706 results about "Training effect" patented technology

The invention provides a physical training posture correction method based on machine vision, which comprises the following steps: acquiring an athlete training image sequence through a multi-view image acquisition system and preprocessing the athlete training image sequence, extracting three-dimensional posture key points of a human body by utilizing a depth posture recognition model, constructing a skeleton model and calculating real-time kinematics characteristic parameters, and performing multi-dimensional comparison with standard parameters to generate a posture deviation evaluation report, thereby generating a personalized multi-modal correction feedback scheme, and establishing a personal athlete movement feature database to realize adaptive standard parameter optimization. According to the method, the training postures of athletes can be accurately recognized and corrected in real time, the training effect can be improved, sports injuries can be prevented, and training individuation and scientificity are improved.

The invention discloses an elderly cognitive function adaptive training method and system based on multi-modal interaction feedback, and relates to the technical field of smart medical treatment. The method comprises the steps that basic information of a user is collected for initial cognitive ability evaluation, a user cognitive portrait is constructed according to an evaluation result, and an initial training task with the corresponding difficulty is allocated; collecting multi-modal interaction data in real time according to the initial training task; carrying out fusion analysis on the multi-modal interaction data by utilizing a machine learning model to obtain a quantized real-time state index; based on the real-time state index and the performance data of the current task, dynamically adjusting a subsequent training task through an adaptive decision rule engine; all-dimensional data of each training task is recorded, a visual cognitive competence development trend report is generated through longitudinal comparative analysis, and a machine learning model and a self-adaptive decision rule engine are continuously optimized and trained by utilizing accumulated user data to form an optimized training closed loop. The cognitive function training effect of the old people can be improved.

The invention relates to the technical field of medical data processing and human-computer interaction, and particularly discloses a rehabilitation training feedback adjusting system based on a brain-computer interface and myoelectricity sensing. The system comprises a multi-modal physiological signal acquisition module, a signal fusion and intention decoding module, a rehabilitation state dynamic evaluation module, a self-adaptive feedback strategy generation module and a multi-channel feedback execution module. By synchronously collecting and fusing the electroencephalogram signals and the electromyographic signals to decode the motion intention, dynamically evaluate the rehabilitation state and predict the trend, a multi-sensory collaborative feedback strategy is adaptively generated, personalized and dynamic precise adjustment of rehabilitation training is achieved, and the training effect and the patient participation degree are improved. The system can autonomously switch between a reinforcement learning strategy and an auxiliary guiding strategy according to the real-time performance and the long-term trend of a patient, and dynamically optimize various feedback parameters.

The utility model relates to the technical field of sitting posture correction, and discloses a child sitting posture training device which comprises a correction assembly, the correction assembly comprises a first cushion block and a second cushion block, the first cushion block is provided with a first top face and a first bottom face which are oppositely arranged, and the second cushion block is provided with a second top face. The second cushion block is provided with a second top surface, a second bottom surface and a plurality of side surfaces, the second top surface and the second bottom surface are oppositely arranged, the side surfaces are arranged between the second top surface and the second bottom surface, at least two adjacent side surfaces are arranged at a preset included angle, the second bottom surface is detachably connected with the first bottom surface, and the size of the second bottom surface is smaller than that of the first bottom surface; when the first cushion block is located at the supporting position, a child patient can sit on the second top face and step on the first bottom face, the two legs of the child patient can abut against the two side faces arranged at the preset included angle respectively, when the first cushion block is located at the table top position, the two legs of the child patient can abut against the two side faces arranged at the preset included angle respectively in the sitting posture state, and the first top face is used for containing objects. Adjustability and use flexibility are good, operation is convenient, and the training effect is good.

The invention relates to the technical field of lower limb rehabilitation training, and discloses an intelligent load lower limb rehabilitation training system fused with a multi-source sensor. The system comprises a multi-source sensing module, a motion intention recognition module, a self-adaptive track generation module, a real-time load regulation and control module and an actuator driving module. The multi-source sensing module synchronously collects plantar pressure, joint angles and electromyographic signals during training of a user through a plantar pressure sensor array, a knee joint angle sensor and a surface electromyographic sensor; the motion intention recognition module extracts time domain and frequency domain features from the multi-source data, and obtains a real-time motion intention through classification; the self-adaptive track generation module generates an exclusive three-dimensional motion track in combination with the real-time intention and historical rehabilitation data of the user; the real-time load regulation and control module generates a self-adaptive load control signal through a fuzzy decision algorithm; the actuator driving module adjusts the magnetic powder brake through PWM current, outputs corresponding real-time resistance torque, and assists in optimizing the rehabilitation training effect.

