Method and system for generating training mode and medium

Abstract

The invention provides a method for generating a training mode. The method comprises the following steps: acquiring multi-source physiological data of a user; acquiring equipment parameters of current training equipment; inputting the multi-source physiological data and the equipment parameters into a preset training optimization model, wherein the training optimization model is used for outputting a target training parameter set matched with the physiological state of the current user; generating a training mode according to the target training parameter set; and issuing the generated training mode to training equipment for execution, or displaying, storing or pushing on a terminal interface, or simultaneously executing the two modes for a user to confirm or directly adopt, thereby realizing real-time automatic adjustment of the training intensity, ensuring active adjustment when the physiological state of the user is poor to guarantee safety, and improving the user experience. And when the state is good, effective stimulation is provided to improve the training efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent fitness and training equipment technology, and in particular to a method, system and medium for generating training methods. Background Technology

[0002] With increasing health awareness, personalized training has become a mainstream trend in the fitness industry. Existing training systems, from basic gym equipment to smart devices equipped with sensors, all attempt to provide users with a better training experience. These systems typically rely on user data such as age, weight, or limited dynamic data like average heart rate to provide preset training programs, achieving a degree of initial personalization in training.

[0003] However, existing electrical pulse training devices rely on users manually adjusting the intensity, lacking real-time awareness of physiological states. Maintaining the original intensity when the user's heart rate is too high or blood oxygen is too low can easily lead to discomfort such as dizziness and fatigue, posing a safety risk. Moreover, while existing devices can collect heart rate data, they have not established a correlation model between physiological data and training parameters, making it impossible to output personalized suggestions based on the user's real-time state. Training effectiveness depends on user experience, and novice users are prone to inappropriate intensity. A user's fatigue level, recovery level, and neural recruitment ability fluctuate continuously in a single training session or even a single training movement. Static or lagging single indicators cannot accurately reflect this complex real-time state, causing the training intensity to exceed the user's instantaneous tolerance limit or fall far below their effective stimulation threshold, resulting in inefficient training.

[0004] Therefore, there is a need for a method, system, and medium that can generate training methods that respond in real time to the user's physiological state and the device's output parameters. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, system, and medium for generating training methods that can respond in real time to the user's physiological state and device output parameters in order to solve the above problems.

[0006] Embodiments of this application provide a method for generating training methods, comprising the following steps: Acquire multi-source physiological data of the user, which is used to characterize the user's physiological endurance state at the current training moment; Obtain the device parameters of the current training device, which are used to characterize the stimulation capability of the device under the current operating conditions; The multi-source physiological data and the device parameters are input into a preset training optimization model, which is used to output a target training parameter set that matches the current user's physiological state. A training method is generated based on the target training parameter set; The generated training method is sent to the training device for execution, or displayed, stored, or pushed on the terminal interface, or both are executed simultaneously, for user confirmation or direct adoption.

[0007] In at least one embodiment of this application, the multi-source physiological data includes at least heart rate data, blood oxygen saturation data, respiratory rate data, and muscle impedance data collected from external health platforms and / or training devices, used to distinguish the physiological endurance state of the user in the resting, warm-up, peak training, or fatigue recovery phases.

[0008] In at least one embodiment of this application, the device parameters include the upper limit of the output intensity of the current training device, the range of tempo or frequency available in the current training mode, and the remaining training time quota. When generating the target training parameter set, the training optimization model uses the upper limit of output intensity and the rhythm or frequency range as device-side constraints.

[0009] In at least one embodiment of this application, the training optimization model determines the user's current physiological load level based on the multi-source physiological data; Based on the device parameters, determine the current available training intensity range of the device, and determine the target training parameter set within the intersection of the physiological load level and the available training intensity range.

[0010] In at least one embodiment of this application, the step of "generating the training method according to the target training parameter set" includes: When the multi-source physiological data indicates that the user's training needs for a certain target muscle group or target area are higher than those for other areas, a corresponding local training method is generated based on the target training parameter set.

[0011] In at least one embodiment of this application, the "local training method" specifically includes the following steps: When the target part information is received from the user, the training sub-model corresponding to the target part is called to generate a local training method based on the target part information. When no user input is received, the training optimization model autonomously determines the target area and generates the local training method based on the abnormal or deviated indicators in the multi-source physiological data.

