Personalized training load adjusting method and system based on dynamic physiological data

Abstract

The invention is suitable for the technical field of personalized exercise training and load management, and provides a personalized training load adjusting method and system based on dynamic physiological data. The method comprises the following steps: acquiring a posture deviation value change trend of each reference athlete along with the change of a training frequency and adjustment data which is autonomously implemented in training and belongs to a training load adjustment item set, and carrying out coupling degree calculation on the adjustment data and the posture standard value change trend, and determining the adjustment item with the highest coupling degree as the corresponding optimal adjustment item. According to the method, the grassland condition comprehensive index is constructed and combined with the posture deviation value, so that the comprehensive threshold influencing posture stability is scientifically recognized; on the basis, comparison athletes showing different adaptive capacities under the same or approximate grassland condition are screened out, the reference athletes with the training frequency in the lowest range are further extracted, and the correlation between the environmental condition and posture correction is revealed from multiple dimensions.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of personalized training and load management, and particularly relates to a personalized training load adjustment method and system based on dynamic physiological data. BACKGROUND

[0002] In the prior art, personalized load management mainly relies on the collection of physiological indicators of athletes and conventional training feedback. For example, through heart rate, respiratory rate, blood lactate concentration or muscle fatigue degree data, combined with common training plan adjustment models, the individualization of training intensity and recovery cycle is realized. This kind of method can reflect the physical state of athletes to a certain extent, but more focuses on the overall physiological load evaluation after exercise, and lacks dynamic consideration of specific training site environmental factors. Especially in grassland sports projects such as golf, football or rugby, the posture stability and action standardization of athletes are often significantly affected by objective environmental conditions such as lawn humidity, slope, density, etc., and the existing technology mostly does not include these complex environmental conditions in the load adjustment model.

[0003] On the basis of existing research, some technical solutions attempt to monitor the deviation of sports posture through video action recognition or sensor collection, thereby assisting in training correction. However, these solutions often only use action deviation as an independent indicator, and fail to establish a dynamic coupling relationship combined with environmental conditions. In other words, the existing technology more stays at the level of "detection and feedback", and cannot identify the rules of action deviation under specific environmental conditions, nor can it distinguish the different recovery efficiencies exhibited by athletes due to individual adaptive capacity differences. As a result, training load adjustment still relies on experience or uniform adjustment standards, and lacks personalized adjustment schemes for specific sports environments.

[0004] Therefore, the core deficiency of the current technology is that it fails to associate environmental parameters, action deviation and autonomous adjustment behavior, and lacks a mechanism that can dynamically identify key environmental thresholds and screen out experience that can be learned by different athletes' adaptive capacity. SUMMARY

[0005] The purpose of the present application is to provide a personalized training load adjustment method and system based on dynamic physiological data, aiming to solve the problems raised in the background art.

[0006] The present application is implemented as follows: a personalized training load adjustment method based on dynamic physiological data, the method comprising: collecting a database of target training grasslands, and obtaining a grassland condition comprehensive index and a posture deviation value at each training position when a test athlete trains along a predetermined training route; extracting training samples of a plurality of comparative athletes from the database, the training samples being of the comparative athletes who have the posture deviation value continuously greater than the posture deviation threshold value when the grass condition comprehensive index exceeds the comprehensive threshold value and when the posture deviation value continuously greater than the posture deviation threshold value occurs near the comprehensive threshold value on the predetermined training route; analyzing the training samples, screening a plurality of comparative athletes whose training frequency is in the lowest range during the posture deviation value returning to not more than the posture deviation threshold value, and determining the comparative athletes as reference athletes; obtaining the posture deviation value change trend of each reference athlete with the training frequency and adjustment data of the reference athlete which is voluntarily implemented in the training and belongs to the training load adjustment project set, coupling the adjustment data and the posture standard value change trend, and determining the adjustment project with the highest coupling degree as the corresponding optimal adjustment project; summarizing the optimal adjustment projects of different reference athletes, and generating a personalized training load adjustment scheme for the tested athlete.

[0007] As a further limitation of the technical scheme of the embodiment of the application, the grass condition comprehensive index is calculated by the parameters of the turf water content, the grass surface slope, the grass leaf coverage density and the ground surface rebound characteristics corresponding to different training positions on the predetermined training route; wherein the numerical value of the grass condition comprehensive index is used to represent the comprehensive influence of the grass condition on the athlete's posture stability, and the greater the numerical value is, the more significant the influence on the posture stability is.

[0008] As a further limitation of the technical scheme of the embodiment of the application, the posture deviation value refers to the deviation degree of the athlete from the preset standard posture when training at each training position.