The invention discloses a neural signal-based wounded rehabilitation effect evaluation model construction method, and relates to the technical field of medical rehabilitation, and the method comprises the steps: synchronously collecting electroencephalogram, myoelectricity and motion parameters, extracting multi-source features to construct feature vectors corresponding to training actions, and according to the feature vector data of multiple training actions of a wounded, constructing a neural signal-based wounded rehabilitation effect evaluation model; and capturing dynamic changes of neural signals and action control ability in the training action sequence based on the sequence model, and constructing an evaluation model. According to the invention, time-dependent learning is carried out on the corresponding characteristics of each training action by using the sequence model, dynamic changes of neural signals and action control ability along with the training actions can be captured, an improvement trend in a rehabilitation process is embodied, and an evaluation model aiming at an action training effect is constructed; the action indexes output by the evaluation model can reflect the instant effect and gradual improvement condition of each action in training, and help to identify rehabilitation inflection points and training bottlenecks.

The invention relates to the technical field of model training sample processing, in particular to a sample distribution adaptive adjustment method and system based on model training feedback driving, and the method comprises the following steps: S1, collecting feedback indexes in a training process in real time in a model training period, and obtaining a feedback index set; s2, weak item categories are analyzed and recognized based on the feedback index set, and an optimization instruction is generated; s3, dynamically adjusting the sampling weight to form an updated sampling strategy; s4, samples are collected according to a sampling strategy, and weak item category samples are supplemented; s5, putting the optimized sample set into the next round of training, and circulating the steps S1 to S4 until the training indexes of the learning effects of all key categories meet the termination condition; and acquiring a sampling strategy and a sample set. According to the method, real-time, refined and automatic sampling adjustment can be realized by taking the actual performance of model training as a core feedback index, so that the training effect and generalization ability of the model in key areas such as weak-term categories and long-tail categories are improved.

The invention belongs to the technical field of shooting training assistance, and discloses a kinetic energy weapon trajectory attitude analysis and shooting time acquisition method and system. The method comprises the following steps: installing and calibrating a weapon detection terminal comprising an acceleration sensor and a gyroscope sensor on a kinetic energy weapon gun body; in the shooting process, acceleration and angular velocity data of the weapon are collected at high frequency through the terminal and wirelessly transmitted to the analysis processing equipment; the analysis processing equipment is used for performing gravity compensation and attitude calculation on the received data to obtain a real-time attitude angle and processing angle abrupt change; analyzing the data statistical characteristic change of the acceleration and / or angular velocity data, and comparing the data statistical characteristic change with a preset threshold value to accurately judge the shooting moment; and finally outputting track attitude information for evaluation. The weapon attitude can be accurately analyzed, the shooting time is accurately collected, an objective and quantitative evaluation basis is provided for shooting training, and the training effect is improved.

The invention discloses a cognitive behavior training system, method and device and a program product, relates to the field of medical rehabilitation, and is used for solving at least one problem of single training target, single task difficulty and single task element. According to the method, main training tasks of five dimensions are carried out in stages, cognitive competence corresponding to task training of each dimension is progressively carried out step by step, and centralized, continuous, selective, alternate and dispersive attention cognitive competence intervention is respectively carried out. The main training task of each dimension sequentially comprises multiple levels of sub-training tasks with gradually increased difficulty, and each level of sub-training task comprises multiple groups of segmented tasks. And respectively evaluating the training effect under each dimension. According to the method, the difference and compliance of cognitive behavior training are improved, the intervention efficiency is improved, and the long-term intervention effect is ensured.

The invention relates to the technical field of rehabilitation training, in particular to a rehabilitation training method and system integrating a rehabilitation robot and a cloud platform. Comprising the following steps: constructing a standardized motion track data set; joint time sequence features are extracted, coordination deviation in the multi-joint coordination process is analyzed, time sequence coordination deviation distribution is determined, and when deviation exceeds a preset range, an abnormal deviation track and a compensation behavior mode are recognized; generating a personalized training protocol scheme in combination with the compensatory behavior pattern and patient personalized data, and obtaining an optimized motion guidance path through multi-joint collaborative path simulation and parameter correction; training feedback indexes are extracted based on the motion guidance path, the training effect is judged, rehabilitation robot control parameters are dynamically updated, and a continuously optimized function recovery path is formed. The problems that in existing rehabilitation training, multi-joint collaborative evaluation is insufficient, and a training scheme is difficult to dynamically adapt are solved, and intelligentization, individualization and continuous optimization of the rehabilitation training process are achieved.