[0012] In at least one embodiment of this application, after the generated training method is sent to the training device for execution, the method further includes the following steps: Collect real-time physiological data and actual device output parameters during the training process; This information is then fed back into the training optimization model for adaptive adjustment of subsequent training methods.

[0013] Embodiments of this application provide a system for generating training methods, applicable to any of the methods for generating training methods described above.

[0014] In at least one embodiment of this application, The data acquisition unit is used to acquire multi-source physiological data of the user to characterize the user's physiological endurance at the current training moment; The parameter acquisition unit is used to acquire the device parameters of the current training device to characterize the stimulation capability of the training device under the current operating conditions. The training optimization module is connected to the physiological data acquisition unit and the device parameter acquisition unit. It is used to input the multi-source physiological data and the device parameters into a preset training optimization model and output a target training parameter set that matches the current user's physiological state. A training method generation module, connected to the training optimization module, is used to generate a training method based on the target training parameter set; The interaction and distribution unit is connected to the training method generation module and is used to distribute the generated training method to the training device for execution, or to display, store or push it on the terminal interface, or to perform both of the above simultaneously, so that the user can confirm or directly adopt it.

[0015] Embodiments of this application provide a medium for generating training methods, applicable to any of the methods described above for generating training methods.

[0016] The method, system, and medium for generating training methods provided above have the following beneficial effects: By acquiring multi-source physiological data, the system comprehensively and dynamically captures the user's physiological endurance at the current training moment, overcoming the limitations of static or lagging single indicators.

[0017] Then, a pre-set training optimization model is used, which can intelligently integrate multi-source physiological data and device parameters to establish a dynamic mapping relationship between the two, thereby replacing manual adjustment that relies on user experience.

[0018] Finally, by outputting and executing a target training parameter set that precisely matches the current user's physiological state, the training intensity is adjusted in real time and automatically. This can proactively reduce risks to ensure safety when the user's physiological state is poor, such as when the heart rate is too high, and can also provide sufficient and effective stimulation to ensure training efficiency when the user is in a good state. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating a method for generating training patterns according to an embodiment of this application. Detailed Implementation

[0020] The embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0021] It should be noted that when a component is considered to be "connected" to another component, it can be directly connected to the other component or may also have an intervening component. When a component is considered to be "placed" on another component, it can be directly placed on the other component or may also have an intervening component. The terms "top," "bottom," "upper," "lower," "left," "right," "front," "back," and similar expressions used in this article are for illustrative purposes only.

[0022] Embodiments of this application provide a method for generating training methods, comprising the following steps: S10: Obtain the user's multi-source physiological data, which is used to characterize the user's physiological endurance state at the current training moment; S20: Obtain the device parameters of the current training device, wherein the device parameters are used to characterize the stimulation capability of the device under the current operating conditions; S30: Input the multi-source physiological data and the device parameters into a preset training optimization model, wherein the training optimization model is used to output a target training parameter set that matches the current user's physiological state; S40: Generate a training method based on the target training parameter set; S50: The generated training method is sent to the training device for execution, or displayed, stored or pushed on the terminal interface, or both of the above are executed simultaneously, for user confirmation or direct adoption.

[0023] The method, system, and medium described above for generating training methods that can respond in real time to the user's physiological state and device output parameters have the following beneficial effects: By acquiring multi-source physiological data, the system comprehensively and dynamically captures the user's physiological endurance at the current training moment, overcoming the limitations of static or lagging single indicators.

[0024] Then, a pre-set training optimization model is used, which can intelligently integrate multi-source physiological data and device parameters to establish a dynamic mapping relationship between the two, thereby replacing manual adjustment that relies on user experience.

[0025] Finally, by outputting and executing a target training parameter set that precisely matches the current user's physiological state, the training intensity is adjusted in real time and automatically. This can proactively reduce risks to ensure safety when the user's physiological state is poor, such as when the heart rate is too high, and can also provide sufficient and effective stimulation to ensure training efficiency when the user is in a good state.

[0026] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other. Example 1:

[0027] according to Figure 1 This application provides a method for generating training methods, comprising the following steps: S10: Obtain the user's multi-source physiological data, which is used to characterize the user's physiological endurance state at the current training moment; S20: Obtain the device parameters of the current training device, wherein the device parameters are used to characterize the stimulation capability of the device under the current operating conditions; S30: Input the multi-source physiological data and the device parameters into a preset training optimization model, wherein the training optimization model is used to output a target training parameter set that matches the current user's physiological state; S40: Generate a training method based on the target training parameter set; S50: The generated training method is sent to the training device for execution, or displayed, stored or pushed on the terminal interface, or both of the above are executed simultaneously, for user confirmation or direct adoption.