[0009] As a further limitation of the technical scheme of the embodiment of the application, when the grass condition comprehensive index exceeds the comprehensive threshold value and the posture deviation value continuously greater than the posture deviation threshold value, the step of extracting a plurality of training samples of comparative athletes from the database includes: arranging the grass condition comprehensive indexes of each training position of the predetermined training route in the order from small to large and generating a comprehensive index change trend, and determining whether there is a threshold point in the change trend, so that after exceeding the threshold point, the posture deviation value of the tested athlete corresponding to each training position is greater than the posture deviation threshold value; if the threshold point exists, the threshold point is set as the comprehensive threshold value, and a plurality of training samples of comparative athletes are selected from the database, the training samples being of the comparative athletes who have the posture deviation value continuously greater than the posture deviation threshold value after the comprehensive threshold value on the same predetermined training route.

[0010] As a further limitation of the technical scheme of the embodiment of the present application, the step of analyzing the training samples and screening a plurality of comparative athletes whose training frequency is in the lowest range in the process of restoring the posture deviation value to not more than the posture deviation threshold value to determine the reference athletes comprises: analyzing the training samples of each comparative athlete, determining the training frequency of each comparative athlete when the posture deviation value is restored from being greater than the posture deviation threshold value to not more than the threshold value in the training process, and screening a plurality of comparative athletes whose training frequency is in the lowest range from the comparative athletes; determining the comparative athletes screened as the reference athletes.

[0011] As a further limitation of the technical scheme of the embodiment of the present application, the training load adjustment item set comprises: swing plane angle adjustment, down rod rhythm adjustment, stand distance adjustment, center of gravity offset range control, and lower limb force balance ratio adjustment, which are quantifiable training adjustment items.

[0012] As a further limitation of the technical scheme of the embodiment of the present application, the step of obtaining the posture deviation value change trend of each reference athlete with the training frequency change and the adjustment data of the reference athlete autonomously implemented in the training and belonging to the training load adjustment item set, and coupling the adjustment data and the posture standard value change trend to determine the adjustment item with the highest coupling degree as the corresponding best adjustment item comprises: obtaining the posture deviation value change trend of each reference athlete at the comprehensive threshold point corresponding to the training position with the training frequency change, and at least one adjustment data of the reference athlete autonomously implemented in the training process and belonging to the training load adjustment item set; calculating the change proportion of the adjustment data at each training frequency relative to the previous training frequency, and coupling the adjustment data change proportion corresponding to each training frequency and the posture deviation value change proportion; determining the adjustment item with the highest coupling degree as the best adjustment item of the corresponding reference athlete.

[0013] As a further limitation of the technical scheme of the embodiment of the present application, when the best adjustment items of different reference athletes are summarized, if the best adjustment items of two or more reference athletes are the same, the best adjustment item with the lowest training frequency in the process of restoring the posture deviation value to not more than the posture deviation threshold value is selected as the preferred item.

[0014] The personalized training load adjustment system based on dynamic physiological data comprises: a data acquisition module for acquiring the database of the target training grassland, and acquiring the grassland condition comprehensive index and the posture deviation value at each training position when the tested athlete trains along the predetermined training route; a sample extraction module configured to extract, from the database, a plurality of training samples of the comparative athletes when the grass condition comprehensive index exceeds the comprehensive threshold value and the posture deviation value lasts for more than the posture deviation threshold value on the predetermined training route and near the comprehensive threshold value; a reference screening module configured to analyze the training samples, screen a plurality of comparative athletes whose training frequency is in a lowest range in the process of restoring the posture deviation value to not more than the posture deviation threshold value, and determine the comparative athletes as reference athletes; a coupling analysis module configured to obtain a posture deviation value change trend of each reference athlete with the training frequency and adjustment data of the reference athlete in the training, the adjustment data being self-implemented and belonging to a training load adjustment project set, perform coupling degree calculation on the adjustment data and the posture standard value change trend, and determine an adjustment project with the highest coupling degree as a corresponding optimal adjustment project; a scheme generation module configured to summarize the optimal adjustment projects of the different reference athletes, and generate an individualized training load adjustment scheme for the tested athlete.

[0015] As a further limitation of the technical scheme of the embodiment of the present application, the grass condition comprehensive index is obtained by comprehensively calculating the parameters of the water content of the lawn, the grass surface slope, the grass leaf coverage density and the ground surface rebound characteristics corresponding to different training positions on the predetermined training route; wherein the numerical value of the grass condition comprehensive index is used to represent the comprehensive influence of the grass condition on the athlete's posture stability, and the larger the numerical value is, the more significant the influence on the posture stability is.