The invention relates to the field of data processing, in particular to a rehabilitation decision data processing system based on artificial intelligence, which comprises the following steps of: extracting training state characteristics of a rehabilitation target, calculating a training effect degree characterization value in combination with an action posture goodness of fit, and marking a corresponding training period stage; based on training period stage marking, determining training deviation cumulant and the criticality of the training period stage relative to the whole feedback period, evaluating rehabilitation conversion characterization parameters, and judging whether a rehabilitation feedback stage needs to be entered or not; identifying swelling amplitudes and swelling areas corresponding to a plurality of joints, judging whether the swelling amplitudes and the swelling areas conform to a joint state standard or not, determining rehabilitation abnormal joints, obtaining dislocation amplitudes and swelling rebound times in a current training period stage, and marking the rehabilitation abnormal joints; rehabilitation plan adjustment signals are adaptively emitted. The rehabilitation training effect of the rehabilitation target is accurately evaluated and dynamically tracked, the dynamic adjustment of the rehabilitation plan is promoted, and the rehabilitation efficiency is improved.

The invention relates to the technical field of rehabilitation training, and discloses a three-dimensional reconstruction rehabilitation training auxiliary method based on AgenticAI and MCP protocols, which is used for providing personalized rehabilitation training support for a user and improving the body function state. The method comprises the steps that current state description information of a user is obtained through a natural language interaction interface, and a decision scheme containing multiple candidate rehabilitation actions is generated through fusion analysis of an AgenticAI decision module in combination with historical rehabilitation training records and physiological index data, obtained by a context engineering engine, of the user. And a corresponding three-dimensional reconstruction training tool is matched by means of an MCP protocol server, personalized calling parameters are generated according to a user capability evaluation result and preference setting, the tool is executed, real-time operation data are collected, the data are stored, and a user capability evaluation portrait is updated. According to training effect feedback data, weight parameters of the decision module are adjusted through a federated learning optimization algorithm, a cross-cycle personalized rehabilitation training plan is finally generated, and the personalization and systematicness of rehabilitation training are improved.

The invention discloses an intelligent diopter training system and method based on a multi-modal physiological feedback and reinforcement learning algorithm. The intelligent diopter training system comprises a multi-modal physiological data acquisition module, a central processing PC, a user terminal and a cloud data platform. Visual behavior data, ciliary muscle state data and autonomic nerve reaction data of a user are collected in real time through a multi-modal physiological data collection module, multi-modal physiological data fusion and feature extraction are carried out, and a refraction state evaluation model is used for calculating a comprehensive score of a refraction state grade, visual fatigue and adjustment sensitivity of the current user. A personalized training parameter set of the next training period is dynamically decided and generated based on a reinforcement learning algorithm, and the user terminal presents visual training stimulation according to the current personalized training parameter set. The cloud data platform stores the data and generates a visual training effect trend chart, a diopter change prediction report and personalized training suggestions to complete training scheme personalization, training means intellectualization and feedback evaluation comprehensiveness.

The application provides an ultrahigh frequency electrocardiogram mapping analysis method and system, through a Hilbert transform algorithm, time-frequency characteristics of high-frequency electrocardiogram signals can be retained, and influence of complex clutter on the high-frequency electrocardiogram signals can be reduced to the maximum extent; through drawing of an electrical activation map, time-space distribution of electrical activity is described in a graphical manner, and atrium / ventricle asynchrony or myocardial ischemia problems can be more accurately revealed; through transfer learning, a model can better understand and process new data, and the problem of poor model training effect caused by less high-frequency electrocardiogram data is effectively solved; through construction of an intelligent diagnosis system, the automation level of diagnosis is improved, and auxiliary diagnosis of inputting an electrical activation map and outputting a classification result is realized.