[0028] Specifically, in step S10, the system acquires multi-source physiological data from the user through a physiological data acquisition pathway. This multi-source physiological data can be obtained from a wearable terminal, which may be a heart rate monitor, smart clothing, a wristband-type acquisition device, a physiological monitoring module built into a training device, or through a data synchronization interface with an external health platform.

[0029] In step S20, operating parameters characterize the actual stimulus output capability of the device under the current operating conditions. By obtaining the above device parameters in this step, the constraint of "where the device can currently reach" can be fed into the model as an input of equal importance to the user's physiological state, avoiding mismatches where the user's current state allows for high-intensity stimulation, but the device cannot output due to heat dissipation, contact, or strategy limitations.

[0030] In step S30, the multi-source physiological data and the device parameters are input into a preset training optimization model. The user's current physiological load level is estimated based on the multi-source physiological data obtained in S10. The training intensity range and training rhythm range that the current device can provide are determined based on the device parameters obtained in S20. Finally, within the intersection of these two types of information, a set of target training parameters is automatically generated that does not exceed the user's immediate tolerance or the device's immediate output capability.

[0031] In step S40, the system further organizes the target training parameter set output in S30 into a combination of training instructions that the device can directly recognize and execute, or a training scheme description that the user can understand and select.

[0032] In step S50, the generated training method is sent to the training device for execution, and / or displayed, stored or pushed on the terminal interface to adapt to different usage patterns.

[0033] In one specific embodiment, the multi-source physiological data includes at least heart rate data, blood oxygen saturation data, respiratory rate data, and muscle impedance data collected from external health platforms and / or training devices, used to distinguish the user's physiological endurance state during rest, warm-up, peak training, or fatigue recovery phases.

[0034] Specifically, it should be noted that the collected heart rate data can be obtained through external health platforms such as smart bracelets, sports watches, and chest strap heart rate monitors, or through the heart rate collection module of the training device itself.

[0035] Furthermore, heart rate data is primarily used to reflect the overall load level of the cardiovascular system and is an important basis for determining whether a user has entered a high-intensity training zone.

[0036] Blood oxygen saturation data can be obtained through finger-type, ear-clip-type, or wrist-worn photoplethysmography (PPG) sensors. Blood oxygen data can reflect whether the body's oxygen supply is sufficient. At the same heart rate level, if blood oxygen decreases, it often means that the current training intensity is too high for the user or that recovery is insufficient.

[0037] Respiratory rate data can be obtained from airflow sensors on training equipment, chest strap stretch sensors, or respiratory parameters imported from external platforms. This data is used to identify whether the user is in a compensatory accelerated breathing phase. When the respiratory rate is fast but the heart rate is not yet in the high range, it often indicates that the user is just transitioning from warm-up to peak training. At this time, incremental training is more suitable than sudden increase training.

[0038] Muscle impedance data can be collected by the training device itself or by electrodes used in conjunction with the device. This data characterizes the conductivity and tissue condition of local muscles. When a muscle group is stimulated repeatedly or contracts repeatedly within a short period, its impedance will exhibit characteristic changes. This embodiment utilizes these changes in local electrical characteristics to determine whether this area needs a break or requires localized training.

[0039] Furthermore, by comprehensively judging the above four types of data at the same time, the system can divide the user's training state into at least four stages: First, the resting stage, where the heart rate is in the low range, blood oxygen is normal, respiratory rate is stable, and muscle resistance does not decrease significantly, the system can generate a normal or light-weight training mode; Second, the warm-up stage, where the heart rate rises but has not yet reached the high range, breathing begins to accelerate, and blood oxygen remains stable, the system can generate a training mode with moderate rhythm and gradual increase; Third, the peak training stage, where the heart rate is close to the user's target heart rate or the preset ratio of the maximum heart rate, the respiratory rate is high or even enters the stable high-frequency range, and if blood oxygen is still normal and muscle resistance does not show excessive fatigue, the system can generate a high-intensity or high-stimulation-density training mode; Fourth, the fatigue recovery stage, where the heart rate begins to decrease but breathing is still relatively fast, or the heart rate does not decrease significantly but muscle resistance shows fatigue, this embodiment can generate a training mode mainly based on recovery, relaxation, or local low-load stimulation, thereby avoiding the issuance of high-intensity programs before the user has recovered.

