Intelligent resistance training device and method

Abstract

The invention provides intelligent resistance training equipment and method. The method comprises the following steps: synchronously collecting resistance signals of a neck and lower limbs when a user executes a collaborative resistance action; determining force application delay time between the neck and the lower limbs according to the resistance signals of the neck and the lower limbs; according to the angular velocity component of the neck of the user and the anti-resistance signal of the neck, determining a posture-force coupling coefficient when the user executes the collaborative anti-resistance action; determining a load adjustment coefficient of a lower limb target load based on the force application delay time and the posture-force coupling coefficient in combination with a preset load adjustment rule; and adjusting the lower limb load applied by the equipment according to the load adjustment coefficient, and generating prompt information containing posture coordination abnormity at the same time. By adopting the scheme of the invention, the training load conforming to the current coordination capability of the user can be dynamically allocated.

Description

Technical Field

[0001] This application relates to the field of intelligent resistance training technology, and more specifically, to an intelligent resistance training device and method. Background Technology

[0002] Intelligent resistance training refers to intelligent strength training systems that transform the static and discrete load application process in traditional resistance training into a quantifiable, interactive, and adaptable intelligent system based on mechanical sensing, adaptive control, and real-time data analysis technologies. This system utilizes dynamic load adjustment, motion trajectory tracking, and biofeedback intervention to achieve precise perception and adaptive control of the user's muscle strength level, neural adaptation, and movement patterns.

[0003] Traditional intelligent resistance training relies heavily on independent measurement of the strength of individual muscle groups or on training based on preset fixed load ratios. This makes it difficult to assess and respond in real-time and quantitatively to the timing and quality of neuromuscular synergy among multiple muscle groups, such as the neck and lower limbs. This results in a severe disconnect between the training load and the user's real-time motor coordination. For example, traditional methods may set the load based solely on the maximum force generated by the lower limbs, ignoring the significant delay in force exertion from the neck compared to the lower limbs. This delay causes a misalignment in the timing of force output in the early stages of the movement, or ignores abnormal angular velocity and ineffective compensation caused by poor posture control in the neck. Under this load, although the user can complete the surface range of motion, it actually reinforces uncoordinated, high-risk erroneous force exertion patterns, failing to achieve the core training goal of improving neuromuscular synergy. Therefore, how to dynamically allocate training loads that match the user's current coordination ability has become a challenge for the industry. Summary of the Invention

[0004] This application provides an intelligent resistance training device and method that can dynamically allocate training loads that match the user's current coordination ability.

[0005] In a first aspect, this application provides an adaptive load distribution method for synchronous resistance training, used by an intelligent resistance training device to adaptively distribute loads to the user's neck and lower limbs. The method includes the following steps: Synchronously collect resistance signals from the neck and lower limbs when the user performs coordinated resistance movements; The force delay time between the neck and lower limbs is determined based on the resistance signals from the neck and lower limbs. The attitude-force coupling coefficient when the user performs cooperative resistive movements is determined by the angular velocity component of the user's neck and the resistance signal of the neck. The load adjustment coefficient for the target load on the lower limbs is determined based on the force delay time and the attitude-force coupling coefficient, combined with a preset load adjustment rule. The lower limb load applied by the device is adjusted according to the load adjustment coefficient, and a prompt message containing abnormal posture coordination is generated at the same time.

[0006] In some embodiments, determining the force delay time between the neck and lower limbs based on the resistance signals from the neck and lower limbs specifically includes: The moment of force exertion in the neck and lower limbs is detected from the resistance signals of the neck and lower limbs; The original force delay for each user's exertion is determined by the force initiation time of the neck and lower limbs. The multiple original force delays generated by the continuous action cycle are aggregated to obtain the force delay time between the neck and lower limbs.

[0007] In some embodiments, determining the attitude-force coupling coefficient when a user performs a coordinated resistive action by using the angular velocity component of the user's neck and the neck's resistance signal specifically includes: Extract the neck angular velocity component signal when the user performs cooperative resistance movements; The neck resistance signal and the neck angular velocity component signal are time-series aligned, and effective signal segments corresponding to the same force exertion cycle are extracted. Based on the effective signal segment, determine the signal cross-correlation information between the neck resistance signal and the neck angular velocity component signal; The attitude-force coupling coefficient when the user performs a cooperative resistance action is determined based on the mutual information of the signals.

[0008] In some embodiments, determining the load adjustment coefficient for the lower limb target load based on the force exertion delay time and the attitude-force coupling coefficient in conjunction with a preset load adjustment rule specifically includes: Obtain the preset load adjustment rules; The corresponding first adjustment factor is determined based on the power exertion delay time and the preset load adjustment rule; The corresponding second adjustment factor is determined based on the attitude-force coupling coefficient and the preset load adjustment rule; The first adjustment factor and the second adjustment factor are combined to obtain the load adjustment coefficient of the target load of the lower limb.

