training groups. This allows the training load to be adaptively adjusted according to the user's real-time physical condition in a single continuous multi-set training scenario, improving the real-time performance, flexibility, and accuracy of training load adjustment.

[0040] In some embodiments, the training feature data described above may include, but is not limited to, training completion data and training quality data.

[0041] Training completion data indicates the user's degree of task completion in each training session, and may include, but is not limited to, actual completion amount, target completion amount, and completion rate. Actual completion amount refers to the training metric actually achieved by the user in each training session. For example, for repetition-based exercises (such as squats, curls, and presses), actual completion amount is the actual number of repetitions performed; for time-based exercises (such as planks and static squats), actual completion amount is the actual duration of the exercise held. Target completion amount refers to the training metric preset by the training plan for that training session, which may include a target number of repetitions or a target duration. Completion rate is the ratio between actual completion amount and target completion amount, used to quantify the user's degree of completion for that training task.

[0042] Training quality data is used to indicate the quality of a user's movement execution in each training session, and can be obtained by parsing and calculating the raw signals collected by sensors. In this embodiment, training quality data can be determined based on at least one of the following: movement speed data, movement rhythm data, movement amplitude data, and left-right balance data.

[0043] Motion speed data is used to indicate the user's speed in a single action or multiple actions. It can be obtained by integrating or filtering the acceleration signal collected by the accelerometer and can be used to evaluate the speed of action execution and speed fluctuations.

[0044] Movement speed is a key parameter reflecting the force characteristics of the neuromuscular system. According to Hill's muscle contraction model, the concentric contraction speed of a muscle is inversely proportional to the generated active tension: the faster the speed, the lower the tension that a single muscle fiber can output; the slower the speed, the higher the tension output is allowed, such as... Figure 7 As shown. This physiological characteristic determines that different training goals require different movement speeds. For example, explosive power training requires high-speed concentric contraction to preferentially recruit type II fast-twitch muscle fibers and improve motor unit synchronicity, while hypertrophy training is more suitable for moderately controllable speeds to evenly activate type I slow-twitch and type II fast-twitch muscle fibers, thereby obtaining sufficient mechanical tension duration. In addition, the velocity loss rate within a single training set, that is, the percentage of the difference between the first and last movement speeds within a set relative to the initial speed, is a core indicator that objectively reflects the decline in movement quality and the accumulation of neuromuscular fatigue: a velocity loss within a reasonable range indicates that the training load matches the current physical condition, while a sudden drop in speed indicates movement deformation, increased compensation, and abnormal joint load. In the embodiments of this application, movement speed data can be used to quantitatively evaluate the force efficiency of a single movement and the ability to maintain the quality of a single training set based on the above-mentioned tension-velocity curve principle and muscle fiber recruitment theory.

[0045] Motion rhythm data is used to indicate the periodic characteristics of a user's actions, including but not limited to the duration of the action cycle, the fluctuation of the action cycle, and the switching of rhythm types. It can be obtained by analyzing the time series periodicity of accelerometer or gyroscope signals. For example, the standard deviation and expected value of multiple action cycles can be calculated, and the coefficient of variation (standard deviation divided by expected value) can be used to measure rhythm stability; at the same time, the number of rhythm type switching (such as constant speed, acceleration, deceleration) can be recorded.

[0046] Movement rhythm can generally be broken down into four phases: eccentric contraction, peak contraction, concentric contraction, and bottom pause. From an exercise physiology perspective, the rhythm of each phase has a differentiated physiological impact on training quality: During the eccentric phase, muscles are passively lengthened under external force, generating higher mechanical tension than during the concentric phase. This phase is the primary stimulus for inducing controllable muscle micro-injuries and triggering subsequent muscle fiber repair and hypertrophy. During the peak contraction phase, muscles are in an isometric contraction state, and a brief static pause maximizes the electromyographic activation of the target muscle group and reduces compensatory leveraging by adjacent muscle groups. The concentric phase mainly reflects the active recruitment efficiency and force exertion speed of motor units. The bottom pause eliminates movement inertia and re-establishes neuromuscular control, ensuring that the initial force exertion of each repetition is in an effective force state. Inappropriate rhythm allocation, such as uncontrolled rapid descent during the eccentric phase or an excessively short peak contraction time, weakens mechanical tension stimulation and increases joint impact load. Movement rhythm data can be used to extract the movement cycle duration, inter-phase transition rate, and intra-set rhythm consistency of each phase, thereby evaluating the rhythm control quality of training movements based on mechanical tension theory and metabolic stress theory.

[0047] Motion amplitude data is used to indicate the amount of spatial position change achieved by the user during the execution of an action, such as the range of joint angle changes and the displacement distance of the device. For example, for rotational movements, the angle change can be obtained by integrating the gyroscope signal; for translational movements, the displacement information can be obtained by double integration of the accelerometer signal.

[0048] In resistance training, the range of motion directly determines the length-tension relationship of muscle contraction. For example... Figure 8As shown, the peak of the curve corresponds to the optimal initial length, at which point the overlap of thick and thin filaments is optimal, the number of crossbridges is maximized, and the tension is greatest. When the length is shorter or longer than this optimal value, the number of crossbridges decreases, and the tension also decreases. Skeletal muscles can generate maximum active tension at the optimal initial length. Insufficient range of motion will prevent the target muscle group from completing sufficient eccentric stretching and concentric contraction within the optimal length range, weakening the effectiveness of mechanical tension stimulation. Conversely, a range of motion exceeding the safe range may lead to abnormal stress on the passive structures of the joints. Furthermore, the stability of the range of motion is an important indicator of the quality of neuromuscular control, which depends on the trunk stability platform provided by the pre-activation of the core muscles, joint proprioceptive feedback, and the coordinated contraction of agonist and antagonist muscles. When there is core fatigue or delayed proprioceptive feedback, the range of motion may exhibit unexpected trajectory deviations or stroke contractions. This instability not only reduces the effective stimulation of the target muscle group but also induces compensatory load concentration in adjacent joints through the transmission of the human kinetic chain, increasing the risk of sports injuries. In the embodiments of this application, the range of motion data can be used to evaluate the scientific validity and safety of training movements from two dimensions: maximizing mechanical tension and improving the quality of motor control.