[0040] In one specific embodiment, the device parameters include the upper limit of the output intensity of the current training device, the available rhythm or frequency range of the current training mode, and the remaining training time quota. When generating the target training parameter set, the training optimization model uses the upper limit of output intensity and the rhythm or frequency range as device-side constraints.

[0041] Specifically, the upper limit of output intensity refers to the maximum intensity or maximum output capability that the device can provide in the current training mode. For example, for an electrical pulse training device, its upper limit of output intensity may refer to the maximum electrical pulse amplitude or maximum current value that the device can adjust. This parameter can be set according to the device's hardware capabilities, or it can be dynamically adjusted based on the device's current battery level, remaining consumables, and other factors.

[0042] Furthermore, by using this value as a constraint in the training and optimization model, the system can ensure that the output training intensity does not exceed the device's tolerance limit, avoiding device damage or user discomfort due to excessive intensity. Assuming the device's output intensity limit is 80%, if the training and optimization model requires the device to output 90% intensity, it will automatically adjust to 80%, ensuring the device operates within a safe range.

[0043] Furthermore, the available tempo or frequency range for training modes refers to the minimum and maximum tempo or frequency that the device can support in different training modes. If the user is in a high-intensity training state, the training optimization model may output higher frequency stimuli; while if the user is in a low-load or recovery state, the model may output lower frequency training modes. By using this range as a constraint on the device side, the system ensures that it does not generate training schemes that exceed the actual operating capabilities of the device, avoiding poor training results or safety issues due to improper device frequency settings.

[0044] Furthermore, the remaining training time quota refers to the remaining available training time for the device within the current training cycle. Many training devices may have time limitations within a certain training cycle; for example, a device may only be able to work continuously for a maximum of 30 minutes in a certain mode. In this case, the training optimization model must take this limitation into account and avoid exceeding the remaining time when generating training methods.

[0045] In summary, by simultaneously introducing multiple parameters such as the upper limit of the device's output intensity, frequency range, and remaining time quota, the device's constraints are incorporated into the training optimization model, thereby ensuring that the generated training scheme can both meet the user's physiological tolerance and make reasonable use of the device's actual output capacity.

[0046] In one specific embodiment, the training optimization model determines the user's current physiological load level based on the multi-source physiological data; Based on the device parameters, determine the current available training intensity range of the device, and determine the target training parameter set within the intersection of the physiological load level and the available training intensity range.

[0047] Specifically, the input of multi-source physiological data directly affects the training optimization model's assessment of the user's current physiological load. Multi-source physiological data typically includes the user's heart rate, blood oxygen saturation, respiratory rate, and muscle impedance data. The combination of these data can provide comprehensive and real-time feedback, characterizing the user's physiological state at the current training moment.

[0048] For example, if the heart rate is high and the breathing rate is rapid, the system may determine the user's physiological load level as "high load" or "overtraining"; while if the heart rate is normal and muscle resistance remains at a normal level, the load level can be determined as "low load" or "recovery state". This determination of physiological load level will provide a key reference for subsequent training program adjustments.

[0049] Furthermore, device parameters include the device's current maximum output intensity, adjustable frequency or tempo range, and remaining training time quota. Training devices typically have a performance limit, and the system uses these device parameters to determine the maximum training intensity and intensity range that the device can currently provide.

[0050] By analyzing these device parameters, the training optimization model can accurately understand the device's output capabilities and use these capabilities as an upper limit for training intensity to avoid overuse of the device.

[0051] Furthermore, the core of the training optimization model lies in its ability to generate a target set of training parameters within the intersection of the user's physiological load level and the available training intensity range of the device. Specifically, the training optimization model will combine the user's physiological load level, such as low load, medium load, and high load, with the device's current available intensity range, such as output intensity, frequency range, and duration quota, to determine a reasonable range of training parameters.

[0052] In summary, the system can dynamically adjust the training plan based on the user's real-time physiological state and the device's current output capacity, ensuring that the training intensity matches the user's ability. Device capacity, as a constraint, prevents users from overloading the device or training when its output capacity is insufficient, ensuring the reliability and safety of the device during training.

[0053] In one specific embodiment, the step of "generating the training method based on the target training parameter set" includes: When the multi-source physiological data indicates that the user's training needs for a certain target muscle group or target area are higher than those for other areas, a corresponding local training method is generated based on the target training parameter set.