[0009] In some embodiments, adjusting the lower limb load applied by the device according to the load adjustment coefficient, and simultaneously generating a prompt message containing abnormal posture coordination, specifically includes: The target load for the user's lower limbs is determined based on the load adjustment coefficient and the user's lower limb baseline load. The intelligent resistance training device is controlled to adjust the applied lower limb load to the target lower limb load; Based on the force exertion delay time and the attitude-force coupling coefficient, a coordination anomaly is determined, and then a prompt message containing the specific anomaly type is generated.

[0010] In some embodiments, the resistance signal refers to a digital signal sequence showing the real-time force change of a specified muscle group (neck or lower limb) against a preset resistance of the device when the user performs a synergistic resistance action.

[0011] In some embodiments, the intelligent resistance training device is an electromechanical integrated training instrument.

[0012] Secondly, this application provides an intelligent resistance training device, which includes an adaptive load allocation unit, the adaptive load allocation unit comprising: The acquisition module is used to simultaneously acquire resistance signals from the neck and lower limbs when the user performs coordinated resistance movements; The processing module is used to determine the force delay time between the neck and lower limbs based on the resistance signals from the neck and lower limbs. The processing module is also used to determine the attitude-force coupling coefficient when the user performs a coordinated resistance action by using the angular velocity component of the user's neck and the resistance signal of the neck. The processing module is also used to determine the load adjustment coefficient of the target load of the lower limbs based on the force delay time and the attitude-force coupling coefficient combined with the preset load adjustment rules; The execution module is used to adjust the lower limb load applied by the device according to the load adjustment coefficient, and at the same time generate a prompt message containing abnormal posture coordination.

[0013] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the adaptive load allocation method for synchronous resistive training described above.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the adaptive load allocation method for synchronous resistive training described above.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The intelligent resistance training device and method provided in this application determine the force exertion delay time by synchronously collecting resistance signals from the neck and lower limbs. This transforms the abstract and difficult-to-describe problem of motor coordination into a precisely measurable temporal difference. The quantitative indicator of delay time provides a direct and objective data basis for identifying force exertion timing misalignments at the neuromuscular control level. This process, by aligning and analyzing continuous motion signals on the time axis, achieves a precise assessment of the neural drive efficiency and coordination timing of the user's core and lower limb muscle groups. It transforms the subjective experience of sensory incoordination into the interventionable physical problem of delay, providing a key temporal coordination criterion for subsequent load adjustment. Subsequently, based on this force exertion delay time and combined with the posture-force coupling coefficient reflecting the quality of neck posture control, the adjustment coefficient of the target load for the lower limbs is jointly determined through preset load adjustment rules. This process can perform multi-dimensional fusion and comprehensive decision-making between discrete temporal anomaly indicators (delay time) and spatial posture control indicators (coupling coefficient), mapping the two different types of identified motor coordination defects into a unified... The system provides executable load modulation commands. Through the core decision-making logic of load adjustment rules, it transforms the two objectives of avoiding the reinforcement of error patterns and providing effective training stimuli from external training principles into internal control objectives of real-time resistance adjustment of the driving equipment. It utilizes delay time indicators to prevent the application of overload during periods of temporal misalignment, thus mitigating the risk of injury. Simultaneously, it uses coupling coefficient indicators to proactively reduce the load during postural instability to guide correct force application, thereby providing a dual constraint for dynamic load allocation that combines safety correction and synergistic guidance. Finally, it adjusts the applied lower limb load in real time based on the load adjustment coefficient and generates prompts simultaneously. This application, through dynamically modulated load, forces users to complete actions within a mechanical environment adapted to their current control capabilities. This avoids inducing or solidifying compensatory patterns due to excessive load and ensures that the load is sufficient to form effective synergistic training stimuli. This makes the mechanical input of each training action no longer fixed or blind, effectively suppressing the reinforcement of error patterns and low training efficiency caused by a disconnect between load and coordination. In summary, this scheme can dynamically allocate training loads that match the user's current coordination capabilities. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an adaptive load allocation method for synchronous resistive training according to some embodiments of this application; Figure 2 This is a flowchart illustrating the process of determining the force delay time according to some embodiments of this application; Figure 3 This is a schematic flowchart illustrating the determination of attitude-force coupling coefficients according to some embodiments of this application; Figure 4This is a schematic diagram of the structure of an adaptive load distribution unit according to some embodiments of this application; Figure 5 This is an internal structural diagram of a computer device that implements an adaptive load allocation method for synchronous resistive training according to some embodiments of this application. Detailed Implementation

[0017] To better understand the technical solutions in this embodiment, the technical solutions in this embodiment will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0018] refer to Figure 1 The figure is a flowchart illustrating an adaptive load allocation method for synchronous resistance training according to some embodiments of this application. The adaptive load allocation method for synchronous resistance training mainly includes the following steps: In step 101, resistance signals from the neck and lower limbs are simultaneously acquired when the user performs coordinated resistance movements.

