Search

CN-121983236-A - Real-time health state monitoring system based on biosensor

CN121983236ACN 121983236 ACN121983236 ACN 121983236ACN-121983236-A

Abstract

The invention discloses a real-time health state monitoring system based on a biosensor, which relates to the technical field of health monitoring and comprises a sensor module, a motion association module, a project state evaluation module, a risk early warning module, a training adjustment module and an optimization feedback module, wherein the sensor module comprises a physiological sensing unit and a posture sensing unit, the physiological sensing unit and the posture sensing unit acquire data through flexible sensors arranged on the body surface of an athlete to obtain physiological data and posture data, the relationship between posture change and the physiological data is analyzed through the motion association module, the project state evaluation module is combined, personalized health monitoring is realized based on individual fitness and historical data of the athlete, the health risk and the training adjustment module are quantified through the risk early warning module, the training strength is dynamically adjusted, the risk of the motion injury is reduced, and finally the adjusted training performance is evaluated through the optimization feedback module, so that the training is optimized and improved.

Inventors

  • WANG ZEMING

Assignees

  • 深圳蜜拓蜜健康管理有限公司

Dates

Publication Date
20260505
Application Date
20260114

Claims (8)

  1. 1. The real-time health state monitoring system based on the biological sensor is characterized by comprising a sensor module, a motion association module, a project state evaluation module, a risk early warning module, a training adjustment module and an optimization feedback module; The sensor module comprises a physiological sensing unit and a posture sensing unit, wherein the physiological sensing unit and the posture sensing unit acquire data through flexible sensors arranged on the body surface of an athlete to obtain physiological data and posture data; The motion association module is used for analyzing the change information of the physiological data and the physical state data along with time, evaluating the association between the physiological data and the physical state data, obtaining an association coefficient and reflecting the association strength between the two data; the project state evaluation module is used for analyzing the training state of each sports project by combining the individual adaptation condition of the athlete, the sports project index weight and the relevance coefficient to obtain a training state comprehensive value; the risk early warning module analyzes the health risk condition of the future time based on the change condition of the training state comprehensive value along with the time to obtain a health risk value, and judges whether the training intensity needs to be adjusted according to the health risk value; The training adjustment module adjusts the current training intensity based on the health risk value and the training state integrated value, and the optimization feedback module analyzes the data in the project state evaluation module based on the training state integrated value change condition after the training intensity adjustment.
  2. 2. The system for monitoring the real-time health status based on the biosensor according to claim 1, wherein the motion correlation module first calculates a variation of each physiological data, sets a time interval, and compares the variation of each physiological data with the time interval to obtain an instantaneous variation rate of the physiological data; Calculating the variation of the physical data, adding a physiological response lag time according to different characteristics of the physiological data, ensuring the correlation accuracy between the physiological data and the physical data, and comparing the variation of the physical data with a time interval to obtain the instantaneous variation rate of the physical data; And finally, respectively comparing the instantaneous change rate of the physiological data and the instantaneous change rate of the physical state data with the standard instantaneous change rate set by the system, setting association weights according to the association strength between the physiological data and the physical state data and the individual difference of athletes, and introducing a time attenuation item to obtain an association coefficient C ij (t) of the ith physiological index and the jth physical state index at the moment t.
  3. 3. The real-time health status monitoring system based on a biosensor according to claim 2, wherein the program status evaluation module first screens the association coefficients required for training programs and then evaluates the training status, and the evaluation process is as follows: ; S (t) in the formula is the training state comprehensive score of the athlete at the moment t, and reflects the training state of the athlete at the moment t in the self-belonged project; beta (t) is an individual fitness influence coefficient at the moment t, and reflects individual fitness of athlete individuals to training intensity and an individual coefficient of historical state stability; c ij (t) is the association coefficient of the ith physiological index and the jth morphological index at the moment t; W pro (j) is a project customization index influence coefficient, and the value range is 0 to 1; n represents the number of core indexes, namely the number of indexes associated with the physiology and the physical state of the training program; the project state evaluation module selects corresponding physiological data and physical data according to different sports projects, and introduces individual fitness to realize personalized health state monitoring of different athletes.
  4. 4. The system for monitoring the real-time health state based on the biosensor according to claim 3, wherein the risk early-warning module predicts training risk at a future time based on a dynamic change rate of training state with time, firstly compares a training state comprehensive score S (t) of the athlete at a time t with a project safety threshold preset by the system, and quantifies the relative degree of risk as a safety threshold deviation term; Calculating the time change rate of the training state comprehensive score S (t) of the athlete at the moment t, reflecting the state deterioration speed, combining the safety threshold deviation item with the time change rate of the training state comprehensive score S (t) of the athlete at the moment t, introducing a fatigue accumulation coefficient set on the basis of historical fatigue data of the athlete, and obtaining a health risk value P risk (t+Δt) at the moment t+Δt, and reflecting the training risk degree at the future time.
  5. 5. The system for monitoring the real-time health status based on the biosensor according to claim 4, wherein the training adjustment module is configured to analyze the health risk value P risk (t+Δt) at the time t+Δt and the difference between the current training status and the optimal training status to generate a quantized training intensity adjustment amplitude according to the following procedures: Firstly, calculating the difference value between the health risk value P risk (t+Δt) at the moment of t+Δt and a system set threshold; calculating the difference between the training state comprehensive score S (t) and the system set optimal state score; And adjusting the training intensity according to the difference value between the health risk value P risk (t+Δt) at the time t+Δt and the system set threshold value, the difference value between the training state comprehensive score S (t) and the system set optimal state score, and increasing the training intensity adjusting force along with the increase of the difference value to finally obtain the training adjusting coefficient K adj (t) at the time t.
  6. 6. The biosensor-based real-time health status monitoring system according to claim 5, wherein the training intensity is adjusted by the training adjustment module, the adjusted training status integrated score is obtained by analyzing by the project status evaluation module, then the difference between the adjusted training status integrated score and the training status integrated score S (t) is calculated to obtain the status change score DeltaS, and the status change score DeltaS is combined with the t-moment training adjustment coefficient K adj (t) and the system set optimal status score for analysis, so as to quantify the adjustment amplitude of the t-moment individual fitness influence coefficient beta (t) and obtain the t+1-moment individual fitness influence coefficient.
  7. 7. The real-time health status monitoring system based on a biosensor according to claim 1, further comprising a visualization module for displaying training data of the athlete in real time and performing visual presentation, wherein the visualization module comprises a remote connection unit, and the coach and the athlete are connected to the system through a terminal device and the remote connection unit, view the monitoring data and receive an alarm.
  8. 8. The biosensor-based real-time health status monitoring system of claim 1, wherein said sensor module comprises a pre-processing unit for removing flexible sensor array noise, supplementing missing values, and simultaneously aligning physiological data with physical data in a time axis.