[0049] Left-right balance data is used to indicate the degree of force balance between the left and right limbs in bilateral movements. For example, in a squat or bicep curl with dumbbells held in both hands, the peak acceleration / angular velocity, work done, or range of motion of the dumbbells on both sides is calculated to obtain the difference in force exertion between the left and right limbs. Typically, left-right balance data can be obtained through comparative analysis of sensor signals from both sides.

[0050] The essence of left-right balance is the manifestation of the bilateral coordinated control ability of the neuromuscular system. Although there are slight innate bilateral differences in the human body, significant left-right imbalance in resistance training can disrupt the symmetrical biomechanical structure of movements: the stronger limb bears excessive load while the weaker limb receives insufficient stimulation, leading to an unbalanced overall strength development. Simultaneously, to maintain movement execution in an unbalanced state, the trunk and core muscle groups will produce compensatory center of gravity shifts, which in turn cause asymmetrical load concentration in the spine, pelvis, and adjacent joints through kinetic chain transmission, increasing the risk of chronic strain injuries in areas such as the shoulders, knees, and lower back. From a neurocontrol perspective, left-right imbalance reflects the difference in recruitment efficiency and proprioceptive feedback sensitivity between the two sides; the weaker limb often exhibits problems with delayed neural mobilization and decreased accuracy in movement trajectory control. This application's embodiments, by setting left-right balance data and comparing and analyzing signals collected by sensors on both sides (such as bilateral IMUs, bilateral motor encoders, or bilateral skeletal point trajectories extracted by visual sensing modules), quantify the difference in force exertion and trajectory deviation between the two sides, thereby evaluating the quality and safety of training movements from the perspective of bilateral symmetry and kinetic chain integrity.

[0051] Based on this, the aforementioned data on movement speed, movement rhythm, movement amplitude, and left-right balance comprehensively characterize the quality features of resistance training movements from four independent and complementary perspectives: time dynamics, phase control, spatial trajectory, and bilateral symmetry.

[0052] It should be understood that embodiments of this application may provide an indicator data pool, which includes training quality data from multiple dimensions. In practical applications, a single dimension of data can be arbitrarily selected from the indicator data pool as training quality data, or multiple dimensions of data or a combination of multiple dimensions of data can be selected as training quality data.

[0053] Taking an indicator data pool that includes motion speed data, motion rhythm data, motion amplitude data, and left-right balance data as an example, in some embodiments, the process of determining training quality data may include: selecting any one dimension of data from the motion speed data, motion rhythm data, motion amplitude data, and left-right balance data as training quality data; or, selecting at least two dimensions of data from the motion speed data, motion rhythm data, motion amplitude data, and left-right balance data, obtaining the weight values ​​corresponding to the at least two dimensions of data respectively, and performing a weighted summation of the at least two dimensions of data according to the weight values ​​corresponding to the at least two dimensions of data respectively to obtain the training quality data. The weight values ​​corresponding to multiple dimensions of data may be the same or different; the weight values ​​corresponding to each dimension of data may be preset or determined based on motion type and requirements, etc., and this application embodiment does not limit this.

[0054] Furthermore, training quality data for the desired dimensions can be selected arbitrarily from the indicator data pool or according to preset filtering conditions to adapt to the differentiated judgment needs of different movement types, user habits, and training stages. For example, preset filtering conditions include the highest accuracy and / or discrimination in the current training scenario, which can be obtained based on data dispersion analysis, sensitivity analysis, and anti-interference analysis of all dimensions of data (movement speed data, movement rhythm data, movement amplitude data, left-right balance data, etc.) in the indicator data pool. Specifically, data dispersion analysis is used to assess the differences in the numerical distribution of each dimension of data across different training groups; sensitivity analysis is used to assess the responsiveness of each dimension of data to changes in the user's physical condition; and anti-interference analysis is used to assess the stability of each dimension of data in the presence of slight shaking or signal noise. Combining the results of these three analyses, the dimension data with the highest score can be selected to further determine the training quality data. For example, when a user performs dumbbell curls, the movement amplitude data has the highest dispersion, the highest sensitivity, and good anti-interference performance, so movement amplitude data can be selected as the training quality data.

[0055] The above embodiments use training quality data, including but not limited to at least one of the following: movement speed data, movement rhythm data, movement amplitude data, and left-right balance data. These data can be acquired using any one or more types of sensors. This application does not limit the content or acquisition method of the training quality data; in practical applications, it can be flexibly set according to the training scenario, movement type, accuracy requirements, and device form.

[0056] For example, training quality data can be collected based on an IMU. An IMU includes an accelerometer and a gyroscope. An accelerometer can be used to measure acceleration information in three directions in space (which can be mapped to motion velocity data, etc.), and a gyroscope can be used to measure rotational angular velocity information (which can be mapped to motion amplitude data, motion trajectory data, etc.).

[0057] For example, training quality data can be collected using visual sensors such as cameras and depth cameras. Visual sensors can be used to capture images or videos of the user's training movements, extracting motion posture data (such as the position of human skeletal points, changes in joint angles, etc.) from the captured images or videos, and further mapping this data into training quality data. In addition to being mapped to the four types of training quality data shown in the above embodiments, the motion posture data extracted from images or videos can also be mapped to other types, such as human motion posture tracking data, real-time skeletal point rendering, and joint range of motion analysis.

[0058] For example, training quality data can be collected based on a motor resistance sensing module. This module can include a motor with a digital encoder and a linked resistance output mechanism (such as a cable traction system). The encoder can be used to collect the motor's rotation angle, speed, and output torque in real time and map them to training quality data. The motor, as the resistance source, can dynamically adjust its output resistance according to control commands to replace traditional weightlifting equipment (such as dumbbells and barbells) for strength training. Typically, the encoder in a motor resistance sensing module collects data with higher accuracy than an IMU, and the resistance output can be digitally controlled to achieve more precise training load adjustment and training quality feedback.