[0019] In specific implementation, multiple high-precision force sensing units and a unified timing control module integrated into the intelligent resistance training device can be used to synchronously collect the resistance signals of the neck and lower limbs when the user performs coordinated resistance movements. Specifically, a first strain gauge force sensor is rigidly connected to the mechanical transmission path of the neck support and force application module of the intelligent resistance training device to detect the resistance force generated when the neck extends or flexes; a second strain gauge force sensor is rigidly connected to the mechanical transmission path of the lower limb pedaling or pushing module to detect the resistance force generated when the lower limbs extend; when the user begins to perform a standard coordinated resistance movement cycle (e.g., starting from the ready posture, simultaneously performing neck extension and lower limb extension), the device's main control unit sends a hardware synchronization trigger signal, which simultaneously activates the data acquisition circuits of the first and second strain gauge force sensors, and... Using the same preset sampling frequency, the original analog voltage signals sensed by the two sensors are converted into digital signals. To achieve strict synchronization, the hardware synchronization trigger can be generated by the timer interrupt of the embedded system or a dedicated synchronization clock chip, ensuring that the timestamps of the data collected by the two channels are completely aligned at the system clock level. Subsequently, the two digital force signals acquired synchronously are preprocessed, including: first, each signal is independently zero-point calibrated to eliminate the initial bias of the sensor, and then a low-pass digital filter (such as a Butterworth filter) with a cutoff frequency of 30Hz is used to filter out high-frequency noise and power frequency interference introduced by equipment vibration and muscle tremors. Finally, two digital force signal sequences that are strictly aligned in time and have undergone noise reduction are output, which serve as the neck resistance signal characterizing the instantaneous force intensity of the user's neck and the lower limb resistance signal characterizing the instantaneous force intensity of the lower limbs, respectively.

[0020] It should be noted that the resistance signal mentioned in this application refers to a digital signal sequence of real-time force value changes of a specified muscle group (neck or lower limb) against the preset resistance of the device when the user performs a coordinated resistance movement; the intelligent resistance training device is an electromechanical integrated training instrument, equipped with a neck and lower limb training module with independently adjustable resistance source, integrated multi-axis sensors and processor; the synchronous acquisition refers to ensuring, through hardware or underlying software mechanisms, that data sampling from sensors at different physical locations begins at the same absolute time point and has the exact same time interval, which is a prerequisite for subsequent accurate calculation of force delay time.

[0021] In step 102, the force delay time between the neck and lower limbs is determined based on the resistance signals of the neck and lower limbs.

[0022] In some embodiments, reference Figure 2 As shown in the figure, this is a schematic flowchart illustrating the determination of the force delay time according to some embodiments of this application. The determination of the force delay time between the neck and lower limbs based on the resistance signals of the neck and lower limbs can be achieved through the following steps: First, in step 1021, the moment when the force is first applied to the neck and lower limbs is detected from the resistance signals of the neck and lower limbs; Then, in step 1022, the original force delay for each user's force exertion is determined by the force exertion start time of the neck and lower limbs; Finally, in step 1023, the multiple original force delays generated by the continuous action cycle are aggregated to obtain the force delay time between the neck and lower limbs.

[0023] In specific implementation, detecting the force initiation time of the neck and lower limbs from the resistance signals can be achieved in the following way: For example, for the neck resistance signals and lower limb resistance signals that have been synchronously acquired and preprocessed, the force initiation point is detected separately. Specifically, for each force signal, the baseline level and statistical distribution characteristics of the signal force value are first calculated when the user is in a ready posture but has not yet started to exert force; then, a sliding time window of preset length is used to traverse the entire signal sequence, and the average rate of change of the signal value relative to time within the window is calculated in real time as the instantaneous force initiation time at that moment. Force rate estimation; the system presets a dynamic threshold judgment condition based on the baseline statistical characteristics and a minimum stable duration for confirming the effectiveness of force exertion; when the instantaneous force rate estimate of the signal first continuously exceeds the dynamic threshold and the duration of the exceeding state reaches the minimum stable duration, the "first exceeding" moment is determined to be the effective force exertion starting point of the corresponding muscle group in the current synergistic resistance movement cycle; the time point determined from the neck resistance signal is taken as the neck force exertion starting moment, and the time point determined from the lower limb resistance signal is taken as the lower limb force exertion starting moment.

