CN107169307A - Health risk assessment method and apparatus - Google Patents
Health risk assessment method and apparatus Download PDFInfo
- Publication number
- CN107169307A CN107169307A CN201710549362.XA CN201710549362A CN107169307A CN 107169307 A CN107169307 A CN 107169307A CN 201710549362 A CN201710549362 A CN 201710549362A CN 107169307 A CN107169307 A CN 107169307A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- module
- risk
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention provides a kind of health risk assessment method and apparatus, and this method at least includes data collection steps and risk analysis step；Data collection steps, at least one user's physiology sign data of collection, and preserve the data；Risk analysis step, according to the data assessment data level, the data level calculates the risk factor that user falls ill with reference to the weighing factor of the data.The health risk assessment method of the present invention, the reliable disease risks assessment result of physiology sign data output that user terminal is gathered can be combined, so that using the device of the health risk assessment method, accurate, reliable, portable health service can be provided the user.
Description
Technical field
The present invention relates to Computer Applied Technology, more particularly to a kind of health risk assessment method and apparatus.
Background technology
Medical research shows that the change of the index such as human heart rate, blood pressure, blood oxygen amount and sleep quality and index is to assessing body
Body phase related disorders, degree of fatigue and health evaluating have important references value.
But Intelligent worn device can only realize some simple Sport Administration functions at present, equipment be unable to data storage or
Memory capacity is limited, still cannot be used for the health analysis of medical level, to vast in chronic disease human patients or potential slow
Property disease patient groups, how with reference to intelligent terminal, the portable reliable health service of enjoyment is not yet proposed effective at present
Solution.
The content of the invention
The invention provides a kind of health risk assessment method and apparatus, with reference to the gathered data of intelligent terminal, Ke Yiwei
User provides portable reliable medical treatment ＆ health risk assessment service.
The present invention provides a kind of health risk assessment method, including：At least include data collection steps and risk analysis is walked
Suddenly；Data collection steps, at least one user's physiology sign data of collection, and preserve the data；Risk analysis step, according to
Data assessment data level, the weighing factor of data level combination data calculates the risk factor of user's morbidity.
The present invention also provides a kind of health risk assessment device, at least including data acquisition module, memory module and risk
Analysis module；Data acquisition module, at least one user's physiology sign data of collection, and store data in the storage mould
Block；Risk analysis module, the data assessment data level stored according to memory module, the weighing factor of data level combination data
Calculate the risk factor of user's morbidity.
The health risk assessment method that the present invention is provided, the physiology sign data that this method can combine user terminal collection is defeated
Go out reliable health risk assessment result so that the device of the application health risk assessment method, can provide the user it is accurate,
Reliably, portable health service.Seen a doctor by appraisal procedure output result automatic early-warning risk, instead of existing body not
Seen a doctor again after suitable, patient can be allowed to be treated at the initial stage of a disease, reduced patient's treatment cost, improve the body of existing medical services
Test sense and ageing.Physiology sign data when intelligent terminal can preserve body abnormality simultaneously is used for diagnosis so that doctor
Life can more accurately understand the condition of user to improve the accuracy of diagnosis.
Brief description of the drawings
Fig. 1 is the flow chart of health risk assessment method of the present invention.
Fig. 2 is the instant methods of risk assessments of S102 in Fig. 1 of the present invention；
Fig. 3 is the S102 risk profile appraisal procedures in Fig. 1 of the present invention；
Fig. 4 is the forecast model construction method of prediction index in Fig. 3；
Fig. 5 is the structural representation of health analysis apparatus for evaluating of the present invention.
Embodiment
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with the accompanying drawings with specific embodiment pair
The present invention is described in detail.
As shown in figure 1, the invention discloses a kind of health risk assessment method, at least including data collection steps and risk
Analytical procedure.
Data collection steps (S101), at least one user's physiology sign data of collection, and preserve the data；
Risk analysis step (S102), according to the data assessment data level, the data level is with reference to the data
Weighing factor calculate user morbidity risk factor.
The onset risk of user is judged according to risk index, index is higher, and onset risk is bigger.
The health risk assessment method of the present invention, can be by gathering user's physiology sign data in real time, and is stored in end
End.By long-term data accumulation, the data of risk analysis module analysis storage, according to physiology sign data variation tendency and different
Often situations such as, can be caused by some chronic diseases of Accurate Prediction such as angiocardiopathy, and relevant disease by analysis and evaluation
The risk of chronic disease complication such as cardiovascular complication, and give indicating risk, it is proposed that user carries out prevention to burst disease
Prepare.
S102 steps in Fig. 1, as shown in Fig. 2 can comprise the following steps, to assess the morbidity of cardiovascular patient i.e.