[0016] Compared with the prior art, the present application has the following beneficial effects: The present application proposes an individualized training load adjustment method and system based on dynamic physiological data, aiming at the problem that the posture stability is easily affected in the grass sports environment. By constructing a grass condition comprehensive index and combining a posture deviation value, a comprehensive threshold value affecting the posture stability is scientifically identified. On this basis, comparative athletes showing different adaptive capacities under the same or similar grass conditions are screened out, and reference athletes whose training frequency is in a lowest range are further extracted, so as to reveal the correlation between the environmental conditions and the posture correction from multiple dimensions. Further, through coupling degree calculation, the self-adjustment data of the reference athletes are closely corresponding to the posture recovery process, the optimal adjustment project with the most key is determined, and finally an individualized training load adjustment scheme suitable for the tested athlete is generated.

[0017] The present application innovatively realizes the closed-loop correlation of environmental parameters, individual motion deviation and self-adjustment behavior, can improve the training efficiency and the pertinence of posture correction while ensuring the scientificity and quantifiability, is especially suitable for sports such as golf which need to continuously fine-tune the posture, and has the application potential of being popularized to other grass sports. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of the method provided in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the comprehensive threshold and comparison sample extraction process in the method provided in this embodiment of the invention. Figure 3 The method provided in this embodiment of the invention refers to the athlete screening flowchart; Figure 4 This is a flowchart illustrating the process of determining the optimal adjustment item in the method provided by the embodiments of the present invention; Figure 5 The application architecture diagram of the system provided in the embodiments of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0021] Specifically, a personalized training load adjustment method based on dynamic physiological data includes the following steps: Step S100: Collect the database of the target training grassland, and obtain the comprehensive index of grassland conditions and posture deviation value of each training location when the test subject trains along the predetermined training route.

[0022] The comprehensive index of grass conditions is calculated by combining parameters such as grass moisture content, grass slope, grass cover density, and ground rebound characteristics at different training locations along the predetermined training route. The value of the comprehensive index of grass conditions is used to characterize the overall impact of grass conditions on the athlete's postural stability; the larger the value, the more significant the impact on postural stability.

[0023] The posture deviation value refers to the degree of deviation of an athlete from a preset standard posture when training in various training positions.

[0024] In this embodiment of the invention, the target training grass refers to a specific grass area used for athletes to practice techniques and adjust movements. This area can be a standard fairway, practice green, or a specially designed grass training field on a golf course. The grass should be able to ensure that athletes can continuously perform training activities such as hitting or swinging the ball under different surface conditions. This invention is preferably applied to golf because a significant characteristic of this sport is that the athletes' movements are relatively slow-paced, allowing for continuous observation and gradual adjustment of body posture during training, thus facilitating the real-time collection of dynamic physiological data and the quantitative assessment of movement deviations.

[0025] The predetermined training route refers to a training path that is artificially planned and measured on the target training grass. It consists of multiple fixed training locations, each with clear spatial coordinates and measurement points, used to collect multi-point data on the comprehensive index of grass conditions and posture deviation values. This predetermined training route can be laid out along the fairway of a golf hole, or it can be a series of training points set in the practice area according to specific distances, slopes, and shot requirements, thereby ensuring the comparability and repeatability of data from different training locations.

[0026] The comprehensive index of grassland conditions is based on the combined influence of the grassland physical environment on the stability of athletes' postures. Its calculation method involves weighting or performing functional calculations on parameters such as grass moisture content, grass slope, grass cover density, and surface resilience at each training location along a predetermined training route to form a comprehensive index that quantifies the overall condition of the grassland.

[0027] Lawn moisture content can be measured using a portable soil moisture sensor or an infrared moisture meter; grass slope can be collected using an electronic level or a laser rangefinder; grass cover density can be calculated using high-resolution image analysis or image recognition algorithms; and surface rebound characteristics can be determined using a pressure sensor or a ball rebound test device.

[0028] These measurement methods are all mature and feasible environmental monitoring technologies in the existing field, and have been widely used in sports field management and agricultural monitoring. Therefore, they can be reliably used for the calculation of the grassland condition index.

[0029] The source of the posture deviation value lies in the degree of deviation between the human posture and an individualized standard. The method for obtaining this value is as follows: During the athlete's training, existing mature technologies such as 3D motion capture systems, inertial measurement units (IMUs), force platforms, or optical motion analysis systems are used to collect dynamic physiological and kinematic parameters in real time, including the athlete's key joint angles, center of gravity trajectory, swing path, and movement stability. These parameters are then compared with a personalized standard posture model established for the athlete to calculate the athlete's posture deviation value at each training position. This standard posture is not a uniform, universal posture, but rather a personalized standard posture constructed based on the athlete's physical characteristics, habitual movements, and past best technical movement data to ensure that the deviation accurately reflects the athlete's optimal posture requirements.