[0024] It should be noted that the force initiation time mentioned in this application refers to the precise time point at which the user-specified muscle group begins to effectively resist the resistance of the external equipment, as identified from the resistance signal. This is used to provide a unified action initiation benchmark for analyzing the neuromuscular activation timing relationship between different muscle groups.

[0025] In specific implementation, determining the original force exertion delay for each user's force exertion by using the force exertion start times of the neck and lower limbs can be achieved in the following way: for example, within one coordinated resistance action cycle, the absolute timestamp value of the force exertion start time of the lower limbs is subtracted from the absolute timestamp value of the force exertion start time of the neck, and the resulting time difference is calculated as the original force exertion delay of this coordinated action; in other embodiments, other methods can also be used, which are not limited here.

[0026] It should be noted that the original force exertion delay mentioned in this application refers to the time difference between the starting time of force exertion of the lower limb muscle group and the starting time of force exertion of the neck muscle group in a single synergistic resistance movement. It is used to directly quantify the degree of deviation in the neural drive timing of force exertion in different parts within a specific movement cycle.

[0027] In specific implementation, the aggregation of multiple original force delays generated by continuous action cycles to obtain the force delay time between the neck and lower limbs can be achieved in the following way: For example, aggregating a series of original force delays generated by the user during continuous execution of multiple coordinated resistance action cycles; firstly, using an outlier removal method based on statistical distribution to clean the original force delay sequence, for example, calculating the first quartile and the third quartile of the sequence, and filtering out data points whose values ​​are lower than the first quartile minus a certain multiple of the interquartile range or higher than the third quartile plus the same multiple of the interquartile range as outliers; then, calculating the central tendency value of the effective original force delay sequence obtained after cleaning using the arithmetic mean or median, and outputting the calculation result as the final force delay time; in other embodiments, other methods can also be used, which are not limited here.

[0028] It should be noted that the force exertion delay time mentioned in this application refers to the stable characterization value obtained after aggregating the original force exertion delays of multiple consecutive action cycles. It is used to comprehensively evaluate the overall performance level of the neuromuscular system in terms of temporal coordination when the user exerts force in coordination with the neck and lower limbs in the current state.

[0029] In step 103, the attitude-force coupling coefficient when the user performs cooperative resistance actions is determined by the angular velocity component of the user's neck and the resistance signal of the neck.

[0030] In some embodiments, determining the attitude-force coupling coefficient when a user performs a cooperative resistive action by using the angular velocity component of the user's neck and the neck's resistance signal can be achieved through the following steps: Extract the neck angular velocity component signal when the user performs cooperative resistance movements; The neck resistance signal and the neck angular velocity component signal are time-series aligned, and effective signal segments corresponding to the same force exertion cycle are extracted. Based on the effective signal segment, determine the signal cross-correlation information between the neck resistance signal and the neck angular velocity component signal; The attitude-force coupling coefficient when the user performs a cooperative resistance action is determined based on the mutual information of the signals.

[0031] In practice, an inertial measurement unit integrated into a user-worn neck resistance module or head-mounted device can be used to collect raw triaxial angular velocity data of the user's neck during coordinated resistance movements in real time, using the same hardware synchronization clock as the force signal acquisition. Then, based on a preset primary neck motion plane (e.g., the sagittal plane for neck extension and flexion movements), the single-axis angular velocity component most relevant to the coordinated resistance movement is extracted from the raw triaxial angular velocity data. Finally, this angular velocity component signal undergoes preprocessing consistent with the force signal, including zero-bias calibration and low-pass digital filtering with the same cutoff frequency to eliminate sensor noise and motion artifacts, thereby obtaining a preprocessed neck angular velocity component signal comparable to the neck resistance signal.

[0032] It should be noted that the neck angular velocity component signal mentioned in this application refers to a physical quantity signal extracted from neck inertial measurement data that reflects the speed of neck joint rotation in a specific plane of motion, and is used to characterize the dynamic process of neck posture changes when a user performs resistance movements.

[0033] In specific implementation, the time series alignment of the neck resistance signal and the neck angular velocity component signal, and the extraction of effective signal segments corresponding to the same force exertion cycle, can be achieved in the following way: for example, aligning the neck angular velocity component signal and the neck resistance signal on the time axis; then, based on the neck force exertion start time detected from the neck resistance signal, and the time when the signal amplitude falls back to below the dynamic threshold used in the force exertion start point detection, a time window representing the entire process of a single neck force exertion is jointly determined; according to this time window, data segments with exactly the same start and end times are synchronously extracted from the aligned two signals, and these two data segments are jointly defined as effective signal segments.