When risk factor：
Step 201：User's core signal ECG, blood pressure BP and blood oxygen SpO that sensor device module is gathered 3 indexs
Data are contrasted with user's normal index data, assess the instant grade of acquisition index data, remember H1c,S1c,B1cRefer to for 3
Target immediate assessment grade.
User's normal index data refer to the similar achievement data for being determined as user's body health through risk analysis module.This
Application is to H1c,S1c,B1cGrade classification do not limit, set according to the actual requirements.
Step 202：Calculate instant risk assessment coefficients R isk1=A { H1c,S1c,B1c, wherein weighing factor vector A
={ a1,a2,a3}.Weighing factor vector refers to statistical result setting, or is set by medical practitioner according to the health of user
It is fixed.
Instant risk assessment can realize the real-time monitoring to user's physiology sign data, and the body that user can be monitored in real time is different
Often, user is reminded to see a doctor in time.Physiology sign data when intelligent terminal can preserve body abnormality simultaneously is used for diagnosis,
Doctor is allowd more accurately to understand the condition of user to improve the accuracy of diagnosis.
S102 steps in Fig. 1, as shown in figure 3, can also comprise the following steps, to assess the morbidity of cardiovascular patient
Forecasting risk coefficient：
Step 301：The core signal ECG of user, blood pressure BP and the blood oxygen SpO that are stored based on memory module 3 indexs
Data, numerical value of prediction 3 indexs of user in intended duration.
Intended duration is included in short term with for a long time, can be set by user according to self-demand.
Step 302：By the way that 3 indexs are predicted with numerical value and normal index data comparison, assessment prediction index value etc.
Level, remembers H2c,S2c,B2cFor the forecast assessment grade of 3 indexs.
Step 303：Calculation risk assessment prediction coefficients R isk2=A { H2c,S2c,B2c, wherein weighing factor vector A
={ a1,a2,a3}。
The intelligent terminal of the application can not only realize instant risk assessment, for some potential chronic diseases, also may be used
With the Secular Variation Tendency gathered by sensor assembly, onset risk is predicted, warning in advance user takes corresponding prevention to arrange
Apply, or see a doctor in advance.
Further, the prediction index numerical value in Fig. 3 in step S301, can use existing forecast model, also may be used
With as shown in figure 4, including：
Step 401：Build model, it is assumed that the numerical value L of the sample index of sample L ith collectioni, the p of being expressed as over (p
≤ i) secondary collection numerical value linear combination, add the white noise of ith, i.e.,：
Li=θ0+φ1Li-1+…+φpLi-p+ai, wherein { ai, i=0, ± 1, ± 2 ... } and it is white noise, φ1, φ2...,
φpFor constant coefficient, θ0For constant.
Step 402：Based on sample data, constant coefficient φ is resolved1, φ2..., φpAnd θ0；
Step 403：Prediction index numerical value, it is known that k user sample index data, the index value that prediction kth is+l times, order
I=k+l, the index value for obtaining kth+l is：
Lk+l=θ0+φ1Lk+l-1+φ2Lk+l-2+…+φpLk+l-p+ak+l。
In the method for the invention, stored during data storage with preset data bag form；
Preset data bag form is encoded by the form of packet header addend evidence, and packet header includes start bit, device number, time
Stamp, physiology sign and status data name and check bit；Start bit is used to distinguish every segment data bag；Device number is used to distinguish display use
The distinct device at family；Timestamp is used to record acquisition time；Physiology sign data name is used for the life for distinguishing different sensors collection
Sign data and the different status information of user are managed, check bit is used for whether verification data transmission to malfunction.
In the method for the invention, risk analysis step also includes sleep state detection, and sleep state detection at least includes
Following steps：
Step 501：The attitude data of user is analyzed, the length of one's sleep and deep sleep time of user is extracted；
Step 502：According to user's heart rate HR, the blood in the length of one's sleep of user and deep sleep time, and 2 times
Oxygen SpO data, judge user's sleep state.
Wherein, step 501 may comprise steps of again：
Step 501-1, pass through attitude detection automatically turn on sleep state detect；
Step 501-2, start timing of being slept to user, and gather acceleration transducer data and heart rate, blood oxygen transducer
The heart rate of collection, blood oxygen concentration data；
Step 501-3, the data to the real-time collection of acceleration transducer are analyzed, and judge user's posture.In acceleration
When gathered data is steady for a long time, starts to start timing to user's progress deep sleep, once user has attitudes vibration, stop deep
Degree sleep timing；
Step 501-4, during sleep procedure and deep sleep, respectively timing pass through heart rate, blood oxygen transducer gather
User's heart rate, oximetry data；
After step 501-5, user's revival, terminate sleep state monitoring function automatically by attitude detection.By to posture
With heart rate data analysis, the length of one's sleep on that night amount and deep sleep time quantum, and blood oxygen concentration and the heart in sleep procedure are extracted
Rate.