[0059] In summary, the technical solution provided in this application divides training feature data into two dimensions: training completion data and training quality data. Training completion data reflects the user's basic execution ability from the perspective of task achievement, while training quality data reflects the user's motor control ability and physical condition from the perspective of movement standardization. Combining training completion data and training quality data avoids the judgment bias caused by relying solely on a single dimension of data, providing a comprehensive and multi-dimensional data foundation for accurately determining the training achievement status.

[0060] In some embodiments, step S200 may include: if the training completion data of each training session in the first N training sessions meets the preset completion conditions and the training quality data of each training session in the first N training sessions meets the preset quality conditions, then the training achievement status is determined to be "achieved"; if the training completion data of any training session in the first N training sessions does not meet the preset completion conditions, or the training quality data of any training session in the first N training sessions does not meet the preset quality conditions, then the training achievement status is determined to be "not achieved".

[0061] The preset completion condition refers to the data standard that the training data must meet to complete. This application does not limit the specific content of the preset completion condition; in practical applications, it can be flexibly set according to the type and requirements of the training data. For example, taking training data including completion rate as an example, the preset completion condition may include an actual completion rate greater than or equal to a completion rate threshold (e.g., the completion rate threshold is between 70% and 85%). If the actual completion rate of any of the first N training sets is less than the completion rate threshold, then it is determined that the training data of that set does not meet the preset completion condition.

[0062] Preset quality conditions refer to the data standards that training quality data should meet. This application does not limit the specific content of the preset quality conditions; in practical applications, they can be flexibly set according to the type and requirements of the training quality data. For example, for training quality data of motion feature type (such as movement speed data, movement amplitude data, etc.), preset quality conditions may include actual data fluctuation being less than or equal to a data fluctuation threshold (e.g., the data fluctuation threshold is between 5% and 20%); for rhythm type training quality data (such as movement rhythm data, etc.), preset quality conditions may include actual rhythm type switching times being less than or equal to a switching time threshold (e.g., the switching time threshold is between 1 and 4 times).

[0063] It should be understood that in the embodiments of this application, the training quality data corresponding to different training groups can be data of the same dimension (e.g., each training group uses motion amplitude data) or data of different dimensions (e.g., the first training group uses motion amplitude data, and the second training group uses motion speed data). Based on this, when the training quality data corresponding to different training groups is data of the same dimension, the preset quality conditions corresponding to different training groups can be set to the same or different threshold conditions. For example, all can be set to a data fluctuation threshold of 10.5%, or the first training group can be set to a data fluctuation threshold of 8.5% and the second training group can be set to a data fluctuation threshold of 10.5%. When the training quality data corresponding to different training groups is data of different dimensions, the preset quality conditions corresponding to different training groups can also be set to the same or different threshold conditions. For example, all can be set to a data fluctuation threshold of 10.5%, or the first training group can be set to a data fluctuation threshold of 10.5% and the second training group can be set to a threshold of 2 switching times.

[0064] Taking the training achievement status, which includes both achievement and non-achievement, as an example, if the training completion data of each of the first N training sessions meets the preset completion conditions, and the training quality data of each of the first N training sessions also meets the preset quality conditions, then the training achievement status is determined to be "achieved." If the training completion data of any of the first N training sessions does not meet the preset completion conditions, or the training quality data of any of the first N training sessions does not meet the preset quality conditions, then the training achievement status is determined to be "non-achieved." Of course, in practical applications, the classification of training achievement status can be more refined, such as being divided into exceeding the standard, achieving the standard, and non-achieving, etc. Correspondingly, the preset completion conditions and preset quality conditions also need to be further divided into more threshold conditions.

[0065] This application embodiment can also classify user performance levels for training completion data and training quality data respectively, and then classify the training achievement status based on the user performance levels corresponding to the training completion data and training quality data respectively. For example, as shown in the example... Figure 2 As shown, training completion data can include completion rate (divided into incomplete, completed, and over-completed), and training quality data can include rhythm stability (divided into irregular rhythm, average rhythm, and stable rhythm), movement speed (divided into fast speed, slow speed, and appropriate speed), movement amplitude (divided into small amplitude, large amplitude, and appropriate amplitude), and left-right balance (divided into poor balance, average balance, and good balance). Based on the user performance levels corresponding to the training completion data and training quality data, the training achievement status can be further divided into training failure, achievement, and exceeding the target. It should be understood that... Figure 2This example only categorizes training achievement status into three types, but this does not constitute a limitation on the embodiments of this application. Taking the division of training completion data into P user performance levels (P being a positive integer) and training quality data into Q user performance levels (Q being a positive integer) as an example, the training achievement status can be divided into at most P×Q types. For example, based on... Figure 2 The user performance levels shown in the training completion data and training quality data can be divided into a maximum of 9 (3×3) types for the training achievement status.

[0066] In the above example, training completion data and training quality data are used as two independent dimensions to determine the training achievement status, but this does not constitute a limitation on the embodiments of this application. In practical applications, the two independent dimensions of training completion data and training quality data can also be fused to calculate a comprehensive training score, and then the training achievement status can be determined based on the comprehensive training score. For example, the two independent dimensions of training completion data and training quality data can be mapped to data scores respectively, and then the data scores corresponding to these two independent dimensions can be weighted and summed or arithmetically averaged to calculate a comprehensive training score. The training achievement status can then be determined based on a comparison between the comprehensive training score and a preset score threshold.

[0067] In summary, the technical solution provided by the embodiments of this application, by dividing the training achievement status into mutually exclusive status levels, such as achievement and non-achievement, provides a clear and reliable decision boundary for subsequent bidirectional mutually exclusive training load adjustment, avoiding ambiguity and conflict in the training load adjustment scheme.

[0068] In some embodiments, step S300 may include: increasing the training load of the N+1th training group if the training target status of the first N training groups is met; and decreasing the training load of the N+1th training group if the training target status of the first N training groups is not met.