[0034] It should be noted that the effective signal segment mentioned in this application refers to the force signal and angular velocity signal data segment that is strictly aligned in time and extracted, corresponding to the same complete neck force exertion cycle. This is used to ensure that the subsequent coupling analysis is carried out within the same physiological event and the same time span, and to guarantee the validity and comparability of the analysis results.

[0035] In specific implementation, determining the signal cross-correlation information between the neck resistance signal and the neck angular velocity component signal based on the effective signal segment can be achieved in the following way: For example, for the two signals contained in the effective signal segment, the signal cross-correlation information can be obtained by calculating the time-domain cross-correlation function; the specific process is as follows: slide the neck angular velocity component signal segment relative to the neck resistance signal segment on the time axis, with the sliding range covering a preset time shift interval; for each specific time shift, calculate the product of the values ​​of each sampling point of the two signals in the overlapping part, and sum all the product results to obtain the cross-correlation value under that time shift; traverse all time shifts within the preset time shift interval to obtain a series of cross-correlation values, and the sequence composed of these values ​​is the signal cross-correlation information. In other embodiments, other methods can also be used, which are not limited here.

[0036] It should be noted that the signal cross-correlation information mentioned in this application refers to the calculated sequence values ​​used to describe the similarity or correlation between the neck resistance signal and the neck angular velocity component signal at different time offsets, which are used to reveal the temporal matching pattern and correlation degree between changes in force intensity and changes in motion posture.

[0037] For specific implementation, refer to Figure 3 As shown in the figure, this is a flowchart illustrating the determination of the attitude-force coupling coefficient according to some embodiments of this application. The determination of the attitude-force coupling coefficient when the user performs a cooperative resistance action based on the signal cross-correlation information can be achieved in the following way, for example: obtaining the maximum value in the signal cross-correlation information; normalizing the maximum value, where the normalization denominator is the product of the standard deviation of the neck resistance signal and the standard deviation of the neck angular velocity component signal in the effective signal segment;

[0038] It should be noted that the posture-force coupling coefficient described in this application is a normalized scalar value used to comprehensively quantify the overall coordination and efficiency between the user's neck muscle exertion (force) and neck joint movement (posture) in cooperative resistance movements.

[0039] In step 104, the load adjustment coefficient of the target load of the lower limb is determined based on the force delay time and the attitude-force coupling coefficient in combination with the preset load adjustment rules.

[0040] In some embodiments, determining the load adjustment coefficient for the lower limb target load based on the force exertion delay time and the attitude-force coupling coefficient in combination with a preset load adjustment rule can be achieved through the following steps: Obtain the preset load adjustment rules; The corresponding first adjustment factor is determined based on the power exertion delay time and the preset load adjustment rule; The corresponding second adjustment factor is determined based on the attitude-force coupling coefficient and the preset load adjustment rule; The first adjustment factor and the second adjustment factor are combined to obtain the load adjustment coefficient of the target load of the lower limb.

[0041] It should be noted that the preset load adjustment rule defines the mapping relationship between the force delay time and the first adjustment factor, and between the attitude-force coupling coefficient and the second adjustment factor. This includes evaluation parameters for the force delay time and evaluation parameters for the attitude-force coupling coefficient. The evaluation parameters for the force delay time include at least an ideal delay time reference value for evaluating the quality of coordination, and a function or mapping table defining the correspondence between the degree to which the force delay time deviates from the reference value and the first adjustment factor. The evaluation parameters for the attitude-force coupling coefficient include at least an ideal coupling coefficient reference value for evaluating the quality of attitude control, and a function or mapping table defining the correspondence between the degree to which the attitude-force coupling coefficient deviates from the reference value and the second adjustment factor. The design principle of the function or mapping table is that when the force delay time deviates from the ideal value or the attitude-force coupling coefficient deviates from the ideal value, the mapped adjustment factor value is smaller, indicating that the load needs to be reduced.