In the method for the invention, risk analysis step also includes fatigue state detection, and fatigue state detection at least includes
Following steps：
Step 601：The core signal ECG of memory module storage and heart rate variability signals HRV fluctuation characteristic are detected, by ripple
Dynamic feature corresponding conversion is endurance ratio initial value；
Step 602：By endurance ratio initial value and user's heart rate HR, blood oxygen SpO data, user's sleep state, pass through weighting
Calculating obtains final endurance ratio.
The health risk assessment method that the present invention is provided, the physiology sign data that this method can combine user terminal collection is defeated
Go out reliable health risk assessment result so that the intelligent terminal of the application health risk assessment method, can provide the user
Accurately, reliable, portable health service.Seen a doctor by appraisal procedure output result automatic early-warning risk, instead of existing
Seen a doctor again after uncomfortable, patient can be allowed to be treated at the initial stage of a disease, reduce patient's treatment cost, improve existing medical treatment clothes
The experience sense of business and ageing.Physiology sign data when intelligent terminal can preserve body abnormality simultaneously is used for diagnosis,
Doctor is allowd more accurately to understand the condition of user to improve the accuracy of diagnosis.
As shown in figure 5, the invention also discloses a kind of health risk assessment device, at least including data acquisition module, depositing
Store up module and risk analysis module.
Data acquisition module, at least one user's physiology sign data of collection, and store data in memory module.Risk
Analysis module, the data assessment data level stored according to memory module, the data level is weighed with reference to the influence of the data
The risk factor of re-computation user morbidity.
The health risk assessment device of the present invention can be intelligent watch, or bracelet, or other wearable devices, can also
It is the equipment component in user terminal.
For example, the monitoring in real time of the device of the present invention suffers from the application note of primary cardiac illness user, including：
Step A-1, device sensor assembly gather the core signal ECG data of EGC sensor, blood oxygen transducer in real time
Heart rate HR, the blood pressure BP and blood oxygen SpO concentration datas of collection；
Step A-2, risk analysis module are analyzed the heart rate, blood pressure and oximetry data that gather in real time；Once, heart rate
HR data exceptions, blood oxygen SpO concentration is drastically reduced, and blood pressure HR changes the feature for meeting primary heart, assesses user's morbidity
Risk factor, if it is decided that user's primary heart attack, in fact it could happen that the emergency such as heart arrest, then pass through dress
Display screen is put to show assessment result；
Step A-3 or, further, device is rescued to associated mechanisms and affiliated person's request medical treatment by communication module
Help, and user's electrocardiogram (ECG) data of collection is sent to associated mechanisms, report user's real-time status.
Also, for example, apparatus of the present invention monitor the application note of the serious accidental falls of old user in real time：
Step B-1, device sensor assembly gather user's attitude data of acceleration transducer in real time；
Step B-2, when there is violent change in risk analysis module monitors to user's posture, while in violent posture
After change, user's attitudes vibration very little, or without attitudes vibration, illustrate that user may fall down；
Step B-3, risk analysis module analysis same time sensor assembly gather user's heart rate HR, blood pressure BP signs in real time
Data variation, if data variation occurs abnormal, illustrates that user happens suddenly accidental falls, by device display screen by assessment result
Display；
Step B-5 or, further, device is rescued to associated mechanisms and affiliated person's request medical treatment by communication module
Help, and the physiology sign data of collection is sent to associated mechanisms, report user's real-time status.
Indicated above, device of the invention can monitor the user with chronic burst disease, for example high blood of burst disease in real time
Pressure, heart disease etc.；Or old user, burst fortuitous event such as falls down.Device passes through the posture to user and physiology sign
Data are monitored in real time, once user has, burst disease or burst are unexpected, and device can be by urgency communication function, by user
Situation is sent to associated mechanisms or affiliated person, to ask corresponding medical measure and service.
Risk analysis module, as microcontroller, analyzes gathered data using dsp chip；Memory module uses SPI Nand
Flash is as storage device, and the type chip volume is small, the characteristics of pin is less and capacity is big, can be with longer-term storage gathered data.
The massive store design of memory module, storage user data can be gathered for a long time, makes intelligent terminal to the chronic disease such as heart
The prediction of vascular diseases is more accurate.
In this application, user's physiology sign data includes posture, heart rate HR, blood oxygen SpO, blood pressure BP, core signal ECG
With heart rate variability signals HRV etc..
There are 5 class sensors to be used to detect user's posture and collection physiology sign data, wherein acceleration in sensor assembly
Sensor is used to detect user's posture and associated motion information；Blood oxygen, heart rate sensor are used to gather user's blood oxygen SpO, heart rate
HR data, while calculating blood pressure BP data；Infrared body temperature sensor is used to gather user's temperature data；EGC sensor is used for
The core signal ECG data of user are gathered, by extracting the section of the QRS wave in the core signal ECG that EGC sensor is gathered, point
Separation standard is poor between each cycle R crest values for the signal for analysing the QRS complex wave band gathered every time, reflects heart rate with this
Variability Signals HRV.