[0069] If the user has achieved the target training status for the first N training sets, it can be determined that the user demonstrated good physical condition and motor control in the first N training sets. At this point, it can be determined that the user is capable of continuing to withstand higher training loads or exploring training potential. Therefore, if the user has achieved the target training status for the first N training sets, a positive adjustment instruction can be generated to increase the training load for the N+1th training set, such as increasing the number of repetitions and / or the training weight.

[0070] If the training objective status of the current N sets of training is "not met," it can be determined that the user has shown signs of fatigue or decreased movement quality in the first N sets of training. At this point, it can be determined that the user needs to reduce the training load to avoid overtraining or sports injury. Therefore, if the training objective status of the first N sets of training is "not met," a negative adjustment instruction can be generated to reduce the training load of the N+1th set of training, such as reducing the number of repetitions and / or the training weight of the N+1th set.

[0071] For example, the training load includes the number of training iterations. Increasing the training load can include adding a first number of training iterations to the initial target number of training iterations for the N+1th training group, while decreasing the training load can include removing a second number of training iterations from the initial target number of training iterations for the N+1th training group. Both the first and second numbers are positive integers, and they can be the same or different. In practical applications, they can be flexibly set according to requirements, such as the first number being 1, 2, 3, or 4 iterations, and the second number being 1, 2, 3, or 4 iterations. Taking an initial target number of training iterations of 10 for the N+1th training group, with both the first and second numbers being 3, as an example, if the training achievement status of the first N training groups is satisfactory, the target number of training iterations for the N+1th training group can be increased from 10 to 13 iterations; if the training achievement status of the first N training groups is unsatisfactory, the target number of training iterations for the N+1th training group can be reduced from 10 to 7 iterations.

[0072] It should be understood that increasing the load when the target is met and decreasing the load when the target is not met constitute a mutually exclusive adjustment logic. Only one of these two can be triggered in the same training unit within the same training group, to ensure the clarity and consistency of the training load adjustment scheme. It should also be understood that in the embodiments of this application, the amount of increase or decrease in training load can be preset or determined in real time. For example, it can be determined in real time based on the degree of achievement indicated by the training target status, such as the increase corresponding to exceeding the target being greater than the increase corresponding to achieving the target; or it can be determined in real time based on the quality of movement and / or the user's fatigue level indicated by training quality data.

[0073] Taking the method of determining the increase in training load in real time based on the degree of achievement indicated by the training achievement status as an example, the above-mentioned increase in training load for the N+1th training group may include: determining the increase in training load based on the training achievement status, wherein the increase is positively correlated with the degree of achievement indicated by the training achievement status, such as the increase corresponding to exceeding the standard being greater than the increase corresponding to achieving the standard. Taking the method of determining the decrease in training load in real time based on the degree of achievement indicated by the training achievement status as an example, the above-mentioned decrease in training load for the N+1th training group may include: determining the decrease in training load based on the training achievement status, wherein the decrease is positively correlated with the degree of non-achievement indicated by the training achievement status, such as the decrease corresponding to severe non-achievement being greater than the decrease corresponding to slight non-achievement.

[0074] In summary, the technical solution provided in this application constructs a bidirectional, mutually exclusive intelligent adaptive closed-loop system for the number of repetitions, breaking through the unidirectional adjustment mode in related technologies that only supports fatigue-induced reduction of repetitions and lacks positive reinforcement for increasing repetitions. When the user is in good condition, the training load is increased to tap their training potential and achieve a breakthrough; when the user is fatigued, the training load is reduced to actively protect against overtraining. The bidirectional adaptive mechanism provided in this application makes the training plan both challenging and safe, improving the training effect and user experience of intelligent fitness equipment.

[0075] In some embodiments, such as Figure 3 As shown, step S300 may include: when the current completion amount of the N+1th training group reaches the reference completion amount, adjusting the training load of the N+1th training group according to the training achievement status of the previous N training groups.

[0076] During the user's N+1th training session, the current completion rate of the N+1th training session can be monitored in real time. If the current completion rate reaches a reference completion rate, the training load adjustment for the N+1th training session will be triggered. The reference completion rate is a progress threshold used to determine whether to trigger training load adjustment; it can be preset or determined in real time based on the training type or the performance of the previous N training sessions. By setting a reference completion rate to trigger training load adjustment, it is possible to avoid premature adjustment of the training load during the N+1th training session, which could lead to inaccurate decision-making or a decline in user experience. This allows for precise intervention after the user's physical condition has been fully demonstrated.

[0077] In some embodiments, such as Figure 3 As shown, the above training load adjustment method may further include the following steps S010 to S020.

[0078] Step S010: Determine the baseline of the completion amount of the N+1th training group based on the difference in completion amount of the first N training groups.

[0079] Completion variance is used to indicate the dispersion of the actual completion amounts among the training sessions in the first N training sessions. For example, when N equals 2, the completion variance of the first 2 training sessions can be the difference or absolute value of the difference between the actual completion amounts of the first training session and the second training session, or the difference or absolute value of the difference between the actual completion rates determined based on the actual completion amounts. When N equals 3, the completion variance of the first 3 training sessions can be the standard deviation, range, or mean of the pairwise differences between the actual completion amounts of the first 3 training sessions, or the standard deviation, range, or mean of the pairwise differences between the actual completion rates determined based on the actual completion amounts.

[0080] Based on the differences in completion amounts among the first N training groups, the baseline completion amount for the (N+1)th training group can be determined in real time. In some embodiments, step S010 may include: if the differences in completion amounts among the first N training groups are less than or equal to a preset difference threshold, using the target completion amount of the (N+1)th training group as the baseline completion amount for the (N+1)th training group; if the differences in completion amounts among the first N training groups are greater than the preset difference threshold, determining the baseline completion amount for the (N+1)th training group based on the actual completion amounts of the first N training groups.