The invention relates to the technical field of training evaluation, in particular to an evaluation method and system based on functional actions and physical fitness, and the method comprises the steps: collecting an image when a user does an evaluation action; the action quality score after the user completes the assessment action is calculated, the action and physical fitness of the user are assessed according to the action quality score, and the action quality score is in positive correlation with the action execution score for completing the assessment action and the balance coefficient for completing the assessment action. The balance coefficient reflects the stability of plantar pressure distribution when the user completes the evaluation action. The method not only improves the accuracy and individuation level of posture evaluation, but also can flexibly adjust scoring key points according to different users and action types. Finally, the intelligent mirror has higher adaptability, real-time performance and guidance in scenes such as rehabilitation evaluation and physical fitness detection, and the training effect of the user is remarkably improved.

The utility model discloses a rehabilitation training device for nursing chronic obstructive pulmonary disease, a pedaling device comprises a mounting frame and a linkage assembly, and the mounting frame is arranged on the other side of a support frame; the linkage assembly is rotatably arranged in the mounting frame; the breathing device comprises a breathing box, a breathing assembly, a hose and a mask, and the breathing box is arranged on one side of the top of the mounting frame; the breathing assembly is arranged in the breathing box, and the breathing assembly is connected with the linkage assembly; one end of the hose is connected with the breathing assembly; the mask is connected with the other end of the hose; the control system comprises a microprocessor, and the microprocessor is arranged in the breathing box and connected with the breathing assembly. Therefore, the device combines pedaling and breathing training, strengthens lower limb strength and improves the breathing function, the linkage assembly ensures synchronization of the pedaling and breathing training, the training effect is improved, the built-in control system monitors breathing in real time, the training intensity is automatically adjusted, safety and comfort are guaranteed, and the training effectiveness and patient compliance are improved.

The invention relates to the technical field of fire safety and simulation training, and discloses a rule-driven fire-fighting real smoke and real fire training simulation system, which comprises a data acquisition and modeling module, a rule driving module, a rendering output module and a training evaluation module. The data acquisition and modeling module is used for acquiring initial fire data and constructing a reference model of smoke diffusion and fire spreading; the rule driving module simulates the non-synchronous evolution process of the fire through a particle simulation algorithm, a time coordination rule and a feedback loop algorithm; the rendering output module is used for integrating the environment rendering data and the multi-factor propulsion mode and generating a training effect evaluation index; and the evaluation optimization module judges whether the simulation precision of the reference model reaches a preset standard or not according to the training effect evaluation index until a simulation result meeting a precision requirement is obtained. According to the invention, the reality and accuracy of fire-fighting simulation training are improved.

The invention discloses an anti-resistance exercise training system for old people based on intelligent wearable equipment, and relates to the technical field. The problems that in the prior art, a dynamic action monitoring error correction mechanism is lacked, exercise intensity adjustment is not personalized and real-time, interaction and data feedback functions do not exist, and equipment portability and wearing adaptability are insufficient are solved. The system collects data in real time through the whole body position intelligent wearable device, corrects non-standard actions through the action recognition feedback module, dynamically regulates the intensity through the exercise intensity evaluation module, reduces the risks of muscle strain, cardiovascular burden and the like, takes standardized action guidance, personalized intensity adaptation and data visualization as the core, ensures target muscle activation, and improves the training efficiency. The training effect is quantified, the operation is simple, the use threshold is reduced through voice guidance, the boring feeling is relieved through personalized plans and summary reports, the training achievement feeling and compliance of the old people are enhanced, the muscle strength can be improved through whole body position training, and the anti-resistance exercise requirement of the old people is met.

The invention discloses an intelligent ankle rehabilitation exercise management system based on multi-modal data fusion, which belongs to the field of medical assistance and comprises an acquisition processing module, a feature compensation module, an action extraction module, a structure modeling module, a judgment and detection module, an error correction guide module, a management scheduling module, a decision execution module and a report generation module. The motion state of each patient can be comprehensively reflected, fine-grained detection of abnormal actions is achieved, the patient is guided to correct the actions through multi-modal feedback, the secondary injury risk caused by wrong action accumulation is reduced, and the training effect and the controllability of rehabilitation progress are improved; the training plan can be continuously adjusted along with the rehabilitation progress of the patient, dynamic evolution is achieved, meanwhile, insufficient training or potential risks can be rapidly found, doctors and the patient are helped to clearly know the rehabilitation progress, the rehabilitation scheme is continuously optimized, and the training process is more efficient.

