CN108511067A - Method for early warning and electronic equipment - Google Patents
Method for early warning and electronic equipment Download PDFInfo
- Publication number
- CN108511067A CN108511067A CN201810281536.3A CN201810281536A CN108511067A CN 108511067 A CN108511067 A CN 108511067A CN 201810281536 A CN201810281536 A CN 201810281536A CN 108511067 A CN108511067 A CN 108511067A
- Authority
- CN
- China
- Prior art keywords
- data
- deviation
- health
- group
- graphs
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
A kind of method for early warning of the embodiment of the present application offer and electronic equipment, this method include:In detection cycle, health data to be analyzed that the data collection station for receiving tested user is acquired and sent.Obtain first deviation of the health data to be analyzed respectively between group's historical data in history cycle and the second deviation between case history data.Determined whether to generate warning information according to the relationship between the first deviation and the second deviation and predetermined threshold value, if generating warning information, the warning information is back to the data collection station or early warning end.The early warning scheme using group's historical data and case history data as, to realize early warning, avoided with reference to object because individual difference exclusive or because individual is chronically at abnormality cannot find in time caused by early warning inaccuracy defect.
Description
Technical field
The present invention relates to detection technique fields, in particular to a kind of method for early warning and electronic equipment.
Background technology
In the health early warning system of the prior art, often according to previous clinical literature data, artificial threshold value ginseng is carried out
Number setting can then provide warning information, to remind user to arouse attention when specific health data are more than threshold value.However, this
The setting of threshold value, is often based on statistical significance, due to the individual difference of human body, allow some fixed threshold values clinically only
It can need professional that further particular problem is made a concrete analysis of and adjusted as reference.It is automatically analyzed in some needs
With the occasion of healthy early warning, expert is on the scene at any time due to not having, product designer in order to method or apparatus applicability, in order to return
The setting work of threshold value is completed by user, therefore can not achieve full automation by the individual difference for keeping away human body, needs to use
There is centainly professional could use health early warning system well at family.
Invention content
In view of this, the purpose of the application is, a kind of method for early warning and electronic equipment are provided to improve the above problem.
The embodiment of the present application provides a kind of method for early warning, is applied to the clothes communicated to connect with data collection station and early warning end
Business device, the method includes:
In detection cycle, health data to be analyzed that the data collection station for receiving tested user is acquired and sent;
Group's historical data in the health data to be analyzed and the history cycle of acquisition is compared to obtain
State the first deviation between health data to be analyzed and group's historical data, wherein group's historical data is by more
The health data of a data collection station acquisition is generated;
Case history data in the health data to be analyzed and the history cycle of acquisition are compared to obtain
The second deviation between health data to be analyzed and the case history data is stated, the case history data are described tested
Health data of the user in history cycle is generated;
Determine whether to generate according to the relationship between first deviation and second deviation and predetermined threshold value pre-
The warning information is back to the data collection station or the early warning end by alert information if generating warning information.
Further, the method further includes:
Group's historical data and the case history data are updated according to the health data.
Further, the history cycle includes multiple subcycles, and group's historical data is obtained by following steps:
For each data collection station in multiple data collection stations, the data collection station is obtained described
The health data of each sampled point in each subcycle of history cycle;
The health data of the corresponding sampled point of multiple subcycles is subjected to mean value computation, to obtain the phase of each subcycle
With the first average value of the health data of sampled point;
Corresponding first average value of multiple data collection stations is subjected to mean value computation, to obtain the group of each sampled point
Historical data;
The detection cycle is consistent with the subcycle, the history cycle by the health data to be analyzed and acquisition
Interior group's historical data is compared to obtain first between the health data to be analyzed and group's historical data
The step of deviation, including:
For each sampled point, according to group's historical data of group's historical data of the sampled point and multiple sampled points
Variance equivalent be worth to data upper limit value and data lower limiting value;
The health data in the health data to be analyzed corresponding to the sampled point is detected whether under the data
Between limit value and the data upper limit value, if being not at, calculate the health data to be analyzed and the data lower limiting value or
Difference between the data upper limit value is to obtain the first deviation.
Further, the history cycle includes multiple subcycles, and group's historical data is obtained by following steps:
For each tested user in multiple tested users, the tested user is obtained in each of the history cycle
The health data of each sampled point in a subcycle;
Count the occurrence number of the identical health data of numerical value in multiple health datas;
Mean value computation is carried out to the statistical result of multiple subcycles, to obtain the numerical value of health data in the history cycle
Distribution situation;
The numeric distribution situation of the health data of multiple data collection stations is carried out mean value to seek, to obtain group's history
Data;
Group's historical data by the health data to be analyzed and the history cycle of acquisition is compared to obtain
The step of obtaining the first deviation between the health data to be analyzed and group's historical data, including:
Draw the first data graphs of group's historical data and the second data histogram of health data to be analyzed
Figure;
The deviation value for obtaining second data graphs and first data graphs is worth to according to the deviation
The first deviation between the health data to be analyzed and group's historical data.
Further, the deviation value for obtaining second data graphs and first data graphs, according to
The step of deviation is worth to the first deviation between the health data to be analyzed and group's historical data, packet
It includes:
Second data graphs and peak-data in first data graphs, median numbers are obtained respectively according to this
And centre data;
According to the difference of the peak-data of second data graphs and first data graphs, intermediate value data
At least one of difference, difference of centre data obtain first between health data to be analyzed and group's historical data
Deviation.