[0030] The database is used to centrally store and manage the aforementioned collected data. Its sources include real-time environmental parameter data collected on-site, dynamic physiological data uploaded by motion capture equipment, athletes' historical training records, and derived data such as the comprehensive grass condition index and posture deviation values ​​generated from these data. Specifically, the database includes, but is not limited to: raw measurement data of grass moisture content at each training location, grass slope measurement data, grass cover density image data, ground rebound characteristic detection data, athletes' joint angle data, center of gravity position data, limb acceleration data, swing path data, ground reaction force data, and records of athletes' training time and frequency.

[0031] The database can be deployed on a local server or a cloud data platform and synchronized in real time with the field acquisition equipment via wireless or wired data transmission interfaces to ensure the accuracy and real-time nature of subsequent analysis and adjustment scheme generation.

[0032] Furthermore, the personalized training load adjustment method based on dynamic physiological data also includes the following steps: Step S200: When the grass condition comprehensive index exceeds the comprehensive threshold and the posture deviation value is continuously greater than the posture deviation threshold, extract training samples from the database of several comparative athletes whose posture deviation values ​​are continuously greater than the posture deviation threshold when they are on a predetermined training route and near the comprehensive threshold.

[0033] Specifically, Figure 2 The flowchart for the comprehensive threshold and comparison sample extraction is shown.

[0034] Specifically, when the comprehensive index of grassland conditions exceeds the comprehensive threshold and the posture deviation value is consistently greater than the posture deviation threshold, the following steps are taken to extract training samples from the database of several comparative athletes who exhibited consistently greater posture deviation values ​​than the posture deviation threshold while on a predetermined training route and near the comprehensive threshold: Step S201: Arrange the comprehensive index of grass conditions at each training location of the predetermined training route in ascending order and generate a comprehensive index change trend. Determine whether there is a threshold point in the change trend, such that after exceeding the threshold point, the posture deviation value of the tested athlete at each training location is greater than the posture deviation threshold. Step S202: If the threshold point exists, set it as the comprehensive threshold, and select several training samples from the database of comparative athletes who are on the same predetermined training route and whose posture deviation value continues to be greater than the posture deviation threshold after passing near the comprehensive threshold.

[0035] In this embodiment of the invention, the verification objective of step S201 is to identify key inflection points, i.e., comprehensive threshold points, that have a significant impact on postural stability in continuously distributed grass condition data. By arranging the comprehensive index of grass conditions at each training location along a predetermined training route in ascending order and generating a trend of comprehensive index changes, the overall relationship between grass conditions and postural deviation can be visually observed, thereby determining whether there exists a threshold point: when the comprehensive index of grass conditions exceeds this point, the postural deviation value of the tested athlete at each training location is likely to remain greater than the postural deviation threshold. It should be noted that this threshold point does not require the postural deviation value corresponding to all training locations to be strictly greater than the postural deviation threshold. In the actual sports environment, occasional deviations or exceptions at individual locations are allowed, and the overall trend is used as the basis for judgment. The comprehensive threshold point determined in this way can serve as a critical reference for judging whether grass conditions have a significant adverse impact on postural stability, providing a data basis for subsequent sample extraction.

[0036] In step S202, after the comprehensive threshold is determined, control athletes and their training samples are selected from the database who exhibit posture deviation values ​​consistently exceeding the posture deviation threshold on the same predetermined training route. This selection aims to ensure that these control athletes and the tested athletes are comparable in terms of grass conditions; that is, both exhibit similar posture deviations under the same or similar comprehensive grass condition indices. This provides a consistent environmental basis and reliable reference data for subsequent selection of control athletes and training load adjustment analysis.

[0037] Furthermore, the personalized training load adjustment method based on dynamic physiological data also includes the following steps: Step S300: Analyze the training samples and select several control athletes whose training frequency is the lowest during the recovery of posture deviation value to no more than the posture deviation threshold. These control athletes are then identified as reference athletes.

[0038] Specifically, Figure 3 The flowchart for the selection of reference athletes is shown.

[0039] The process of analyzing training samples and selecting a number of control participants whose training frequency was lowest during the recovery of their posture deviation value to within the posture deviation threshold includes the following steps: Step S301: Analyze the training samples of each comparison athlete, determine the training frequency when the posture deviation value is restored from greater than the posture deviation threshold to no more than the threshold during the training process, and select several comparison athletes whose training frequency is in the lowest range. Step S302: The selected comparison athletes are identified as reference athletes.