[0042] In specific implementation, determining the corresponding first adjustment factor based on the power-on delay time and the preset load adjustment rule can be achieved in the following way: for example, comparing the power-on delay time with the ideal delay time reference value in the load adjustment rule and calculating its deviation degree; then, using this deviation degree as input, querying the function or mapping table defined in the rule; based on the specific value of the power-on delay time deviating from the ideal reference value, obtaining a value between 0 and 1 through the function calculation or table lookup, and using this value as the first adjustment factor; wherein, the closer the power-on delay time is to the ideal reference value, the closer the first adjustment factor is to 1; in another embodiment, determining the corresponding first adjustment factor based on the power-on delay time and the preset load adjustment rule can be achieved in the following way, namely: inputting the power-on delay time into a preset fuzzy logic evaluator; the fuzzy logic evaluator predefines multiple parameters describing the delay degree. The system assigns several fuzzy linguistic variables (such as "extremely short delay", "relatively short delay", "moderate delay", "relatively long delay", and "extremely long delay") and their corresponding membership functions. Based on the specific value of the exertion delay time, the system calculates the membership degree of each fuzzy linguistic variable. Then, it calls a preset fuzzy rule base (e.g., "if the delay is extremely short, the adjustment factor is excellent; if the delay is relatively short, the adjustment factor is good; if the delay is moderate, the adjustment factor is moderate") to derive a fuzzy conclusion about the adjustment factor level through fuzzy reasoning. Finally, the fuzzy conclusion is defuzzified and converted into a precise value between 0 and 1, which serves as the first adjustment factor. The domain of the fuzzy linguistic variables, the shape parameters of the membership functions, and the fuzzy rule base can all be dynamically configured and personalized according to the user's training stage, rehabilitation progress, or individual coordination baseline, thereby making the load adjustment more closely match the user's real-time ability and progress curve.

[0043] It should be noted that the first adjustment factor in this application is a value between 0 and 1, determined based on the degree of deviation between the force exertion delay time and the ideal coordination standard. It is used to map the user's performance in force exertion timing coordination as a component basis for adjusting the training load.

[0044] In specific implementation, determining the corresponding second adjustment factor based on the attitude-force coupling coefficient and the preset load adjustment rule can be achieved in the following way: for example, comparing the attitude-force coupling coefficient with the ideal coupling coefficient reference value in the load adjustment rule; then, based on the difference between the coefficient and the ideal reference value, querying the corresponding function or mapping table defined in the rule; based on the specific direction and magnitude of the attitude-force coupling coefficient deviating from the ideal reference value, calculating or looking up a value between 0 and 1 through the function, and using this value as the second adjustment factor; wherein, the closer the attitude-force coupling coefficient is to the ideal reference value, the closer the second adjustment factor is to 1.

[0045] It should be noted that the second adjustment factor in this application is a value between 0 and 1, determined based on the degree of deviation between the posture-force coupling coefficient and the ideal coordination standard. It is used to map the user's performance in posture control and force coordination as another component for adjusting the training load.

[0046] In specific implementation, the first adjustment factor and the second adjustment factor are combined to obtain the load adjustment coefficient of the lower limb target load. This can be achieved in the following way, for example: weighted fusion calculation is performed on the first adjustment factor and the second adjustment factor; the weighted fusion calculation is to multiply the first adjustment factor by a preset first weight, multiply the second adjustment factor by a preset second weight, and then add the two product results. The sum is the load adjustment coefficient of the lower limb target load; wherein, the sum of the first weight and the second weight is 1, and its specific value can be pre-configured according to whether the training focuses on improving the coordination of force exertion timing or the coordination of posture control. This application does not limit this.

[0047] It should be noted that the load adjustment coefficient mentioned in this application is a final adjustment parameter obtained by combining the first adjustment factor and the second adjustment factor. Its function is to transform the evaluation results of the user's real-time temporal coordination and posture control coordination into a unified scaling ratio for dynamically adjusting the target load of the lower limbs.

[0048] In step 105, the lower limb load applied by the device is adjusted according to the load adjustment coefficient, and a prompt message containing abnormal posture coordination is generated.

[0049] In some embodiments, adjusting the lower limb load applied by the device according to the load adjustment coefficient, while generating a prompt message containing abnormal posture coordination, can be achieved through the following steps: The target load for the user's lower limbs is determined based on the load adjustment coefficient and the user's lower limb baseline load. The intelligent resistance training device is controlled to adjust the applied lower limb load to the target lower limb load; Based on the force exertion delay time and the attitude-force coupling coefficient, a coordination anomaly is determined, and then a prompt message containing the specific anomaly type is generated.

[0050] In practice, the target load for a user's lower limbs can be determined by combining the load adjustment coefficient with the user's lower limb baseline load in the following way: for example, the user's preset lower limb baseline load value is read from the user configuration of the intelligent resistance training device. This value is determined according to the user's strength level or training plan. Then, the lower limb baseline load value is multiplied by the load adjustment coefficient, and the result of the multiplication is used as the target load for the lower limbs to be applied.

[0051] It should be noted that the lower limb target load mentioned in this application refers to the optimal mechanical resistance value that the intelligent resistance training device should apply to the user's lower limbs in the current training cycle, based on the user's individual basic load capacity and a load adjustment coefficient calculated in real time, so as to achieve adaptive training that matches the load with the user's real-time coordination ability.

