Search

CN-122000047-A - Physical health monitoring method and system based on big data

CN122000047ACN 122000047 ACN122000047 ACN 122000047ACN-122000047-A

Abstract

The application discloses a physical health monitoring method and a physical health monitoring system based on big data, which relate to the technical field of intelligent sensors, wherein the method comprises the steps of acquiring a gesture data sequence related to physiological gestures in daily activities of a user, and extracting distribution characteristics of abnormal gestures based on the gesture data sequence; the method comprises the steps of determining a quantized value of accumulated pressure based on the distribution characteristics of abnormal gestures, judging a risk level of physiological health of a user based on the quantized value of the accumulated pressure if the quantized value of the accumulated pressure exceeds a preset accumulated pressure quantized threshold value, generating a trend index reflecting a pressure accumulation rule based on the risk level, carrying out weighted adjustment on the distribution characteristics of the abnormal gestures based on the trend index, and generating a health monitoring feedback sequence based on the adjusted abnormal gesture distribution characteristics.

Inventors

  • YU PINHAO

Assignees

  • 广东伟途教育科技有限公司

Dates

Publication Date
20260508
Application Date
20251231

Claims (10)

  1. 1. A physical health monitoring method based on big data, the method comprising: acquiring a gesture data sequence related to a physiological gesture in daily activities of a user, and extracting the distribution characteristics of abnormal gestures based on the gesture data sequence; Determining a quantized value of the accumulated pressure based on the distribution characteristics of the abnormal pose; If the quantized value of the accumulated pressure exceeds a preset accumulated pressure quantized threshold value, judging the risk level of the physiological health of the user based on the quantized value of the accumulated pressure, and generating a trend index reflecting the pressure accumulation rule based on the risk level; Based on the trend index, carrying out weighted adjustment on the distribution characteristics of the abnormal gestures, and determining triggering conditions of risk early warning based on the adjusted abnormal gesture distribution characteristics; and if the triggering condition of the risk early warning is met, generating a health monitoring feedback sequence according to the triggering condition and the trend index reflecting the pressure accumulation rule.
  2. 2. The method of claim 1, wherein the step of obtaining a sequence of gesture data related to a physiological gesture in a daily activity of the user and extracting a distribution feature of an abnormal gesture based on the sequence of gesture data comprises: acquiring the gesture data sequence through a sensor device; Processing the gesture data sequence in a time axis segment recording mode; and extracting the distribution characteristics of the abnormal gestures based on the processed gesture data sequence.
  3. 3. The method of claim 1, wherein the step of determining a quantized value of the cumulative pressure based on the distribution characteristics of the abnormal pose comprises: According to the distribution characteristics of the abnormal gestures, gesture fragments related to physiological loads are screened from a reference database constructed based on user history normal period data; Carrying out data smoothing processing on the attitude fragments; calculating to obtain fluctuation parameters and abnormal amplitudes based on the gesture fragments after the data smoothing treatment; a quantized value of the accumulated pressure is determined based on the fluctuation parameter and the anomaly magnitude.
  4. 4. The method of claim 1, wherein determining a risk level of physiological health of the user based on the quantified value of the cumulative pressure comprises: analyzing a rate of mode change of the quantized value of the accumulated pressure on a time axis; extracting periodic features based on the gesture data sequence; And based on the mode change rate, combining the distribution characteristics of the abnormal gestures and the periodic characteristics, and judging the risk level of the physiological health of the user through a preset risk level judging rule.
  5. 5. The method of claim 3, wherein the generating a trend indicator reflecting a pressure accumulation law based on the risk level comprises: based on the risk level, acquiring historical pressure distribution and load cycle data related to a biomechanical mechanism from a preset database; And integrating and analyzing the historical pressure distribution and the load period data through a data sequence fusion technology to obtain the trend index reflecting the pressure accumulation rule.
  6. 6. The method of claim 5, wherein the step of weighting the distribution characteristics of the abnormal poses based on the trend indicators and determining the triggering conditions for risk early warning based on the adjusted abnormal pose distribution characteristics comprises: acquiring the characteristics of abnormal load points based on the load period data; The distribution characteristics of the abnormal gestures are weighted and adjusted by combining the characteristics of the historical pressure distribution and the abnormal load point positions through the trend indexes; And determining the triggering condition of the risk early warning based on the distribution characteristics of the abnormal gesture after the weighting adjustment.
  7. 7. The method of claim 6, wherein if the triggering condition of the risk early warning is satisfied, the step of generating a health monitoring feedback sequence according to the triggering condition and the trend indicator reflecting a pressure accumulation law comprises: if the triggering condition of the risk early warning is met, generating an intervention measure serialization suggestion list aiming at a physiological structure according to the triggering condition and the trend index reflecting the pressure accumulation rule; Based on the intervention measure serialization suggestion list, combining the load period data and the trend index reflecting the pressure accumulation rule to obtain a personalized attitude adjustment optimization path; And generating the health monitoring feedback sequence based on the personalized attitude adjustment optimization path.
  8. 8. The method of claim 7, wherein the profile of the abnormal pose comprises a duration interval of the abnormal pose, the step of generating the health monitoring feedback sequence based on the personalized pose adjustment optimization path comprising: And adjusting an optimization path based on the personalized gesture, fusing the fluctuation parameter and the duration time interval of the abnormal gesture, and generating the health monitoring feedback sequence.
  9. 9. The method of claim 7, wherein the trend indicative of the pressure accumulation rule includes a long-term accumulation effect and a pressure change slope, and wherein generating the intervention measure serialization proposal list for the physiological structure based on the trigger condition and the trend indicative of the pressure accumulation rule includes: generating the intervention measure serialization suggestion list aiming at the physiological structure according to the triggering condition and the long-term accumulation effect; the step of obtaining the personalized attitude adjustment optimization path based on the intervention measure serialization suggestion list and combining the load period data and the trend index reflecting the pressure accumulation rule comprises the following steps: and based on the intervention measure serialization suggestion list, combining the load cycle data and the pressure change slope to acquire the personalized attitude adjustment optimization path.
  10. 10. A big data based physical health monitoring system, the system comprising: The feature acquisition module is used for acquiring a gesture data sequence related to the physiological gesture in the daily activities of the user and extracting the distribution features of the abnormal gesture based on the gesture data sequence; A quantized value determination module for determining a quantized value of the accumulated pressure based on the distribution characteristics of the abnormal pose; The risk level judging module is used for judging the risk level of the physiological health of the user based on the quantized value of the accumulated pressure if the quantized value of the accumulated pressure exceeds a preset accumulated pressure quantized threshold value, and generating a trend index reflecting the pressure accumulation rule based on the risk level; The adjusting module is used for carrying out weighted adjustment on the distribution characteristics of the abnormal gestures based on the trend indexes, and determining triggering conditions of risk early warning based on the adjusted abnormal gesture distribution characteristics; and the feedback sequence generation module is used for generating a health monitoring feedback sequence according to the triggering condition and the trend index reflecting the pressure accumulation rule if the triggering condition of the risk early warning is met.