[0040] In this embodiment of the invention, step S301 is implemented as follows: The system first sequentially analyzes the training samples corresponding to each comparison athlete, extracts their training data near the comprehensive threshold, and focuses on identifying the complete process of their posture deviation value recovering from being greater than the posture deviation threshold to not exceeding the threshold. During this process, the posture deviation value of each training frequency is continuously compared, and the total training frequency required to achieve posture recovery is recorded, which is used as a quantitative indicator to measure its adaptive efficiency. Subsequently, the system sorts the recovery frequency data of all comparison athletes and selects several comparison athletes with the lowest training frequency as the preferred results of the training sample selection.

[0041] The purpose of this screening step is to further identify individuals with strong adaptive capabilities from a control group of athletes who have been identified as exhibiting postural deviation characteristics under similarly unfavorable grass conditions. These individuals are able to recover to a stable postural state with the fewest training sessions, and their training data can provide a more efficient and targeted reference for subsequently generating personalized training load adjustment programs.

[0042] Based on the screening criteria in step S200, it can be seen that the comparative athletes entering this step are not directly related to the tested athletes in terms of personal fitness level, age, or other profiles. However, they share a common characteristic: under grassy conditions near the comprehensive threshold, they all experienced postural deviations exceeding their own preset thresholds, exhibiting differences in recovery speed solely due to their varying adaptability. Step S300 can identify athletes with stronger recovery capabilities under unfavorable grassy conditions. Because these reference athletes are unrelated to the tested athletes' profiles, their training adjustments during recovery have more universal reference value and can provide truly effective adaptive solutions for the tested athletes.

[0043] Meanwhile, this correction and recovery process is closely related to the sports type background described in step S100. This invention is preferentially applied to golf because the relatively gentle rhythm of golf movements allows athletes to continuously observe and gradually adjust their body posture during training. This sport characteristic is highly compatible with the gradual and gentle posture correction process, ensuring that the adaptive mechanisms reflected by the selected reference athletes can be gradually absorbed and applied by the tested athletes, thereby improving the accuracy and practicality of personalized training load adjustment programs.

[0044] Furthermore, the personalized training load adjustment method based on dynamic physiological data also includes the following steps: Step S400: Obtain the trend of posture deviation values ​​of each reference athlete as training frequency changes and the adjustment data of the athletes that they autonomously implement during training and belong to the training load adjustment item set. Calculate the coupling degree between the adjustment data and the trend of posture standard value changes, and determine the adjustment item with the highest coupling degree as the corresponding best adjustment item.

[0045] The training load adjustment items include quantifiable training adjustment items such as swing plane angle adjustment, downswing rhythm adjustment, stance distance adjustment, center of gravity offset range control, and lower limb force balance ratio adjustment.

[0046] Specifically, Figure 4 A flowchart for determining the optimal adjustment project is shown.

[0047] The process of obtaining the trend of postural deviation values ​​of each reference athlete as training frequency changes, and the adjustment data of their self-implemented training load adjustment items, and calculating the coupling degree between the adjustment data and the trend of postural standard values, to determine the adjustment item with the highest coupling degree as the corresponding optimal adjustment item, specifically includes the following steps: Step S401: Obtain the trend of the posture deviation value of each reference athlete at the training position corresponding to the comprehensive threshold point with the training frequency, as well as at least one adjustment data that the athlete autonomously implements during the training process and belongs to the training load adjustment item set. Step S402: Calculate the change ratio of the adjustment data at each training frequency relative to the previous training frequency, and calculate the coupling degree between the change ratio of the adjustment data corresponding to each training frequency and the change ratio of the posture deviation value. Step S403: The adjustment item with the highest coupling degree is determined as the best adjustment item for the corresponding reference athlete.

[0048] In this embodiment of the invention, step S400 achieves a cleverly universal design by comprehensively analyzing multiple reference athletes within the lowest training frequency range. The aforementioned steps have ensured that these reference athletes and the tested athletes are comparable in grass conditions, while remaining unrelated in terms of their individual profiles. Therefore, their adaptive behavior when facing similar grass conditions can serve as a reliable, universal reference. Through the analysis in step S400, it can be discovered that each reference athlete may have a specific, optimal adjustment item that is most crucial to their recovery effect during the process of restoring postural stability, thus providing the tested athletes with multi-dimensional and personalized adjustment references.