The invention belongs to the technical field of lung rehabilitation training, and particularly relates to a lung rehabilitation training effect evaluation system and method based on multi-modal data fusion. According to the method, a dynamic reference model conforming to individual differences is established through three-dimensional pulmonary respiration mobility modeling based on patient CT images, individualized comparative analysis of lung function recovery states of different patients is achieved, and meanwhile external respiration dynamics and internal physiological state parameters are collected and fused; rehabilitation quality is evaluated from the two aspects of exercise performance and physiological response, scientificity and reliability of evaluation are remarkably improved, a patient can visually perceive difference between own breathing actions and an ideal state through AR visual correction prompts, active correction of actions and muscle memory formation are promoted, effectiveness of rehabilitation training is improved, and the rehabilitation training effect is improved. The training difficulty and the resistance threshold value are dynamically adjusted according to the historical evaluation result and the real-time correction effect, it is guaranteed that rehabilitation training is gradually strengthened within the safe and reasonable range, and the rehabilitation efficiency is improved.

The invention provides an intelligent medical inquiry method, device and equipment and a computer readable storage medium. According to the method, user intentions are classified by calling a large language model based on interaction information from a user, so that recall of a disease probability and recall of an optimal inquiry point are realized by calling different agents based on another large language model under the condition of determining that the classification of the user intentions is medical inquiry. Therefore, corresponding disease probability distribution and further inquiry information are generated and displayed to the user in a chart form. According to the method, a user can quickly obtain the dynamically updated suspected disease probability distribution diagram, and the user experience is greatly improved. According to the method, tasks of the large language model are decomposed through multiple agents, each subtask can be optimized independently, the training efficiency and the training effect of the model are greatly improved, and through combination of models of different scales, calculation power configuration can be optimized, and the model training cost is reduced.

The invention relates to a data acquisition method and system based on a rehabilitation device, and relates to the field of data acquisition and processing.The method comprises the steps that man-machine interaction force data and plantar pressure distribution data are acquired; obtaining a man-machine interaction force value based on the man-machine interaction force data; if the human-computer interaction force value exceeds a preset human-computer interaction force threshold value, an active auxiliary mode of the rehabilitation device is triggered; if the human-computer interaction force value does not exceed the preset human-computer interaction force threshold value, obtaining plantar pressure distribution characteristics from the plantar pressure distribution data; generating a control feedback signal in combination with the human-computer interaction force value and the plantar pressure distribution characteristics; and controlling the rehabilitation device to perform auxiliary operation based on the control feedback signal. The training effect evaluation method and device have the effect of improving the accuracy of training effect evaluation.

The invention relates to the technical field of sports science, and discloses a heart rate and exercise load synchronous monitoring training system, which comprises a multi-modal data acquisition module used for synchronously acquiring a physiological signal data set and a kinematics data set of a user; the data fusion and feature extraction module is used for generating a comprehensive state parameter set comprising real-time heart rate variability, an exercise load intensity index, a body balance coefficient and a fatigue degree evaluation value; the dynamic load evaluation module is used for calculating an optimal heart rate interval, a strength distribution optimization weight and an attitude stability compensation parameter in the current motion mode; the somatosensory feedback and decision module is used for generating a personalized training instruction set based on a reinforcement learning algorithm; and the cloud collaboration and personalized adaptation module is used for triggering a collaborative intervention mechanism based on multi-agent consensus. The training effect can be improved, the exercise safety is guaranteed, and the exercise injury probability is reduced.

The invention provides an astronaut physical exercise process intelligent guide feedback method and system, and relates to the technical field of data feedback, and the method comprises the steps: obtaining three-dimensional motion track data in an astronaut training process, and carrying out kinematics analysis calculation to obtain a joint angle sequence and limb space posture parameters; the method comprises the following steps: obtaining a deviation vector by comparing and analyzing with a standard action template, generating a posture correction instruction and feeding back in real time, and regulating and controlling load parameters of training equipment, thereby realizing accurate guidance and intelligent correction in the astronaut training process, and improving the training effect and safety.

A forearm exerciser is provided, including an exerciser body, wherein the exerciser body is of a cylindrical structure and includes a winding portion in the middle and grip portions symmetrically arranged at both ends of the winding portion. A suspension rope is connected to the winding portion, and an inner ring for allowing the rod body to pass through is formed at a central axis of the exerciser body, so as to ensure the training effect of the forearm and ensure the safe training of a trainee.