Intelligent terminal gathers user's physiology sign data in real time, and is packaged into packet with certain form, is stored in
Store up module.Data packet format, is encoded according to the form of packet header addend evidence, and its middle wrapping head includes start bit, device number, time
Stamp, physiology sign and status data name and check bit.Start bit is used to distinguish every segment data bag；Device number is used to distinguish display use
The distinct device at family；Timestamp is used to record acquisition time；Physiology sign data name is mainly used in distinguishing different sensors collection
Physiology sign data and the different status information of user, electrocardiogram (ECG) data or heart rate data when such as distinguishing the data of collection
Deng；Check bit is used for whether verification data transmission to malfunction.
Further, data are first pre-processed before packing, or before storing, with rejecting abnormalities data.
In the apparatus of the present, the also instant risk analysis module of risk analysis module, the module includes：
Instant grade evaluation module：User's core signal ECG, blood pressure BP and the blood oxygen SpO that sensor device module is gathered
3 achievement datas contrasted with user's normal index data, the instant grade of evaluation index numerical value, remember H1c,S1c,B1cFor
The immediate assessment grade of 3 indexs；
Instant Risk Calculation module：Calculate instant risk assessment coefficients R isk1=A { H1c,S1c,B1c, wherein influenceing
Weight vectors A={ a1,a2,a3}。
In the apparatus of the present, risk analysis module also includes risk profile module, and risk profile module at least includes
With lower module：
Prediction module：The core signal ECG of user, blood pressure BP and the blood oxygen SpO that are stored based on memory module 3 indexs
Data, numerical value of prediction 3 indexs of user in intended duration；
Forecast ratings evaluation module：By predicting numerical value and normal index data comparison, assessment prediction index to 3 indexs
The grade of numerical value, remembers H2c,S2c,B2cFor the forecast assessment grade of 3 indexs；
Risk profile computing module：Calculation risk assessment prediction coefficients R isk2=A { H2c,S2c,B2c, wherein influenceing
Weight vectors A={ a1,a2,a3}。
Further, prediction index numerical value includes：
Model construction module：Build model, the numerical value L of the sample index of sample L ith collectioni, the p of being expressed as over
The linear combination of the numerical value of (p≤i) secondary collection, adds the white noise of ith, i.e.,：
Li=θ0+φ1Li-1+…+φpLi-p+ai, wherein { ai, i=0, ± 1, ± 2 ... } and it is white noise, φ1, φ2...,
φpFor constant coefficient, θ0For constant；
Model coefficient resolves module：Based on sample data, constant coefficient φ is resolved1, φ2..., φpAnd θ0；
Model prediction module：Prediction index numerical value, it is known that k user sample index data, the index number that prediction kth is+l times
Value, makes i=k+l, the index value for obtaining kth+l is：
Lk+l=θ0+φ1Lk+l-1+φ2Lk+l-2+…+φpLk+l-p+ak+l。
An alternative embodiment of the invention, risk analysis module also includes sleep state detection module, specifically includes：
Length of one's sleep detection module：The attitude data of user is analyzed, the length of one's sleep and deep sleep time of user is extracted；
Sleep state analysis module：According to the user in the length of one's sleep of user and deep sleep time, and 2 times
Heart rate HR, blood oxygen SpO data, judge user's sleep state.
An alternative embodiment of the invention, risk analysis module also includes fatigue state detection module, specifically includes：
Endurance ratio initial value computing module：Device gathers user's electrocardiosignal (ECG), HRV by sensor to be believed
Number (HRV), heart rate and oximetry data.The core signal ECG and heart rate variability letter of risk analysis module detection memory module storage
Number HRV fluctuation characteristic, is endurance ratio initial value by fluctuation characteristic corresponding conversion.
Endurance ratio COMPREHENSIVE CALCULATING module：Risk analysis module by endurance ratio initial value and heart rate HR, blood oxygen SpO data,
User's sleep state, weighted calculation obtains final endurance ratio.
In addition to Fig. 5, device of the invention can be combined with platform or server, obtain more function or services, now
Terminal is used as the acquisition terminal of a health service platform, physiology body of the collection for Platform Analysis assessment user health situation
Levy data；And for servicing user's medical diagnosis.Terminal can be connected by bluetooth with smart mobile phone, and the data of collection are sent out
It is sent in the equipment such as smart mobile phone, then is transmitted data to by internet on Platform Server, or mobile phone is directly by collection
Data are sent on Platform Server.
The foregoing is merely illustrative of the preferred embodiments of the present invention, not to limit the present invention scope, it is all
Within the spirit and principle of technical solution of the present invention, any modification, equivalent substitution and improvements done etc. should be included in this hair
Within bright protection domain.