[0081] The specific value of the preset difference threshold is not limited in this application embodiment. In actual application, it can be arbitrarily and flexibly set according to the action type, the specific type of difference in the amount of completion and other requirements. For example, the preset difference threshold can be set between 10% and 20%, or between 1 and 3 times, or between 5 and 10 seconds.

[0082] When the difference in completion rate among the current N training groups is less than or equal to a preset difference threshold, it can be determined that the user performance of the first N training groups is relatively stable. In this case, the initial target completion rate of the N+1th training group (such as the preset number of training sessions or training duration in the training plan for the N+1th training group) can be used as the base for the completion rate of the N+1th training group. For example, if the initial target completion rate for each training group is 10 times, the actual completion rate of the first training group is 10 times, the actual completion rate of the second training group is 9 times, and the difference between the actual completion rates determined based on the actual completion rates is 10%, which is less than the preset difference threshold of 18%, then the base for the completion rate of the third training group can be the initial target completion rate of 10 times for the third training group.

[0083] When the difference in completion volume among the current N training groups exceeds a preset difference threshold, it can be determined that the user performance in the first N training groups fluctuates significantly. In this case, calculating the adjustment trigger point for the training load based on the initial target completion volume may not be reasonable. To reflect the actual fluctuations in user performance, this embodiment determines the completion volume baseline for the N+1th training group based on the actual completion volume of the first N training groups. This baseline can be determined by taking the average, weighted average, maximum, minimum, or median of the actual completion volume of the first N training groups. For example, if the initial target completion volume for each training group is 10 repetitions, the actual completion volume of the first training group is 10 repetitions, the actual completion volume of the second training group is 6 repetitions, and the difference between the actual completion rates determined based on the actual completion volume is 40%, which is greater than the preset difference threshold of 18%, then the completion volume baseline for the third training group can be the average of the actual completion volumes of the first two training groups, which is 8 repetitions.

[0084] Step S020: Determine the reference completion amount of the N+1th training group based on the preset progress ratio and the completion amount of the N+1th training group.

[0085] The preset progress percentage refers to the percentage threshold used to determine when to trigger training load adjustment during the N+1th training session. This application does not limit the specific value of the preset progress percentage; in practical applications, it can be flexibly set according to needs, for example, 20%, 50%, or 70%. In practical applications, the preset progress percentage can be set to greater than 50% to trigger training load adjustment in the middle to later stages of the N+1th training session. This is because: in strength training, the user's true fatigue level and remaining potential usually only become fully apparent in the middle to later stages; if training load adjustment is triggered too early in the first half, the user's physical reserves are still sufficient, making the adjustment decision less representative, and informing the user of increased training load too early may cause psychological burden; while when training load adjustment is triggered in the middle to later stages, the user has fully entered the training state, and outputting "can continue" or "needs to reduce" based on their performance is more in line with physiological reality and psychological expectations, which is conducive to accurately tapping the user's potential.

[0086] Based on the preset progress ratio and the baseline completion volume of the N+1th training group, the reference completion volume for the N+1th training group is further determined. For example, the product of the preset progress ratio and the baseline completion volume of the N+1th training group is used as the reference completion volume for the N+1th training group (reference completion volume = baseline completion volume × preset progress ratio). For example, taking a repetition-based exercise as an example, assuming the baseline completion volume of the N+1th training group is 10 repetitions and the preset progress ratio is 80%, then the reference completion volume for the N+1th training group is 8 repetitions, and the training load adjustment is triggered when the 8th repetition is completed in the N+1th training group; assuming the baseline completion volume of the N+1th training group is 8 repetitions and the preset progress ratio is 80%, then the reference completion volume for the N+1th training group is 7 repetitions (8 × 80% rounded up), and the training load adjustment is triggered when the 7th repetition is completed in the N+1th training group.

[0087] In summary, the technical solution provided in this application, by introducing a dynamic calculation mechanism for the baseline and reference completion amount, allows the timing of training load adjustment to be adaptively set based on the stability of the first N training sessions, improving the rationality and personalization of the trigger point calculation. Simultaneously, by triggering training load adjustment in the middle to later stages of the N+1th training session, it avoids decision-making errors and a decline in user experience caused by premature adjustment, achieving precise intervention after the user's physical condition has been fully demonstrated, effectively balancing training breakthroughs and exercise safety.

[0088] In some embodiments, the training load adjustment method described above may further include: performing a load cue operation; wherein the load cue operation is used to indicate that the training load of the N+1th training group has changed.

[0089] When it is necessary to adjust the training load for the N+1th training session, the adjustment information can be conveyed to the user by executing a load prompt operation. This application embodiment does not limit the specific type of load prompt operation; in practical applications, it can be flexibly set according to the type and needs of the smart fitness equipment. For example, the load prompt operation may include, but is not limited to, at least one of the following: voice broadcast operation, light flashing operation, body vibration operation, body button confirmation operation, gesture sensing operation, and other uninterrupted interaction methods. For example, taking a smart dumbbell as an example, the built-in voice module of the smart dumbbell can announce "2 times have been added for you" or "2 times have been removed for you," while the smart dumbbell's body vibration motor emits a short vibration, allowing the user to directly perceive the adjustment result without putting the smart dumbbell down.

[0090] This application does not limit the timing of the load prompt operation. In practical applications, it can be flexibly set according to needs. For example, the load prompt operation can be performed before the start of the N+1th training session, such as during the group rest period, by informing the user through the terminal interface or device voice that "based on your performance in the first two groups, the number of training sessions in the third group may be adjusted," so that the user can be aware of the special features in advance; or, the load prompt operation can be performed when the N+1th training session reaches the reference completion amount to trigger the training load adjustment, informing the user of the specific adjustment content; or, the load prompt operation can be performed after the training load adjustment and before the user completes the training, informing the user of the current remaining workload.