[0049] The training load adjustment program, in addition to including swing plane angle adjustment, downswing rhythm adjustment, stance adjustment, center of gravity shift range control, and lower limb force balance ratio adjustment, may also include other programs such as impact point consistency practice, single swing set or rest interval adjustment, clubhead loft selection, and shoe sole friction coefficient level adjustment. These programs all share common characteristics: first, they can be adjusted autonomously by athletes during training without immediate forced intervention from external equipment; second, the degree of adjustment can be quantified, such as angle values, frequency values, torque ratios, or time intervals, and therefore can be recorded in real time and used for data calculation.

[0050] In the specific implementation process, step S401 first calls the original data of the reference athlete at the corresponding training position at the comprehensive threshold point in the database. Using mature acquisition technologies such as a 3D motion capture system, inertial measurement unit (IMU), and pressure distribution sensor, the trend of the athlete's posture deviation value changing with training frequency is obtained. Simultaneously, at least one adjustment data point autonomously implemented during training and belonging to the training load adjustment item set is extracted. This adjustment data is obtained through real-time sensing recording and video image recognition, which can accurately quantify parameter changes in each training session.

[0051] Step S402 calculates the percentage change of each adjustment data point relative to the previous training frequency at each training frequency on the data processing platform, and then calculates the coupling degree between these percentage changes and the corresponding percentage change in posture deviation. The coupling degree calculation can employ algorithms such as statistical correlation coefficients, mutual information, or time-series dynamic coupling analysis to achieve a bidirectional quantitative correlation between changes in adjustment data and improvements in posture stability. The unique aspect of this coupling degree calculation is that it cleverly links the changing trends of the actively adjusted data of the training items and the natural recovery process of posture deviation—two different dimensions—thereby revealing the key regulatory factors that most effectively drive posture stability.

[0052] Finally, in step S403, the adjustment item with the highest coupling degree is determined as the optimal adjustment item for the corresponding reference athlete. The reason for using the highest coupling degree as the selection criterion is that a higher coupling degree indicates the most significant synchronous relationship and causal link between the change in this adjustment item and the posture recovery process, directly reflecting the dominant role of this adjustment behavior in posture correction. Therefore, this optimal adjustment item can be considered the most effective adaptive strategy for the reference athlete when facing unfavorable grass conditions, providing the tested athlete with a highly targeted training load adjustment reference.

[0053] Furthermore, the personalized training load adjustment method based on dynamic physiological data also includes the following steps: Step S500: Summarize the best adjustment items for different reference athletes and generate a personalized training load adjustment plan for the tested athlete.

[0054] When summarizing the best adjustment items for different reference athletes, if two or more reference athletes have the same best adjustment item, the best adjustment item with the lowest training frequency in the process of restoring the posture deviation value to no more than the posture deviation threshold shall be selected as the preferred option.

[0055] In this embodiment of the invention, the purpose of step S500 is to comprehensively summarize the optimal adjustment items of multiple reference athletes determined in the aforementioned steps, and finally form a personalized training load adjustment plan for the tested athlete. In this way, the tested athlete no longer relies solely on single self-experimentation, but can directly utilize the actual experience of reference athletes who have shown strong adaptability under similar grass conditions to quickly obtain multiple verified training adjustment directions.

[0056] During the data aggregation process, multiple reference athletes may exhibit the same optimal adjustment item. In such cases, this invention proposes selecting the optimal adjustment item that requires the lowest training frequency to restore the postural deviation value to within the postural deviation threshold. The advantage of this approach is that it ensures the selected adjustment item not only significantly improves postural stability but also achieves its effect with minimal training cost, demonstrating the highest training efficiency and application value. For the tested athletes, this means maximizing postural correction benefits within limited training time and intensity, avoiding overtraining and wasted training resources.

[0057] The personalized training load adjustment plan is applied as follows: the system converts the summarized results into an executable training plan, which includes: the adjustment items that the athlete should prioritize, the recommended training frequency, the range of adjustment, and a tracking method for dynamically monitoring postural deviation values ​​during subsequent training. In actual training, the athlete can gradually implement the corresponding adjustments according to the plan and observe changes in postural deviation values ​​in real time through sensor feedback and data monitoring, thereby verifying the effectiveness of the adjustments and further optimizing training habits.

[0058] The overall beneficial effects of this invention are as follows: First, by comprehensively considering thresholds, comparing athlete screening, identifying reference athletes, and determining the optimal adjustment items, a closed-loop adjustment mechanism from environmental conditions to training behavior is established, realizing the scientific and personalized adjustment of training load.

[0059] Secondly, this method makes full use of the different adaptation results of different athletes under the same adverse environmental conditions, and transforms these differences into a reference plan that the tested athletes can directly apply, thereby significantly improving training efficiency.