Claims (16)
1. a kind of health risk assessment method, it is characterised in that at least including data collection steps and risk analysis step；
Data collection steps, at least one user's physiology sign data of collection, and preserve the data；
Risk analysis step, according to the data assessment data level, weighing factor of the data level with reference to the data
Calculate the risk factor of user's morbidity.
2. according to the method described in claim 1, it is characterised in that user's physiology sign data include posture, heart rate HR,
Blood oxygen SpO, blood pressure BP, core signal ECG and heart rate variability signals HRV.
3. method according to claim 2, it is characterised in that risk analysis step includes：
Step 201：User's core signal ECG, blood pressure BP and blood oxygen SpO that sensor device module is gathered 3 achievement datas
Contrasted with user's normal index data, assess the instant grade H1 of the index valuec,S1c,B1c；
Step 202：Calculate instant risk assessment coefficients R isk1=A { H1c,S1c,B1c, wherein weighing factor vector A={ a1,
a2,a3}。
4. method according to claim 2, it is characterised in that the risk analysis step also includes：
Step 301：3 of the core signal ECG of the user, blood pressure BP and the blood oxygen SpO stored based on the memory module
Achievement data, numerical value of 3 indexs in intended duration described in prediction user；
Step 302：By predicting numerical value and normal index data comparison to 3 indexs, the prediction index numerical value is assessed
Grade, remember H2c,S2c,B2cFor the forecast assessment grade of 3 indexs；
Step 303：Calculation risk assessment prediction coefficients R isk2=A { H2c,S2c,B2c, wherein weighing factor vector A={ a1,
a2,a3}。
5. method according to claim 4, it is characterised in that 3 indexs are in intended duration described in the prediction user
Numerical value include：
Step 401：Build model, the numerical value L of the sample index of sample L ith collectioni, the p of being expressed as over (p≤i) is secondary to be adopted
The linear combination of the numerical value of collection, adds the white noise of ith, i.e.,：
Li=θ0+φ1Li-1+…+φpLi-p+ai, wherein { ai, i=0, ± 1, ± 2 ... } and it is white noise, φ1, φ2..., φpFor
Constant coefficient, θ0For constant；
Step 402：Based on sample data, constant coefficient φ is resolved1, φ2..., φpAnd θ0；
Step 403：Prediction index numerical value, it is known that k user sample index data, the index value that prediction kth is+l times, makes i=k
+ l, the index value for obtaining kth+l is：
Lk+l=θ0+φ1Lk+l-1+φ2Lk+l-2+…+φpLk+l-p+ak+l。
6. according to the method described in claim 1, it is characterised in that stored during the data storage with preset data bag form；
The preset data bag form is encoded by the form of packet header addend evidence, the packet header include start bit, device number, when
Between stamp, physiology sign and status data name and check bit；The start bit is used to distinguish every segment data bag；The device number is used for
Distinguish the distinct device for showing user；The timestamp is used to record acquisition time；The physiology sign data name is used to distinguish
The physiology sign data and the different status information of user of different sensors collection, the check bit are transmitted for verification data
Whether malfunction.
7. method according to claim 2, it is characterised in that the risk analysis step also includes sleep state and detected,
The sleep state detection at least comprises the following steps：
Step 501：The attitude data of the user is analyzed, the length of one's sleep and deep sleep time of user is extracted；
Step 502：According to user's heart rate HR in the length of one's sleep of user and deep sleep time, and 2 time, blood
Oxygen SpO data, judge user's sleep state.
8. method according to claim 7, it is characterised in that the risk analysis step also includes fatigue state and detected,
The fatigue state detection at least comprises the following steps：
Step 601：The core signal ECG of the memory module storage and heart rate variability signals HRV fluctuation characteristic are detected, by institute
Fluctuation characteristic corresponding conversion is stated for endurance ratio initial value；
Step 602：By endurance ratio initial value and user's heart rate HR, blood oxygen SpO data and user's sleep state, pass through weighting
Calculating obtains final endurance ratio.
9. a kind of health risk assessment device, it is characterised in that at least including data acquisition module, memory module and risk analysis
Module；
Data acquisition module, at least one user's physiology sign data of collection, and store the data in the memory module；
Risk analysis module, the data level according to the data assessment of memory module storage, the data level is combined
The weighing factor of the data calculates the risk factor of user's morbidity.
10. device according to claim 9, it is characterised in that user's physiology sign data includes posture, heart rate
HR, blood oxygen SpO, blood pressure BP, core signal ECG and heart rate variability signals HRV.