[0091] In practical applications, users can interactively accept or reject training load adjustments. For example, after a load prompt is executed, the user can confirm whether to perform the training load adjustment via voice commands (such as "accept adjustment" or "cancel adjustment"); or after training, the user can provide a satisfaction rating or feedback on the training load adjustment through the training settlement report on the terminal interface. This application embodiment can retain user acceptance data regarding training load adjustments for subsequent iterative optimization of the selection model and threshold rules. For example, if a user frequently refuses to increase the number of training iterations, the increment amount can be appropriately reduced or the trigger threshold adjusted in subsequent training sessions.

[0092] In summary, the technical solution provided in this application, through the execution of load prompts, achieves uninterrupted notification of training load adjustments. Users can perceive plan changes and continue training without interrupting or manually modifying the process, ensuring continuity and immersion. Furthermore, by supporting multimodal load prompts such as voice, vibration, and light, and through a full-link interactive design including pre-training announcements, real-time notifications during training, and post-training feedback collection, the level of intelligence is enhanced. Moreover, by retaining user behavior data and using iterative methods, the training load adjustment scheme can continuously self-optimize, becoming more tailored to individual user habits.

[0093] The technical solution provided in the embodiments of this application will be described below with an example.

[0094] Please see Figure 4 , Figure 4 This is a flowchart of another training load adjustment method provided in an embodiment of this application. For example... Figure 4 As shown, the training load adjustment method may include the following steps S401 to S409.

[0095] Step S401: In response to the training start operation, load the training parameters of multiple training sets for the target training unit.

[0096] Users can initiate training by clicking the "Start Training" button displayed on the terminal device or by pressing the start button on the smart fitness equipment itself. The smart fitness equipment or its connected terminal device can then load multiple sets of training parameters for the target training unit, such as the target completion amount and training load, and can also initialize the sensor and indicator calculation mechanisms.

[0097] Step S402: Collect training feature data for each training group.

[0098] Users can follow the instructions to perform multiple training sessions sequentially. During each training session, training feature data can be collected through sensors, including training completion data (such as actual completion amount, target completion amount, and completion rate) and training quality data (such as movement speed data, movement rhythm data, movement amplitude data, and left-right balance data).

[0099] Step S403: Determine whether the training completion data of each training session meets the preset completion conditions, and whether the training quality data of each training session meets the preset quality conditions.

[0100] From the pool of indicator data corresponding to the training quality data, the required training quality data can be automatically selected and filtered, and the training completion data can be combined to classify the training achievement status, such as achieving or not achieving the target.

[0101] Step S404: If the training completion data of each training session in the first N training sessions meets the preset completion conditions, and the training quality data of each training session in the first N training sessions meets the preset quality conditions, then the training achievement status is determined to be achieved.

[0102] Step S405: If the training completion data of any training group in the first N training groups does not meet the preset completion conditions, or the training quality data of any training group in the first N training groups does not meet the preset quality conditions, the training achievement status is determined to be unachieved.

[0103] Step S406: Determine whether the current completion amount of the N+1th training group has reached the reference completion amount.

[0104] During the user's training of the N+1th group, the current completion amount of the N+1th group (such as the current number of completions or the current completion time) can be continuously monitored, and it can be determined whether the current completion amount has reached the reference completion amount. If the current completion amount has reached the reference completion amount, then continue to execute the following steps S407 or S408; otherwise, repeat step S406.

[0105] Step S407: If the training target status of the first N training sessions is met, increase the training load of the N+1th training session.

[0106] Step S408: If the training target status of the first N training sessions is not met, reduce the training load of the N+1th training session.

[0107] Training load can include: number of training sessions, training weight, and / or training volume, etc.

[0108] Step S409: Perform the load alert operation.

[0109] related Figure 4 For further descriptions of the steps and their beneficial effects in the embodiments, please refer to the above embodiments, which will not be repeated here.

[0110] It should be noted that the technical solutions provided in the embodiments of this application may have various alternative, extended, or modified solutions in practical applications. Other solutions that can be obtained by those skilled in the art from the content disclosed in the embodiments of this application all fall within the protection scope of this application. For example, when adjusting the training load of the N+1th training group, in addition to relying on the training achievement status of the previous N training groups, the training feature data currently collected for the N+1th training group can also be combined; it can also be extended to global adjustment between groups, real-time fine-tuning of a single group throughout the entire process, and proprietary adjustment rules for supergroups / cyclic groups; a personalized setting module can also be added to support users to customize the upper limit of training load adjustment, manually lock preference judgment indicators, turn on / off automatic adjustment function, and customize thresholds, etc.; the indicator data pool corresponding to the training quality data can also be expanded to include force power, interval duration, peak contraction duration, movement trajectory deviation, etc.

[0111] Please see Figure 5 , Figure 5 This is a schematic diagram of a training load adjustment device provided in an embodiment of this application. This training load adjustment device can be used to implement the above-described training load adjustment method. The training load adjustment device can be an electronic device or can be installed within an electronic device. Figure 5 As shown, the training load adjustment device 500 may include: a data acquisition module 510, a target detection module 520, and a load adjustment module 530.

[0112] The data acquisition module 510 is used to: acquire training feature data of each training session during multiple training sessions of the target training unit; the achievement detection module 520 is used to: determine the achievement status of the first N training sessions based on the training feature data of the first N training sessions, where N is a positive integer; the load adjustment module 530 is used to: adjust the training load of the (N+1)th training session based on the achievement status of the first N training sessions.

[0113] In some embodiments, training feature data includes training completion data and training quality data; wherein, training quality data is determined based on at least one of the following: movement speed data, movement rhythm data, movement amplitude data, and left-right balance data; movement speed data is used to indicate the user's movement speed in a single movement or multiple movements, movement rhythm data is used to indicate the periodicity of the user's movement during the execution of the movement, movement amplitude data is used to indicate the amount of spatial position change achieved by the user during the execution of the movement, and left-right balance data is used to indicate the degree of force balance between the left and right limbs in movements involving both limbs.

[0114] In some embodiments, the data acquisition module 510 is further configured to: select any one dimension of data from motion speed data, motion rhythm data, motion amplitude data, and left-right balance data as training quality data; or, select at least two dimensions of data from motion speed data, motion rhythm data, motion amplitude data, and left-right balance data, obtain the weight values ​​corresponding to the at least two dimensions of data respectively, and perform a weighted summation of the at least two dimensions of data according to the weight values ​​corresponding to the at least two dimensions of data respectively to obtain training quality data.