[0054] Specifically, physiological data such as the user's heart rate, respiratory rate, and muscle resistance will change during training. If a target muscle group, such as the rectus abdominis, quadriceps, or calf muscles, shows high fatigue or physiological demand, it indicates that the muscle group needs additional attention and training. At this time, the training optimization model will automatically identify this demand and generate a local training method for that specific area based on the existing target training parameter set.

[0055] For example, when a user is performing leg training, the system detects increased muscle resistance in the quadriceps, indicating that this area is under high load and the heart rate is approaching 70% of the user's maximum heart rate. Simultaneously, the breathing rate is rapid, indicating that the user is under a high training load. At this point, the training optimization model can adjust the training intensity and duration of the quadriceps based on the target training parameter set previously generated by the system, and generate a more focused local training plan. This could include increasing the electrical stimulation intensity of the quadriceps, increasing the load, and appropriately extending the training time to ensure the quadriceps are adequately trained and to avoid over-fatigue.

[0056] In this step, it should be noted that the generation mechanism for local training methods can be implemented in two ways: User input driven: When the system receives information about the target training area manually selected by the user, such as through touchscreen input on the device, voice recognition, or a smart terminal app, the model will directly call the training sub-model corresponding to that area based on the user's input, generating a personalized training method for that area. For example, when the user selects "left rectus abdominis training," the system will automatically generate training parameters suitable for that area and prioritize allocating training resources and intensity to the rectus abdominis.

[0057] Automatic recognition-driven: When the system detects that the physiological load or training demand of a certain part of the user's body is higher than that of other parts, the system can autonomously determine that the part needs more training and automatically select that part to generate a local training mode without user input. For example, when it detects that the left quadriceps muscle shows a faster fatigue trend than other parts during training, the system can automatically adjust the training strategy and prioritize the allocation of training intensity to that part.

[0058] This allows the system to automatically adjust training parameters, such as intensity, duration, and frequency, based on the specific needs of a user's muscle groups or areas. By optimizing the training intensity for local muscle groups, the system can adjust training in real time based on individual user differences and current condition, ensuring that each muscle group receives precise and effective training stimulation, thereby improving training results and promoting muscle growth or recovery. When physiological data such as muscle resistance, heart rate, and respiratory rate in a certain area indicate that the area is in a state of fatigue or critical load, the system can reduce the training burden on that area and instead optimize the training intensity for other areas, avoiding safety hazards caused by overtraining and ensuring the user's health during training.

[0059] In one specific embodiment, the "local training method" specifically includes the following steps: When the target part information is received from the user, the training sub-model corresponding to the target part is called to generate a local training method based on the target part information. When no user input is received, the training optimization model autonomously determines the target area and generates the local training method based on the abnormal or deviated indicators in the multi-source physiological data.

[0060] Specifically, it should be noted that users can select specific muscle groups or areas they wish to train via the device's touchscreen or the selection interface of the mobile app, such as "left biceps," "right quadriceps," or "rectus abdominis." The target area information entered by the user can directly guide the system to call up the corresponding training sub-model, thereby generating a customized training plan for that area.

[0061] Furthermore, the training sub-models are pre-built in a previously constructed training database or model library, and are designed for the training needs and physiological characteristics of different muscle groups. Each training sub-model generates corresponding training parameters based on the specific physiological characteristics of the muscle group, such as muscle volume, strength requirements, and recovery speed. For different muscle groups such as the biceps brachii, quadriceps femoris, and rectus abdominis, the output parameters of the training model, such as intensity, rhythm, duration, and training mode, are different.

[0062] Furthermore, if the system does not receive explicit target area information from the user, it will automatically determine the target areas requiring focused training based on abnormal or deviating-from-preset threshold indicators in multi-source physiological data, using a training optimization model. At this point, the system monitors the user's physiological changes, such as muscle resistance data, heart rate changes, and respiratory rate changes, to identify which muscle groups are currently showing high training needs or signs of fatigue.

[0063] For example, during a full-body workout, if the system detects a sharp increase in quadriceps resistance and a high heart rate, while the resistance and heart rate of other muscle groups, such as the upper limbs, are within the normal range, the system will automatically select the quadriceps as the target area and generate a localized training approach for it. In this case, the system may output parameters that are more suitable for the quadriceps, such as reducing intensity, increasing recovery time, and adjusting the pace, to avoid over-fatigue.