11. device according to claim 10, it is characterised in that the risk analysis module includes instant risk analysis mould
Block, the instant risk analysis module at least includes：
Instant grade evaluation module：3 of user's core signal ECG, blood pressure BP and the blood oxygen SpO that sensor device module is gathered
Achievement data is contrasted with user's normal index data, assesses the instant grade H1 of the index valuec,S1c,B1c；
Instant Risk Calculation module：Calculate instant risk assessment coefficients R isk1=A { H1c,S1c,B1c, wherein weighing factor
Vectorial A={ a1,a2,a3}。
12. device according to claim 10, it is characterised in that the risk analysis module also includes risk profile mould
Block, the risk profile module at least includes：
Prediction module：3 of the core signal ECG of the user, blood pressure BP and the blood oxygen SpO stored based on the memory module
Achievement data, numerical value of 3 indexs in intended duration described in prediction user；
Forecast ratings evaluation module：By predicting numerical value and normal index data comparison to 3 indexs, the prediction is assessed
The grade of index value, remembers H2c,S2c,B2cFor the forecast assessment grade of 3 indexs；
Risk profile computing module：Calculation risk assessment prediction coefficients R isk2=A { H2c,S2c,B2c, wherein weighing factor
Vectorial A={ a1,a2,a3}。
13. device according to claim 12, it is characterised in that 3 indexs are in intended duration described in the prediction user
Interior numerical value includes：
Model construction module：Build model, the numerical value L of the sample index of sample L ith collectioni, the p of being expressed as over (p≤i)
The linear combination of the numerical value of secondary collection, adds the white noise of ith, i.e.,：
Li=θ0+φ1Li-1+…+φpLi-p+ai, wherein { ai, i=0, ± 1, ± 2 ... } and it is white noise, φ1, φ2..., φpFor
Constant coefficient, θ0For constant；
Model coefficient resolves module：Based on sample data, constant coefficient φ is resolved1, φ2..., φpAnd θ0；
Model prediction module：Prediction index numerical value, it is known that k user sample index data, the index value that prediction kth is+l times,
I=k+l is made, the index value for obtaining kth+l is：
Lk+l=θ0+φ1Lk+l-1+φ2Lk+l-2+…+φpLk+l-p+ak+l。
14. device according to claim 9, it is characterised in that stored during the data storage with preset data bag form；
The preset data bag form is encoded by the form of packet header addend evidence, the packet header include start bit, device number, when
Between stamp, physiology sign and status data name and check bit；The start bit is used to distinguish every segment data bag；The device number is used for
Distinguish the distinct device for showing user；The timestamp is used to record acquisition time；The physiology sign data name is used to distinguish
The physiology sign data and the different status information of user of different sensors collection, the check bit are transmitted for verification data
Whether malfunction.
15. device according to claim 10, it is characterised in that the risk analysis module also includes sleep state and detected
Module, the sleep state detection module at least includes：
Length of one's sleep detection module：The attitude data of the user is analyzed, the length of one's sleep and deep sleep time of user is extracted；
Sleep state analysis module：According to the user in the length of one's sleep of user and deep sleep time, and 2 time
Heart rate HR, blood oxygen SpO data, judge user's sleep state.
16. device according to claim 15, it is characterised in that the risk analysis module also includes fatigue state and detected
Module, the fatigue state detection module at least includes：
Endurance ratio initial value computing module：Detect the core signal ECG and heart rate variability signals HRV of memory module storage
Fluctuation characteristic, is endurance ratio initial value by the fluctuation characteristic corresponding conversion；
Endurance ratio COMPREHENSIVE CALCULATING module：Endurance ratio initial value and user's heart rate HR, blood oxygen SpO data and the user are slept
State, final endurance ratio is obtained by weighted calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710549362.XA CN107169307A (en) | 2017-07-07 | 2017-07-07 | Health risk assessment method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710549362.XA CN107169307A (en) | 2017-07-07 | 2017-07-07 | Health risk assessment method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107169307A true CN107169307A (en) | 2017-09-15 |
Family
ID=59823029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710549362.XA Pending CN107169307A (en) | 2017-07-07 | 2017-07-07 | Health risk assessment method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169307A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767956A (en) * | 2017-10-27 | 2018-03-06 | 秦皇岛市惠斯安普医学系统股份有限公司 | A kind of health risk assessment and management method based on biological electricity induction technology |