Description

Physical health monitoring method and system based on big data Technical Field The application relates to the technical field of intelligent sensors, in particular to a physical health monitoring method and system based on big data. Background In modern society, physical health monitoring has become an important means for guaranteeing the quality of life of people and preventing chronic diseases. With the acceleration of life rhythm and the influence of bad habits such as sedentary sitting, the physical health problem is increasingly prominent, and especially in the aspects of spinal health, joint pressure and the like, a scientific method is needed to identify risks and provide intervention basis. The existing physical health monitoring method is lack of deep excavation on dynamic changes and long-term influences when facing complex human body postures and health relations, more focuses on surface symptoms, ignores deep association hidden behind daily behaviors, and particularly fails to effectively capture the regular characteristics of posture changes of individuals in different time periods, and lacks accuracy. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The application mainly aims to provide a constitution health monitoring method and system based on big data, and aims to solve the technical problems that the existing constitution health monitoring method focuses on surface symptoms more and lacks accuracy. In order to achieve the above purpose, the present application provides a physical health monitoring method based on big data, the method comprising: acquiring a gesture data sequence related to a physiological gesture in daily activities of a user, and extracting the distribution characteristics of abnormal gestures based on the gesture data sequence; Determining a quantized value of the accumulated pressure based on the distribution characteristics of the abnormal pose; If the quantized value of the accumulated pressure exceeds a preset accumulated pressure quantized threshold value, judging the risk level of the physiological health of the user based on the quantized value of the accumulated pressure, and generating a trend index reflecting the pressure accumulation rule based on the risk level; Based on the trend index, carrying out weighted adjustment on the distribution characteristics of the abnormal gestures, and determining triggering conditions of risk early warning based on the adjusted abnormal gesture distribution characteristics; and if the triggering condition of the risk early warning is met, generating a health monitoring feedback sequence according to the triggering condition and the trend index reflecting the pressure accumulation rule. In one embodiment, the step of acquiring a gesture data sequence related to a physiological gesture in a daily activity of the user and extracting a distribution feature of an abnormal gesture based on the gesture data sequence includes: acquiring the gesture data sequence through a sensor device; Processing the gesture data sequence in a time axis segment recording mode; and extracting the distribution characteristics of the abnormal gestures based on the processed gesture data sequence. In an embodiment, the step of determining a quantized value of the accumulated pressure based on the distribution characteristics of the abnormal pose includes: According to the distribution characteristics of the abnormal gestures, gesture fragments related to physiological loads are screened from a reference database constructed based on user history normal period data; Carrying out data smoothing processing on the attitude fragments; calculating to obtain fluctuation parameters and abnormal amplitudes based on the gesture fragments after the data smoothing treatment; a quantized value of the accumulated pressure is determined based on the fluctuation parameter and the anomaly magnitude. In an embodiment, the determining the risk level of the physiological health of the user based on the quantized value of the accumulated pressure comprises: analyzing a rate of mode change of the quantized value of the accumulated pressure on a time axis; extracting periodic features based on the gesture data sequence; And based on the mode change rate, combining the distribution characteristics of the abnormal gestures and the periodic characteristics, and judging the risk level of the physiological health of the user through a preset risk level judging rule. In an embodiment, the generating a trend indicator reflecting a pressure accumulation rule based on the risk level includes: based on the risk level, acquiring historical pressure distribution and load cycle data related to a biomechanical mechanism from a preset database; And integrating and analyzing the historical pressure distribu