[0060] Third, this invention is primarily applied to golf. Due to the slow rhythm and gradually adjustable posture of golf movements, this method is particularly well-suited to the training habits and technical characteristics of golfers. It can effectively prevent the solidification of non-standard movements caused by environmental stress and promote athletes to gradually improve their technical level in a healthy way.

[0061] Fourth, this scheme is essentially based on athletes' personalized physiological and environmental data, and therefore has portability in terms of technical principles. It can be extended to other sports that rely on grass or environmental factors, such as football, rugby, and hockey, to provide athletes in different sports with targeted training load adjustment methods.

[0062] Therefore, this invention not only provides a scientific and effective personalized training load adjustment mechanism, but also offers a practical solution for athletes to improve postural stability and athletic performance in complex environments, and has broad application prospects and practical promotion value.

[0063] Furthermore, Figure 5 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0064] In another preferred embodiment of the present invention, a personalized training load adjustment system based on dynamic physiological data includes: The data acquisition module 100 is used to collect a database of the target training grassland and to obtain the comprehensive index of grassland conditions and posture deviation values ​​at each training location when the tested athlete trains along the predetermined training route.

[0065] The comprehensive index of grass conditions is calculated by combining parameters such as grass moisture content, grass slope, grass cover density, and ground rebound characteristics at different training locations along the predetermined training route. The value of the comprehensive index of grass conditions is used to characterize the overall impact of grass conditions on the athlete's postural stability; the larger the value, the more significant the impact on postural stability.

[0066] Furthermore, the personalized training load adjustment system based on dynamic physiological data also includes: The sample extraction module 200 is used to extract training samples from the database of several comparative athletes who have a posture deviation value that is continuously greater than the posture deviation threshold when the comprehensive index of grassland conditions exceeds the comprehensive threshold and the posture deviation value is continuously greater than the posture deviation threshold.

[0067] Furthermore, the personalized training load adjustment system based on dynamic physiological data also includes: The reference screening module 300 is used to analyze the training samples and select several comparative athletes whose training frequency is in the lowest range during the process of recovering the posture deviation value to no more than the posture deviation threshold. These athletes are then identified as reference athletes.

[0068] Furthermore, the personalized training load adjustment system based on dynamic physiological data also includes: The coupling analysis module 400 is used to obtain the trend of the change of posture deviation value of each reference athlete with the change of training frequency and the adjustment data of the athlete's self-implementation in training that belongs to the set of training load adjustment items. The coupling degree of the adjustment data and the trend of the change of posture standard value is calculated, and the adjustment item with the highest coupling degree is determined as the corresponding optimal adjustment item.

[0069] Furthermore, the personalized training load adjustment system based on dynamic physiological data also includes: The scheme generation module 500 is used to summarize the best adjustment items for different reference athletes and generate personalized training load adjustment schemes for the tested athletes.

[0070] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0071] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0072] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A personalized training load adjustment method based on dynamic physiological data, characterized in that, The method includes: A database of target training grasslands was collected, and the comprehensive index of grassland conditions and posture deviation values ​​of each training location were obtained when the test subjects trained along the predetermined training route. When the comprehensive index of grassland conditions exceeds the comprehensive threshold and the posture deviation value is consistently greater than the posture deviation threshold, several training samples of comparative athletes who have consistently exceeded the posture deviation threshold when on a predetermined training route and near the comprehensive threshold are extracted from the database. Analyze the training samples and select a number of control athletes whose training frequency was the lowest during the recovery of their posture deviation value to no more than the posture deviation threshold. The trend of postural deviation values ​​of each reference athlete as training frequency changes and the adjustment data of the athletes’ self-implementation in training that belong to the set of training load adjustment items are obtained. The coupling degree between the adjustment data and the trend of postural standard value changes is calculated, and the adjustment item with the highest coupling degree is determined as the corresponding best adjustment item. The best adjustment items for different reference athletes are summarized to generate personalized training load adjustment plans for the tested athletes.

2. The personalized training load adjustment method based on dynamic physiological data according to claim 1, characterized in that, The comprehensive index of grass conditions is calculated by combining parameters such as grass moisture content, grass slope, grass cover density, and ground rebound characteristics at different training locations along the predetermined training route. The value of the comprehensive index of grass conditions is used to characterize the overall impact of grass conditions on the athlete's postural stability; the larger the value, the more significant the impact on postural stability.

3. The personalized training load adjustment method based on dynamic physiological data according to claim 1, characterized in that, The posture deviation value refers to the degree of deviation of an athlete from a preset standard posture when training in various training positions.