| CN109620194A (en) * | 2018-12-12 | 2019-04-16 | 泰康保险集团股份有限公司 | Heart rate detection processing method, device, medium and electronic equipment |
| CN109859844A (en) * | 2018-12-26 | 2019-06-07 | 江苏恒宝智能系统技术有限公司 | A kind of wearable device, human health danger forecasting system and prediction technique |
| CN109961831A (en) * | 2019-03-29 | 2019-07-02 | 首都医科大学附属北京友谊医院 | A kind of acquisition methods and system of Children with Renal stone operation risk data |
| CN110101382A (en) * | 2019-03-27 | 2019-08-09 | 南京信息职业技术学院 | Risk monitoring device based on ECG signal analysis |
| CN110808102A (en) * | 2019-11-01 | 2020-02-18 | 广州红腾文化科技有限公司 | Information pushing method, system and terminal of health platform |
| CN110929988A (en) * | 2019-10-28 | 2020-03-27 | 广州柏颐信息科技有限公司 | Intelligent analysis method, system and device for care level and storage medium |
| CN111009328A (en) * | 2019-12-25 | 2020-04-14 | 新绎健康科技有限公司 | Regional population health condition assessment method and device |
| CN112885469A (en) * | 2021-02-01 | 2021-06-01 | 中国科学院苏州生物医学工程技术研究所 | Method and system for monitoring vital signs of chronic disease population |
| CN113140323A (en) * | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Health portrait generation method, system, medium and server |
| CN113257418A (en) * | 2021-03-29 | 2021-08-13 | 广州科克里特生命科技有限公司 | Risk detection system and method for low back pain |
| CN114098655A (en) * | 2022-01-25 | 2022-03-01 | 慕思健康睡眠股份有限公司 | Intelligent sleep risk monitoring method and system |
| CN114631945A (en) * | 2022-03-10 | 2022-06-17 | 南通大学附属医院 | Intracardiac branch of academic or vocational study intervention postoperative limbs nursing device based on big data |
| CN116110584A (en) * | 2023-02-23 | 2023-05-12 | 江苏万顶惠康健康科技服务有限公司 | Human health risk assessment early warning system |
| CN116936104A (en) * | 2023-09-15 | 2023-10-24 | 广东恒腾科技有限公司 | Health detector data analysis system and method based on artificial intelligence |
| CN116940990A (en) * | 2021-03-02 | 2023-10-24 | 株式会社花花 | Health management system |
| CN117064350A (en) * | 2023-08-18 | 2023-11-17 | 暨南大学附属第一医院（广州华侨医院） | Safety detection and intelligent evaluation system |
| CN118380159A (en) * | 2024-06-20 | 2024-07-23 | 湘江实验室 | Multi-user real-time collaboration system based on meta universe |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739501A (en) * | 2008-11-04 | 2010-06-16 | 财团法人资讯工业策进会 | Identification system and method for risk degree of sickees |
| CN103778312A (en) * | 2012-10-24 | 2014-05-07 | 中兴通讯股份有限公司 | Remote home health care system |
| CN105512505A (en) * | 2016-01-19 | 2016-04-20 | 宇龙计算机通信科技(深圳)有限公司 | Health prompting method and terminal equipment |
| CN105534503A (en) * | 2016-02-01 | 2016-05-04 | 金昌红 | Old people heart rate monitoring and locating system and method |
| CN105912870A (en) * | 2016-04-21 | 2016-08-31 | 张明飞 | Portable multi-sensor monitoring medical system |
| CN106725382A (en) * | 2016-12-28 | 2017-05-31 | 天津众阳科技有限公司 | Sleep state judgement system and method based on action and HRV measurements |
-
2017
- 2017-07-07 CN CN201710549362.XA patent/CN107169307A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739501A (en) * | 2008-11-04 | 2010-06-16 | 财团法人资讯工业策进会 | Identification system and method for risk degree of sickees |
| CN103778312A (en) * | 2012-10-24 | 2014-05-07 | 中兴通讯股份有限公司 | Remote home health care system |
| CN105512505A (en) * | 2016-01-19 | 2016-04-20 | 宇龙计算机通信科技(深圳)有限公司 | Health prompting method and terminal equipment |
| CN105534503A (en) * | 2016-02-01 | 2016-05-04 | 金昌红 | Old people heart rate monitoring and locating system and method |
| CN105912870A (en) * | 2016-04-21 | 2016-08-31 | 张明飞 | Portable multi-sensor monitoring medical system |
| CN106725382A (en) * | 2016-12-28 | 2017-05-31 | 天津众阳科技有限公司 | Sleep state judgement system and method based on action and HRV measurements |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107767956A (en) * | 2017-10-27 | 2018-03-06 | 秦皇岛市惠斯安普医学系统股份有限公司 | A kind of health risk assessment and management method based on biological electricity induction technology |
| CN109620194A (en) * | 2018-12-12 | 2019-04-16 | 泰康保险集团股份有限公司 | Heart rate detection processing method, device, medium and electronic equipment |
| CN109859844A (en) * | 2018-12-26 | 2019-06-07 | 江苏恒宝智能系统技术有限公司 | A kind of wearable device, human health danger forecasting system and prediction technique |
| CN110101382A (en) * | 2019-03-27 | 2019-08-09 | 南京信息职业技术学院 | Risk monitoring device based on ECG signal analysis |
| CN109961831A (en) * | 2019-03-29 | 2019-07-02 | 首都医科大学附属北京友谊医院 | A kind of acquisition methods and system of Children with Renal stone operation risk data |