Description

Real-time health state monitoring system based on biosensor Technical Field The invention relates to the technical field of health monitoring, in particular to a real-time health state monitoring system based on a biosensor. Background Along with the continuous improvement of the professional degree of competitive sports, the demands of the professional athlete on data, intelligence and individuation in the training, spare combat and post-competition recovery processes are increasingly urgent. Athletes in different projects face different physical loads and state management challenges, meanwhile, the popularization of the Internet of things technology realizes real-time collection of multidimensional data, technical support is provided for data integration and analysis, and the health state monitoring system is pushed to develop in a cross-project adaptation and dynamic early warning direction. In this context, the development of health monitoring systems for professional athlete full cycle status management is becoming a industry necessity. At present, most systems acquire physiological data and physical data independently, and generally trigger an alarm only when indexes exceed a preset threshold, at the moment, athletes may be in a state close to injury, the system lacks the capability of predicting future risks in advance, training strategies cannot be dynamically adjusted according to the actual health state of the athletes, the training quality is reduced while potential safety hazards are increased, physiological load abnormality in training is often closely related to physical actions, but the causality relationship between the physiological data and the physical actions cannot be quantified in the traditional monitoring, the root cause of the problems is difficult to locate, and the monitoring quality of the system is low. Disclosure of Invention The present invention aims to provide a biosensor-based real-time health status monitoring system, which solves the problems set forth in the background art. In order to achieve the aim, the invention provides the technical scheme that the real-time health state monitoring system based on the biological sensor comprises a sensor module, a motion association module, a project state evaluation module, a risk early warning module, a training adjustment module and an optimization feedback module; The sensor module comprises a physiological sensing unit and a posture sensing unit, wherein the physiological sensing unit and the posture sensing unit acquire data through flexible sensors arranged on the body surface of an athlete to obtain physiological data and posture data; The motion association module is used for analyzing the change information of the physiological data and the physical state data along with time, evaluating the association between the physiological data and the physical state data, obtaining an association coefficient and reflecting the association strength between the two data; the project state evaluation module is used for analyzing the training state of each sports project by combining the individual adaptation condition of the athlete, the sports project index weight and the relevance coefficient to obtain a training state comprehensive value; the risk early warning module analyzes the health risk condition of the future time based on the change condition of the training state comprehensive value along with the time to obtain a health risk value, and judges whether the training intensity needs to be adjusted according to the health risk value; The training adjustment module adjusts the current training intensity based on the health risk value and the training state integrated value, and the optimization feedback module analyzes the data in the project state evaluation module based on the training state integrated value change condition after the training intensity adjustment. Optionally, the motion association module calculates the variation of each physiological data at first, sets a time interval, and compares the variation of each physiological data with the time interval to obtain the instantaneous variation rate of the physiological data; Calculating the variation of the physical data, adding a physiological response lag time according to different characteristics of the physiological data, ensuring the correlation accuracy between the physiological data and the physical data, and comparing the variation of the physical data with a time interval to obtain the instantaneous variation rate of the physical data; And finally, respectively comparing the instantaneous change rate of the physiological data and the instantaneous change rate of the physical state data with the standard instantaneous change rate set by the system, setting association weights according to the association strength between the physiological data and the physical state data and the individual difference of athletes, and introducing a time attenuation item to obt