The invention belongs to the technical field of child visual training, and particularly relates to a child visual function training system and method based on ciliary muscle adjustment. The child visual function training system based on ciliary muscle adjustment comprises a collaborative acquisition module and a dynamic training module. The collaborative acquisition module acquires an anterior segment image of an eyeball in real time through a built-in image acquisition unit so as to identify eye features, acquires extraocular muscle pressure deformation data through a built-in pressure acquisition unit, and then associates and analyzes the eye features and the extraocular muscle pressure deformation data through a built-in data fusion unit; a mapping model is established according to the analysis result, the refractive power change of the crystalline lens is calculated, and the calculation result is processed into the ciliary muscle adjustment amount; the dynamic training module determines training parameters in combination with child individual data and historical data acquired by the collaborative acquisition module, and dynamically adjusts training duration and light wave parameters according to the ciliary muscle adjustment amount, thereby solving the problems of poor child training effect and safety risk in the training process.

The invention discloses a target range-oriented data acquisition and analysis method and system and a storage medium. The method comprises the following steps: acquiring action posture information, physiological state information, environment state information and shooting hit information of a trainer; training effect analysis is conducted on the obtained action posture information, physiological state information, environment state information and shooting hit information, and evaluation indexes are generated; and through a large language model technology, a personalized automatic evaluation report is generated based on the evaluation indexes. According to the method, the trainee can obtain accurate feedback in real time in the training process, meanwhile, training effect analysis greatly improves the shooting training efficiency and individuation level, various information data in the shooting training process can be comprehensively collected and analyzed, the trainee is helped to know the training state, progress and defects of the trainee in real time, and the training effect is improved. And a personalized automatic evaluation report is provided according to an analysis result, so that a more efficient shooting training effect is finally realized.

The utility model discloses a four-force-arm multi-track strength training device which comprises a machine frame. The four adjusting assemblies are located on the same side of the rack and arranged on the periphery of the rack, each adjusting assembly comprises an adjusting base and an output rod, the adjusting bases are rotationally connected to the rack in the horizontal direction, and the output rods are rotationally connected to the adjusting bases in the vertical direction; the four stretching parts are connected with the adjusting assemblies in a one-to-one correspondence mode, each stretching part comprises a pulling block, the pulling blocks are connected to the outer side of the output rod, and the pulling blocks are suitable for being pulled outwards; and the resistance output module is connected to the rack, and the resistance output module is used for outputting load force to the pulling block. Two additional force arms and a flexible multi-angle adjusting mechanism are added, the types of training actions are greatly enriched, the adaptability and expansibility of the equipment are improved, a user can do diversified and personalized exercise according to different muscle groups, operation is easy, convenient and visual, the equipment is suitable for people of various body types and training levels, and the practicability is high. And the fitness experience and the training effect are obviously enhanced.

The invention provides a cardiopulmonary resuscitation training control method, a cardiopulmonary resuscitation training control system and cardiopulmonary resuscitation simulation equipment, and relates to the technical field of medical equipment. Operation indexes such as pressing depth, frequency and springback of a cardio-pulmonary resuscitation simulation person and related physiological parameters are converted into holographic 3D images in real time, visual and synchronous presentation of operation data is achieved, and the training effect and teaching efficiency are remarkably improved.

The invention discloses a rhythm mode intelligent identification and sightsinging rhythm training system and a method thereof, and relates to the technical field of music rhythm data processing, and the method comprises the steps: collecting multi-dimensional audio data played by a user, generating physical deviation data through time sequence comparison, judging a rhythm position and a timbre attribute in combination with sound intensity and frequency spectrum data, and carrying out the intelligent identification of the rhythm mode and the sightsinging rhythm training. Calculating deviation data by using the sensing weight coefficient; identifying a core rhythm problem based on the deviation data, and generating a personalized prescription exercise song in combination with the music style preference of the user; determining whether to add interference scene data or not according to a threshold value, generating interference music segments through an algorithm composition engine, and mixing and outputting the interference music segments; the interference intensity and the rhythm density are dynamically adjusted by comparing the change of deviation data before and after the change of the simulated exercise curve. According to the invention, personalized dynamic adjustment and closed-loop optimization of rhythm training are realized, and rhythm evaluation accuracy and training effect are effectively improved.