| CN110929988A (en) * | 2019-10-28 | 2020-03-27 | 广州柏颐信息科技有限公司 | Intelligent analysis method, system and device for care level and storage medium |
| CN110808102A (en) * | 2019-11-01 | 2020-02-18 | 广州红腾文化科技有限公司 | Information pushing method, system and terminal of health platform |
| CN111009328A (en) * | 2019-12-25 | 2020-04-14 | 新绎健康科技有限公司 | Regional population health condition assessment method and device |
| CN113140323A (en) * | 2020-12-31 | 2021-07-20 | 上海明品医学数据科技有限公司 | Health portrait generation method, system, medium and server |
| CN112885469A (en) * | 2021-02-01 | 2021-06-01 | 中国科学院苏州生物医学工程技术研究所 | Method and system for monitoring vital signs of chronic disease population |
| CN116940990A (en) * | 2021-03-02 | 2023-10-24 | 株式会社花花 | Health management system |
| CN113257418A (en) * | 2021-03-29 | 2021-08-13 | 广州科克里特生命科技有限公司 | Risk detection system and method for low back pain |
| CN114098655B (en) * | 2022-01-25 | 2022-04-26 | 慕思健康睡眠股份有限公司 | Intelligent sleep risk monitoring method and system |
| CN114098655A (en) * | 2022-01-25 | 2022-03-01 | 慕思健康睡眠股份有限公司 | Intelligent sleep risk monitoring method and system |
| CN114631945A (en) * | 2022-03-10 | 2022-06-17 | 南通大学附属医院 | Intracardiac branch of academic or vocational study intervention postoperative limbs nursing device based on big data |
| CN116110584A (en) * | 2023-02-23 | 2023-05-12 | 江苏万顶惠康健康科技服务有限公司 | Human health risk assessment early warning system |
| CN116110584B (en) * | 2023-02-23 | 2023-09-22 | 江苏万顶惠康健康科技服务有限公司 | Human health risk assessment early warning system |
| CN117064350A (en) * | 2023-08-18 | 2023-11-17 | 暨南大学附属第一医院（广州华侨医院） | Safety detection and intelligent evaluation system |
| CN116936104A (en) * | 2023-09-15 | 2023-10-24 | 广东恒腾科技有限公司 | Health detector data analysis system and method based on artificial intelligence |
| CN116936104B (en) * | 2023-09-15 | 2023-12-08 | 广东恒腾科技有限公司 | Health detector data analysis system and method based on artificial intelligence |
| CN118380159A (en) * | 2024-06-20 | 2024-07-23 | 湘江实验室 | Multi-user real-time collaboration system based on meta universe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169307A (en) | Health risk assessment method and apparatus | |
| US8744561B2 (en) | Remote health monitoring system | |
| JP7531917B2 (en) | Heart Rate Measurement System | |
| TWI528939B (en) | Method of evaluating the health and/or physical condition of a person and corresponding device and computer software package | |
| EP2845539B1 (en) | Device and method for automatically normalizing the physiological signals of a living being | |
| CN106037701A (en) | Biological information processing system, biological information processing device, and method for generating analysis result information | |
| US20240099639A1 (en) | System for measuring heart rate | |
| US20220361788A1 (en) | System and method for measuring acute and chronic stress | |
| CN108618788A (en) | A kind of psychological pressure apparatus for evaluating and psychological pressure appraisal procedure | |
| CN111820879A (en) | Health evaluation management method suitable for chronic disease patients | |
| CN117158938A (en) | Health monitoring method and device applied to intelligent watch and electronic equipment | |
| CN107403061A (en) | User's medical assessment model building method and medical assessment server | |
| JP2018175488A (en) | Health support device, health support system, health support method, and program of health support device | |
| CN117153405A (en) | Alcoholism risk assessment and early warning method combined with alcohol concentration detection | |
| CN116115201B (en) | Physical health state assessment system | |
| KR101576666B1 (en) | System and method for cardiopulmonary fitness estimation in daily life | |
| TWI661384B (en) | Physiological monitoring feedback system and operating method thereof | |
| CA3126928A1 (en) | Systems, devices, and methods for detecting brain conditions from cranial movement due to blood flow in the brain | |
| US20190380661A1 (en) | Diagnostic Method And System | |
| JP2024531769A (en) | Biometric data monitoring platform using a biosignal sensing ring | |
| US20160228067A1 (en) | System and method for intelligent monitoring of patient vital signs | |
| Bai | [Retracted] Designing and Implementing a Terminal Platform to Manage and Detect the Health of Exercise Parameters Based on Internet Objects | |
| RU129680U1 (en) | SYSTEM FOR DETERMINING THE FUNCTIONAL STATE OF A PEOPLE GROUP | |
| CN117594227B (en) | Health state monitoring method, device, medium and equipment based on wearable equipment | |
| Koceska et al. | Evaluation of wearable system for measuring vital parameters in clinical environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170915 |