[0115] In some embodiments, the above-mentioned compliance detection module 520 is further configured to: determine the training compliance status as compliant when the training completion data of each training session in the first N training sessions meets the preset completion conditions and the training quality data of each training session in the first N training sessions meets the preset quality conditions; and determine the training compliance status as non-compliant when the training completion data of any training session in the first N training sessions does not meet the preset completion conditions or the training quality data of any training session in the first N training sessions does not meet the preset quality conditions.

[0116] In some embodiments, the load adjustment module 530 is further configured to: increase the training load of the N+1th training group when the training target is met; and decrease the training load of the N+1th training group when the training target is not met.

[0117] In some embodiments, the load adjustment module 530 is further configured to: add a first number of training times based on the initial target number of training times for the N+1th training group; or, reduce a second number of training times based on the initial target number of training times for the N+1th training group; wherein the first number and the second number are both positive integers, and the first number and the second number may be the same or different.

[0118] In some embodiments, the load adjustment module 530 is further configured to: determine an increase in training load based on the training achievement status, wherein the increase is positively correlated with the degree of achievement indicated by the training achievement status; or, determine a decrease in training load based on the training achievement status, wherein the decrease is positively correlated with the degree of non-achievement indicated by the training achievement status.

[0119] In some embodiments, the load adjustment module 530 is further configured to: adjust the training load of the N+1th group of training according to the training achievement status when the current completion amount of the N+1th group of training reaches the reference completion amount.

[0120] In some embodiments, the load adjustment module 530 is further configured to: determine the base number of the completion amount of the N+1th training group based on the difference in completion amount of the first N training groups, wherein the difference in completion amount is used to indicate the degree of dispersion between the actual completion amounts of each training group in the first N training groups; and determine the reference completion amount of the N+1th training group based on the preset progress ratio and the base number of the completion amount of the N+1th training group.

[0121] In some embodiments, the preset progress ratio is greater than 50% to trigger training load adjustment in the middle and later stages of the N+1th training group.

[0122] In some embodiments, the load adjustment module 530 is further configured to: when the difference in completion amount of the first N training groups is less than or equal to a preset difference threshold, use the target completion amount of the N+1 training group as the base amount of the N+1 training group; when the difference in completion amount of the first N training groups is greater than the preset difference threshold, determine the base amount of the N+1 training group based on the actual completion amount of the first N training groups.

[0123] In some embodiments, the load adjustment module 530 is further configured to: take the average, weighted average, maximum, minimum, or median of the actual completion amount of the first N training groups to obtain the base number of the completion amount of the N+1 training group.

[0124] In some embodiments, such as Figure 6 As shown, the training load adjustment device 500 may further include a load prompting module 540 for performing a load prompting operation; wherein the load prompting operation is used to prompt that the training load of the N+1th training group has changed.

[0125] For further description of the steps performed by each module in the above-mentioned training load adjustment device and their beneficial effects, please refer to the embodiments of the above-mentioned training load adjustment method. Their technical concepts are the same or similar, and will not be elaborated here.

[0126] This application also provides a computer-readable storage medium storing a computer program or instructions. When the computer program or instructions are executed by a processor, they implement the above-described training load adjustment method and have all the beneficial effects of the above-described training load adjustment method. Further details will not be elaborated here.

[0127] This application also provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed by a processor, they implement the above-described training load adjustment method and have all the beneficial effects of the above-described training load adjustment method. Further details will not be elaborated here.

[0128] This application also provides an electronic device, including a memory and a processor. The memory stores a computer program or instructions; the processor executes the computer program or instructions in the memory to implement the steps of the training load adjustment method described above. This electronic device has all the beneficial effects of the training load adjustment method described above, which will not be elaborated further here.

[0129] Computer-readable storage media can be, for example, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof, without specific limitation herein. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0130] In some embodiments of this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used or combined with an instruction execution system, apparatus, or device.

[0131] The aforementioned computer-readable storage medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0132] Computer program code for performing operations of some embodiments of this application can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a Local Area Network (LAN) or a Wide Area Network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] This application also provides an intelligent fitness device, which may include: a device body; a sensing unit for collecting motion signals; and the aforementioned training load adjustment device or electronic device. This intelligent fitness device possesses all the beneficial effects of the aforementioned training load adjustment device or electronic device, which will not be elaborated upon here. The intelligent fitness device can be implemented as an intelligent dumbbell, intelligent barbell, intelligent kettlebell, or comprehensive strength training device, etc., and this application does not limit this. The sensing unit in the intelligent fitness device may be a built-in sensor (such as an IMU, motor resistance sensing module, etc.) to collect motion signals and map them to the aforementioned training feature data; or, the intelligent fitness device may also be connected to an external sensor (such as a camera) to obtain the aforementioned training feature data; thereby, the intelligent fitness device can execute the aforementioned training load adjustment method.

[0134] This application also provides a terminal device, which may include the aforementioned training load adjustment device or electronic device. This terminal device possesses all the beneficial effects of the aforementioned training load adjustment device or electronic device, which will not be elaborated upon here. The terminal device can be a mobile phone, tablet computer, smart wearable device, smart speaker, or smart TV, etc., and this application does not limit its implementation. The terminal device may have a built-in sensor (such as a camera), connect to an external sensor (such as a camera), and / or connect to smart fitness equipment to obtain the aforementioned training feature data, thereby executing the aforementioned training load adjustment method. The terminal device and the smart fitness equipment can be connected via a hard wire or via a network (such as a wired network, wireless network, Bluetooth, etc.), and this application does not limit their connection.