[0052] In practice, controlling the intelligent resistance training device to adjust the applied lower limb load to the target lower limb load can be achieved in the following way: for example, generating a corresponding control command based on the target lower limb load value to drive the power actuator in the lower limb load application module of the intelligent resistance training device; the power actuator is, for example, a servo motor or a proportional valve, which responds to the control command and adjusts its output resistance torque or hydraulic resistance, thereby adjusting the actual mechanical load applied to the user's lower limb to the target lower limb load value in real time.

[0053] In specific implementation, coordination anomalies can be determined based on the force delay time and the attitude-force coupling coefficient, and then prompt information containing specific anomaly types can be generated. This can be achieved in the following way: comparing the force delay time with a preset delay anomaly threshold, and simultaneously comparing the attitude-force coupling coefficient with a preset coupling anomaly threshold; wherein, the delay anomaly threshold is used to define the acceptable range of force timing synchronization, and the coupling anomaly threshold is used to define the acceptable level of attitude control coordination; if the force delay time is greater than the delay anomaly threshold, a force timing anomaly is determined to exist; if the attitude-force coupling coefficient is less than the coupling anomaly threshold, an attitude control anomaly is determined to exist; based on the above determination results, a text or voice prompt describing the specific anomaly type, such as "force timing asynchrony," "unstable neck posture control," or a combination thereof, is generated and output through the human-computer interaction interface of the intelligent resistance training device; in another embodiment... The method of judging coordination anomalies based on the force delay time and the posture-force coupling coefficient, and then generating prompt information containing specific anomaly types, can be implemented in the following way: A coordination anomaly diagnosis matrix is ​​constructed. This matrix combines the intervals to which the force delay time belongs, such as "ahead of time," "ideal range," "mild lag," and "severe lag," with the intervals to which the posture-force coupling coefficient belongs, such as "strong coupling," "moderate coupling," "weak coupling," and "decoupling," to form multiple anomaly modes. The system maps the currently calculated force delay time and posture-force coupling coefficient to specific anomaly mode cells in the diagnosis matrix. Each cell is associated with a predefined, more descriptive and instructive prompt information template. For example, if mapped to a cell combining "severe lag" and "weak coupling," the generated prompt information might be "Detected: Lower limb force initiation is significantly delayed, and neck force and movement coordination are insufficient."

[0054] Furthermore, in another aspect of this application, in some embodiments, this application provides an intelligent resistance training device, including an adaptive load distribution unit, with reference to... Figure 4 The figure is a schematic diagram of the structure of an adaptive load allocation unit according to some embodiments of this application. The adaptive load allocation unit 200 includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described below: The acquisition module 201 in this application is mainly used to synchronously acquire the resistance signals of the neck and lower limbs when the user performs coordinated resistance movements; Processing module 202, in this application, is mainly used to determine the force delay time between the neck and lower limbs based on the resistance signals of the neck and lower limbs; In addition, the processing module 202 in this application is also used to determine the attitude-force coupling coefficient when the user performs cooperative resistance actions by using the angular velocity component of the user's neck and the resistance signal of the neck. In addition, the processing module 202 in this application is also used to determine the load adjustment coefficient of the target load of the lower limb based on the force delay time and the attitude-force coupling coefficient combined with the preset load adjustment rules; The execution module 203 in this application is mainly used to adjust the lower limb load applied by the device according to the load adjustment coefficient, and at the same time generate a prompt message containing abnormal posture coordination.

[0055] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, the processor being configured to acquire the code and execute the above-described adaptive load allocation method for synchronous resistive training.

[0056] In some embodiments, reference Figure 5 This figure is an internal structural diagram of a computer device implementing an adaptive load allocation method for synchronous resistive training according to some embodiments of this application. The adaptive load allocation method for synchronous resistive training in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0057] The processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more adaptive load allocation methods for controlling the execution of synchronous resistive training in this application.

[0058] The communication bus 302 is used to transmit information between the aforementioned components.

[0059] Memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 303 may exist independently and be connected to processor 301 via communication bus 302. Memory 303 may also be integrated with processor 301.

[0060] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiments, the adaptive load allocation method for synchronous impedance training can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0061] Communication interface 304 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0062] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core processor or a multi-core processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0063] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device may be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0064] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described adaptive load allocation method for synchronous resistance training.