[0064] The technical solution implemented in this embodiment can dynamically generate local training methods based on user input and changes in real-time physiological data, solving the problem of traditional training methods relying too heavily on user input or static data. By combining the user's physiological state and device state, this embodiment can ensure that the training plan is not only individualized but also intelligently adjusted based on real-time feedback during the training process.

[0065] In one specific embodiment, after the generated training method is sent to the training device for execution, the method further includes the following steps: Collect real-time physiological data and actual device output parameters during the training process; This information is then fed back into the training optimization model for adaptive adjustment of subsequent training methods.

[0066] Specifically, during training, the system continuously monitors the user's physiological state and the actual operating parameters of the device. The collected real-time physiological data includes, but is not limited to: heart rate, blood oxygen saturation, respiratory rate, and muscle impedance data. Actual device output parameters are also collected in this step, specifically including the actual intensity value output by the device, the actual training rhythm or frequency, and the remaining training time. Furthermore, the collected real-time physiological data and actual device output parameters are fed back to the training optimization model. This feedback process allows the training optimization model to adaptively adjust based on the current training progress, ensuring that the training method remains consistent with the user's real-time state and optimizing the training plan in a timely manner. When the system detects that the user's heart rate exceeds the set safety range or blood oxygen saturation drops to a warning level, the training optimization model can automatically adjust the training intensity, reduce current output, or shorten training duration to prevent overtraining and reduce training risks. Conversely, if the system finds that the user's physiological data, such as heart rate and respiratory rate, indicates good training adaptation, it can appropriately increase the training intensity or extend the training duration to improve training effectiveness.

[0067] In addition, after comparing the actual intensity, frequency and other parameters of the device output with the preset training target, if the device output is inconsistent with the target, the training optimization model can also adjust the subsequent training mode, such as adjusting the output intensity, changing the training frequency, or calibrating the device in subsequent training to ensure the consistency and accuracy of training. Example 2:

[0068] This embodiment provides a system for generating training methods, which is applied to any of the methods for generating training methods described above. The system for generating training methods specifically includes: a data acquisition unit, a parameter acquisition unit, a training optimization module, a training method generation module, and an interaction and distribution unit.

[0069] The data acquisition unit is used to acquire multi-source physiological data from the user to characterize the user's physiological state at the current training moment. This data is then promptly transmitted to other modules of the system for subsequent analysis and processing. Through this multi-source physiological data, the system can more accurately determine whether the user is currently in a resting, warm-up, peak training, or recovery phase, thereby generating a more precise training plan.

[0070] The parameter acquisition unit is used to acquire the device parameters of the current training device to characterize the stimulation capability of the training device under the current operating conditions, so that the system can generate a training plan based on the actual capability limitations of the device, avoiding overload training and training tasks that the device cannot perform.

[0071] The training optimization module, connected to the physiological data acquisition unit and the device parameter acquisition unit, is used to input the multi-source physiological data and the device parameters into a preset training optimization model, and output a target training parameter set that matches the current user's physiological state. This maximizes the training effect while ensuring user safety, and ensures that the generated training method does not exceed the user's physiological tolerance or the device's output capability.

[0072] The training method generation module, connected to the training optimization module, is used to generate training methods based on the target training parameter set, thereby flexibly adjusting the training methods according to the needs and training objectives of different users to ensure maximum training effect.

[0073] The interaction and distribution unit is connected to the training method generation module and is used to distribute the generated training method to the training device for execution, or to display, store or push it on the terminal interface, or to perform both of the above simultaneously, so that the user can confirm or directly adopt it. Through this unit, the user can easily obtain the training plan or conduct training through the guidance of the smart device, reducing the workload of manually adjusting the device settings and improving the convenience and automation level of training. Example 3:

[0074] This embodiment provides a medium for generating training methods, applicable to any of the methods described above. The medium can be a memory card, USB flash drive, external hard drive, optical disc, ROM, RAM, or a downloadable program package. The medium stores a computer program, which, when executed by a processor, implements the steps of any of the aforementioned methods for generating training methods. By writing the algorithm into the medium, the detection method of this invention can be deployed in various types of terminal devices, such as external health platforms, wearable training devices, home rehabilitation testing instruments, and gym assessment terminals. Further details will not be elaborated upon here.