[0135] It should be noted that, in the data processing stage, the technical solution of this application has strictly limited the scope of data collection to the minimum necessary to achieve the technical objectives, preventing the acquisition of irrelevant information. For any user information to be collected, the data subject will be clearly informed and their consent obtained. Furthermore, technologies such as encrypted storage and access control are employed to strengthen data security and ensure the security and compliance of the entire data processing process. The technical model and decision-making mechanism are based on objective technical parameters and do not introduce unnecessary parameters such as gender or age that may lead to discrimination, resolutely eliminating algorithmic discrimination and upholding public order and good morals. In addition, the specification fully describes the technical implementation methods, application scenarios, and compliance protection details. The claims are consistent with the content of the specification, key compliance designs are clear and verifiable, and the overall technical design is guided by the protection of public interests and adherence to social ethics, without any circumstances that harm public interests or violate public order and good morals.

[0136] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0137] The above provides a detailed description of a training load adjustment method, apparatus, device, medium, and intelligent fitness equipment provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for adjusting training load, characterized in that, The method includes: During multiple training sessions of the target training unit, the training feature data for each training session is acquired. Based on the training feature data of the first N training sessions, the training achievement status of the first N training sessions is determined; where N is a positive integer. Based on the training achievement status, adjust the training load of the N+1th training group.

2. The method according to claim 1, characterized in that, The training feature data includes training completion data and training quality data; wherein... The training quality data is determined based on at least one of the following: movement speed data, movement rhythm data, movement amplitude data, and left-right balance data; The process for determining the training quality data includes: Choose any one dimension of data from the action speed data, the action rhythm data, the action amplitude data, and the left-right balance data as the training quality data; or, Select at least two dimensions of data from the motion speed data, the motion rhythm data, the motion amplitude data, and the left-right balance data; obtain the weight values ​​corresponding to the at least two dimensions of data respectively; and perform a weighted summation of the at least two dimensions of data according to the weight values ​​corresponding to the at least two dimensions of data respectively to obtain the training quality data.

3. The method according to claim 2, characterized in that, Determining the training achievement status of the first N training sessions based on the training feature data includes: If the training completion data of each training session in the first N training sessions meets the preset completion conditions, and the training quality data of each training session in the first N training sessions meets the preset quality conditions, then the training achievement status is determined to be achieved. If the training completion data of any one of the first N training sets does not meet the preset completion conditions, or if the training quality data of any one of the first N training sets does not meet the preset quality conditions, the training achievement status is determined to be unachieved.

4. The method according to claim 1, characterized in that, The step of adjusting the training load for the N+1th training group based on the training achievement status includes: If the training achievement status is achieved, the training load of the N+1th training group is increased; If the training target is not met, reduce the training load of the N+1th training group.

5. The method according to claim 4, characterized in that, The method of increasing the training load of the N+1th training group includes: adding a first number of training times based on the initial target number of training times of the N+1th training group; The reduction of the training load of the N+1th training group includes: reducing the number of training sessions by a second number based on the initial target number of training sessions for the N+1th training group. Wherein, both the first quantity and the second quantity are positive integers, and the first quantity and the second quantity may be the same or different.

6. The method according to claim 4, characterized in that, The step of increasing the training load for the N+1th training group includes: determining the amount of increase in the training load based on the training achievement status; wherein the amount of increase is positively correlated with the degree of achievement indicated by the training achievement status; The reduction of the training load for the N+1th training group includes: determining the amount of reduction of the training load based on the training achievement status; wherein the amount of reduction is positively correlated with the degree of non-achievement indicated by the training achievement status.

7. The method according to claim 1, characterized in that, The step of adjusting the training load for the N+1th training group based on the training achievement status includes: If the current completion amount of the N+1th training group reaches the reference completion amount, the training load of the N+1th training group is adjusted according to the training achievement status.

8. The method according to claim 7, characterized in that, The method further includes: Based on the differences in completion amounts among the first N training groups, the base number of completion amounts for the (N+1)th training group is determined; wherein, the differences in completion amounts are used to indicate the degree of dispersion between the actual completion amounts of each training group in the first N training groups. The reference completion amount of the N+1th training group is determined based on the preset progress ratio and the completion amount base of the N+1th training group.

9. The method according to claim 8, characterized in that, The preset progress ratio is greater than 50% to trigger training load adjustment in the middle and later stages of the N+1th training group.

10. The method according to claim 8, characterized in that, The step of determining the base number of the N+1th training group's completion based on the differences in completion amounts among the first N training groups includes: If the difference in the completion amount of the first N training groups is less than or equal to a preset difference threshold, the target completion amount of the N+1th training group is used as the base number of the completion amount of the N+1th training group. If the difference in completion amount among the first N training groups is greater than the preset difference threshold, the base number of completion amount for the (N+1)th training group is determined based on the actual completion amount of the first N training groups.

11. The method according to claim 10, characterized in that, The step of determining the completion base of the (N+1)th training group based on the actual completion amount of the first N training groups includes: The average, weighted average, maximum, minimum, or median of the actual completion amount of the first N training groups is taken to obtain the base number of the completion amount of the N+1th training group.

12. The method according to claim 1, characterized in that, The method further includes: Perform a load alert operation; wherein the load alert operation is used to alert that the training load of the N+1th training group has changed.

13. A training load adjustment device, characterized in that, The device includes: The data acquisition module is used to acquire training feature data for each training session during multiple training sessions of the target training unit. The achievement detection module is used to determine the achievement status of the first N training sessions based on the training feature data of the first N training sessions; wherein, N is a positive integer; The load adjustment module is used to adjust the training load of the N+1th training group according to the training achievement status.

14. An electronic device, characterized in that, include: A memory on which computer programs or instructions are stored; A processor for executing the computer program or instructions in the memory to implement the training load adjustment method as described in any one of claims 1 to 12.

15. A computer-readable storage medium, characterized in that, It stores computer programs or instructions that, when executed by a processor, implement the training load adjustment method as described in any one of claims 1 to 12.

16. A smart fitness device, characterized in that, include: The instrument itself; The sensing unit is used to collect motion signals; as well as, The training load adjustment device as described in claim 13, or the electronic device as described in claim 14.

Images