[0065] In summary, the intelligent resistance training device and method disclosed in this application firstly collects resistance signals from the neck and lower limbs when the user performs coordinated resistance movements; determines the force delay time between the neck and lower limbs based on the resistance signals; determines the posture-force coupling coefficient when the user performs coordinated resistance movements by using the angular velocity component of the user's neck and the resistance signal of the neck; determines the load adjustment coefficient of the target load of the lower limbs based on the force delay time and the posture-force coupling coefficient combined with a preset load adjustment rule; adjusts the load on the lower limbs applied by the device according to the load adjustment coefficient, and simultaneously generates a prompt message containing abnormal posture coordination; and can dynamically allocate a training load that matches the user's current coordination ability.

[0066] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0067] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An adaptive load distribution method for synchronous resistance training, used by an intelligent resistance training device to adaptively distribute loads to a user's neck and lower limbs, characterized in that, The method includes the following steps: Synchronously collect resistance signals from the neck and lower limbs when the user performs coordinated resistance movements; The force delay time between the neck and lower limbs is determined based on the resistance signals from the neck and lower limbs. The attitude-force coupling coefficient when the user performs cooperative resistive movements is determined by the angular velocity component of the user's neck and the resistance signal of the neck. The load adjustment coefficient for the target load on the lower limbs is determined based on the force delay time and the attitude-force coupling coefficient, combined with a preset load adjustment rule. The lower limb load applied by the device is adjusted according to the load adjustment coefficient, and a prompt message containing abnormal posture coordination is generated at the same time.

2. The method as described in claim 1, characterized in that, Determining the force exertion delay time between the neck and lower limbs based on the resistance signals from the neck and lower limbs specifically includes: The moment of force exertion in the neck and lower limbs is detected from the resistance signals of the neck and lower limbs; The original force delay for each user's exertion is determined by the force initiation time of the neck and lower limbs. The multiple original force delays generated by the continuous action cycle are aggregated to obtain the force delay time between the neck and lower limbs.

3. The method as described in claim 1, characterized in that, The attitude-force coupling coefficient for a user performing a coordinated resistive action is determined by using the angular velocity component of the user's neck and the neck's resistance signal. Specifically, this includes: Extract the neck angular velocity component signal when the user performs cooperative resistance movements; The neck resistance signal and the neck angular velocity component signal are time-series aligned, and effective signal segments corresponding to the same force exertion cycle are extracted. Based on the effective signal segment, determine the signal cross-correlation information between the neck resistance signal and the neck angular velocity component signal; The attitude-force coupling coefficient when the user performs a cooperative resistance action is determined based on the mutual information of the signals.

4. The method as described in claim 1, characterized in that, The load adjustment coefficient for determining the target load on the lower limbs based on the force exertion delay time and the posture-force coupling coefficient, combined with a preset load adjustment rule, specifically includes: Obtain the preset load adjustment rules; The corresponding first adjustment factor is determined based on the power exertion delay time and the preset load adjustment rule; The corresponding second adjustment factor is determined based on the attitude-force coupling coefficient and the preset load adjustment rule; The first adjustment factor and the second adjustment factor are combined to obtain the load adjustment coefficient of the target load of the lower limb.

5. The method as described in claim 1, characterized in that, The lower limb load applied by the device is adjusted according to the load adjustment coefficient, and a prompt message containing abnormal posture coordination is generated, specifically including: The target load for the user's lower limbs is determined based on the load adjustment coefficient and the user's lower limb baseline load. The intelligent resistance training device is controlled to adjust the applied lower limb load to the target lower limb load; Based on the force exertion delay time and the attitude-force coupling coefficient, a coordination anomaly is determined, and then a prompt message containing the specific anomaly type is generated.

6. The method as described in claim 1, wherein the resistance signal refers to a digital signal sequence of real-time force changes of a specified muscle group resisting a preset resistance of the device when the user performs a synergistic resistance action.

7. The method as described in claim 1, wherein the intelligent resistance training device is an electromechanical integrated training instrument.

8. An intelligent resistance training device, comprising an adaptive load distribution unit, characterized in that, The adaptive load allocation unit includes: The acquisition module is used to simultaneously acquire resistance signals from the neck and lower limbs when the user performs coordinated resistance movements; The processing module is used to determine the force delay time between the neck and lower limbs based on the resistance signals from the neck and lower limbs. The processing module is also used to determine the attitude-force coupling coefficient when the user performs a coordinated resistance action by using the angular velocity component of the user's neck and the resistance signal of the neck. The processing module is also used to determine the load adjustment coefficient of the target load of the lower limbs based on the force delay time and the attitude-force coupling coefficient combined with the preset load adjustment rules; The execution module is used to adjust the lower limb load applied by the device according to the load adjustment coefficient, and at the same time generate a prompt message containing abnormal posture coordination.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the adaptive load allocation method for synchronous resistive training as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the adaptive load allocation method for synchronous resistive training as described in any one of claims 1 to 7.

Images