4. The personalized training load adjustment method based on dynamic physiological data according to claim 2, characterized in that, When the comprehensive index of grassland conditions exceeds the comprehensive threshold and the posture deviation value remains greater than the posture deviation threshold, the steps for extracting training samples from the database of several comparative athletes who exhibited posture deviation values ​​consistently greater than the posture deviation threshold on a predetermined training route and near the comprehensive threshold include: Arrange the comprehensive index of grass conditions at each training location along the predetermined training route in ascending order and generate a comprehensive index change trend. Determine whether there is a threshold point in the change trend such that after exceeding the threshold point, the posture deviation value of the tested athlete at each training location is greater than the posture deviation threshold. If such a threshold point exists, it is set as the comprehensive threshold, and several training samples of comparative athletes who, after passing the comprehensive threshold, exhibited a continuous postural deviation value greater than the postural deviation threshold on the same predetermined training route are selected from the database.

5. The personalized training load adjustment method based on dynamic physiological data according to claim 1, characterized in that, The steps for analyzing training samples and selecting a few control participants whose training frequency was lowest during the recovery of posture deviation to within the posture deviation threshold include: Analyze the training samples of each comparison athlete to determine the training frequency at which the posture deviation value was restored from greater than the posture deviation threshold to no more than the threshold during the training process, and select several comparison athletes whose training frequency is in the lowest range. The selected athletes were chosen as the reference athletes.

6. The personalized training load adjustment method based on dynamic physiological data according to claim 4, characterized in that, The training load adjustment items include quantifiable training adjustment items such as swing plane angle adjustment, downswing rhythm adjustment, stance distance adjustment, center of gravity offset range control, and lower limb force balance ratio adjustment.

7. The personalized training load adjustment method based on dynamic physiological data according to claim 6, characterized in that, The steps for obtaining the trends of postural deviation values ​​of each reference athlete as training frequency changes, and their self-implemented adjustment data that belongs to the set of training load adjustment items during training, calculating the coupling degree between the adjustment data and the trend of postural standard values, and determining the adjustment item with the highest coupling degree as the corresponding optimal adjustment item include: Obtain the trend of the postural deviation value of each reference athlete at the training position corresponding to the comprehensive threshold point with the training frequency, as well as the adjustment data of at least one item that the athlete autonomously implements during the training process and belongs to the training load adjustment item set; Calculate the percentage change of the adjustment data at each training frequency relative to the previous training frequency, and calculate the coupling degree between the percentage change of the adjustment data at each training frequency and the percentage change of the posture deviation value. The adjustment item with the highest coupling degree is determined as the best adjustment item for the corresponding reference athlete.

8. The personalized training load adjustment method based on dynamic physiological data according to claim 1, characterized in that, When summarizing the best adjustment items for different reference athletes, if two or more reference athletes have the same best adjustment item, the best adjustment item with the lowest training frequency in the process of restoring the posture deviation value to no more than the posture deviation threshold shall be selected as the preferred option.

9. A personalized training load adjustment system based on dynamic physiological data, characterized in that, The system includes: The data acquisition module is used to collect a database of the target training grassland and obtain the comprehensive index of grassland conditions and posture deviation value of each training location when the test athlete trains along the predetermined training route. The sample extraction module is used to extract training samples from the database of several comparative athletes who have a posture deviation value that is continuously greater than the posture deviation threshold when the grass condition comprehensive index exceeds the comprehensive threshold and the posture deviation value is continuously greater than the posture deviation threshold. The reference screening module is used to analyze the training samples and select several control athletes whose training frequency is the lowest during the recovery of posture deviation value to no more than the posture deviation threshold. These control athletes are then identified as reference athletes. The coupling analysis module is used to obtain the trend of the change of posture deviation value of each reference athlete with the change of training frequency and the adjustment data of the athlete's self-implementation in training that belongs to the set of training load adjustment items. The coupling degree of the adjustment data and the trend of the change of posture standard value is calculated, and the adjustment item with the highest coupling degree is determined as the corresponding optimal adjustment item. The program generation module is used to summarize the best adjustment items for different reference athletes and generate personalized training load adjustment programs for the tested athletes.

10. The personalized training load adjustment system based on dynamic physiological data according to claim 9, characterized in that, The comprehensive index of grass conditions is calculated by combining parameters such as grass moisture content, grass slope, grass cover density, and ground rebound characteristics at different training locations along the predetermined training route. The value of the comprehensive index of grass conditions is used to characterize the overall impact of grass conditions on the athlete's postural stability; the larger the value, the more significant the impact on postural stability.

Images