[0075] Therefore, the method, system, and medium described above for generating training methods that can respond in real time to the user's physiological state and device output parameters have the following beneficial effects: By acquiring multi-source physiological data, the system comprehensively and dynamically captures the user's physiological endurance at the current training moment, overcoming the limitations of static or lagging single indicators.

[0076] Then, a pre-set training optimization model is used, which can intelligently integrate multi-source physiological data and device parameters to establish a dynamic mapping relationship between the two, thereby replacing manual adjustment that relies on user experience.

[0077] Finally, by outputting and executing a target training parameter set that precisely matches the current user's physiological state, the training intensity is adjusted in real time and automatically. This can proactively reduce risks to ensure safety when the user's physiological state is poor, such as when the heart rate is too high, and can also provide sufficient and effective stimulation to ensure training efficiency when the user is in a good state.

[0078] The above description is merely an embodiment of this application. It should be noted that those skilled in the art can make improvements without departing from the inventive concept of this application, but these improvements all fall within the protection scope of this application.

Claims

1. A method for generating training patterns, characterized in that, Includes the following steps: Acquire multi-source physiological data of the user, which is used to characterize the user's physiological endurance state at the current training moment; Obtain the device parameters of the current training device, which are used to characterize the stimulation capability of the device under the current operating conditions; The multi-source physiological data and the device parameters are input into a preset training optimization model, which is used to output a target training parameter set that matches the current user's physiological state. A training method is generated based on the target training parameter set; The generated training method is sent to the training device for execution, or displayed, stored, or pushed on the terminal interface, or both are executed simultaneously, for user confirmation or direct adoption.

2. The method for generating training methods according to claim 1, characterized in that, The multi-source physiological data includes at least heart rate data, blood oxygen saturation data, respiratory rate data, and muscle impedance data collected from external health platforms and / or training devices, used to distinguish the user's physiological endurance state during rest, warm-up, peak training, or fatigue recovery phases.

3. The method for generating training methods according to claim 1, characterized in that, The device parameters include the maximum output intensity of the current training device, the available rhythm or frequency range for the current training mode, and the remaining training time quota. When generating the target training parameter set, the training optimization model uses the upper limit of output intensity and the rhythm or frequency range as device-side constraints.

4. The method for generating training methods according to claim 1, characterized in that, The training optimization model determines the user's current physiological load level based on the multi-source physiological data; Based on the device parameters, determine the current available training intensity range of the device, and determine the target training parameter set within the intersection of the physiological load level and the available training intensity range.

5. The method for generating training methods according to claim 1, characterized in that, The step of "generating the training method based on the target training parameter set" includes: When the multi-source physiological data indicates that the user's training needs for a certain target muscle group or target area are higher than those for other areas, a corresponding local training method is generated based on the target training parameter set.

6. The method for generating training methods according to claim 5, characterized in that, The "local training method" specifically includes the following steps: When the target part information is received from the user, the training sub-model corresponding to the target part is called to generate a local training method based on the target part information. When no user input is received, the training optimization model autonomously determines the target area and generates the local training method based on the abnormal or deviated indicators in the multi-source physiological data.

7. The method for generating training methods according to claim 1, characterized in that, After the generated training method is sent to the training device for execution, the following steps are also included: Collect real-time physiological data and actual device output parameters during the training process; This information is then fed back into the training optimization model for adaptive adjustment of subsequent training methods.

8. A system for generating training methods, characterized in that, The method applied to a generation training method as described in any one of claims 1-7.

9. The system for generating training methods according to claim 8, characterized in that, The data acquisition unit is used to acquire multi-source physiological data of the user to characterize the user's physiological endurance at the current training moment; The parameter acquisition unit is used to acquire the device parameters of the current training device to characterize the stimulation capability of the training device under the current operating conditions. The training optimization module is connected to the physiological data acquisition unit and the device parameter acquisition unit. It is used to input the multi-source physiological data and the device parameters into a preset training optimization model and output a target training parameter set that matches the current user's physiological state. A training method generation module, connected to the training optimization module, is used to generate a training method based on the target training parameter set; The interaction and distribution unit is connected to the training method generation module and is used to distribute the generated training method to the training device for execution, or to display, store or push it on the terminal interface, or to perform both of the above simultaneously, so that the user can confirm or directly adopt it.

10. A medium for generating training methods, characterized in that, The method applied to a generation training method as described in any one of claims 1-7.

Images