Further, the centre data is obtained by following formula:
Wherein, Hcenter is the centre data, and Hmin is first data graphs or the second data histogram
Abscissa minimum value in figure, Hmax are abscissa maximum number in first data graphs or second data graphs
Value, H are each health data in first data graphs or second data graphs, and P (H) is corresponding healthy number
According to occurrence number.
Further, the deviation value for obtaining second data graphs and first data graphs, according to
The step of deviation is worth to the first deviation between the health data to be analyzed and group's historical data, packet
It includes:
Second data graphs and first data graphs are normalized respectively;
The not lap between the second data graphs and the first data graphs after normalized is obtained, with
The first deviation between the health data to be analyzed and group's historical data.
Further, described true according to the relationship between first deviation and second deviation and predetermined threshold value
Fixed the step of whether generating warning information, including:
First deviation and second deviation are weighted superposition and obtain stack result, the superposition is detected
As a result whether it is more than predetermined threshold value, needs to generate warning information if more than judgement if predetermined threshold value.
Further, the health data includes acceleration information, pulse wave data, electro-physiological signals, human body impedance, body
At least one of table temperature and blood glucose level data.
The embodiment of the present application also provides a kind of electronic equipment, including:
Memory;
One or more processors;And
One or more programs, wherein one or more of programs are stored in the memory and are configured to
It is executed by one or more of processors, described program is for the step of executing above-mentioned method for early warning.
Method for early warning and electronic equipment provided by the embodiments of the present application pass through the tested user that will be received in detection cycle
Health data to be analyzed compared respectively with group's historical data in history cycle to obtain the first deviation, Yi Jiyu
Case history data in history cycle are compared to obtain the second deviation.Wherein, group's historical data is by multiple numbers
The health data acquired according to acquisition terminal is generated, healthy number of the case history data according to tested user in history cycle
According to generation.And according to the relationship between the first deviation and the second deviation and predetermined threshold value to determine whether to generate early warning letter
Breath.Group's historical data and case history data, to realize early warning, are avoided individual difference by the early warning scheme as with reference to object
Or it is personal cannot be found in time because being chronically at abnormality caused by early warning inaccuracy defect.
Further, which can dynamically update reference subject, in this way, the real-time of historical data can be ensured to carry
The robustness of high system.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment cited below particularly, and coordinate
Appended attached drawing, is described in detail below.
Description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the application scenarios schematic diagram of method for early warning provided by the embodiments of the present application.
Fig. 2 is the schematic block diagram of server provided by the embodiments of the present application.
Fig. 3 is the flow chart of method for early warning provided by the embodiments of the present application.
Fig. 4 is one of the flow chart of acquisition methods of group's historical data provided by the embodiments of the present application.
Fig. 5 is the flow chart of the sub-step of step S120 in Fig. 3.
Health data distribution schematic diagram in Fig. 6 time domains provided by the embodiments of the present application.
Fig. 7 is the two of the flow chart of the acquisition methods of group's historical data provided by the embodiments of the present application.
Fig. 8 is another flow chart of the sub-step of step S120 in Fig. 3.
Fig. 9 is the schematic diagram of data graphs provided by the embodiments of the present application.
Figure 10 is the schematic diagram of the data graphs provided by the embodiments of the present application after normalized.
Icon:100- servers;110- prior-warning devices;120- processors;130- memories;200- data collection stations;
300- early warning end.
Specific implementation mode
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.
Therefore, below the detailed description of the embodiment of the present invention to providing in the accompanying drawings be not intended to limit it is claimed
The scope of the present invention, but be merely representative of the present invention selected embodiment.Based on the embodiment of the present invention, people in the art
The every other embodiment that member is obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that:Similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent attached drawing in a attached drawing.
Referring to Fig. 1, for the application scenarios schematic diagram of method for early warning provided by the embodiments of the present application, which includes clothes
Business device 100, data collection station 200 and early warning end 300.The server 100 and the data collection station 200 and described
Early warning end 300 communicates to connect, with into row data communication or interaction.In the present embodiment, the data collection station 200 and described
Early warning end 300 can be multiple, and multiple data collection stations 200 and the early warning end 300 and the server 100 communicate to connect.
In the present embodiment, the data collection station 200 can be wearable device, such as bracelet, wrist-watch etc..The early warning end
300 can be with the data collection station 200 associated terminal device, such as smart mobile phone, tablet computer, computer etc..It can
Can also be the electricity that the household of the user is held to be electric terminal that the user oneself of hand-held data gathering terminal 200 is held
Sub- terminal.Warning information can be sent to the early warning end 300, when needing early warning to notify the family of the user or the user
People plays early warning purpose.The server 100 can be individual server, can also be server cluster etc., not make to this
Concrete restriction.
Referring to Fig. 2, for the schematic block diagram of a kind of electronic equipment provided by the embodiments of the present application.In the present embodiment
In, the electronic equipment can be above-mentioned server 100, the server 100 include prior-warning device 110, processor 120 and
Memory 130.Wherein, electric connection direct or indirect between the memory 130 and the processor 120, to realize number
According to transmission or interaction.The prior-warning device 110 can be stored in the storage including at least one in the form of software or firmware
In device 130 or the software function module that is solidificated in the operating system of the server 100.The processor 120 is for executing
The executable module stored in the memory 130, such as software function module or computer that the prior-warning device 110 includes
Program.
Referring to Fig. 3, being a kind of flow of method for early warning applied to above-mentioned server 100 provided in an embodiment of the present invention
Figure.It should be noted that method provided by the invention is not limitation with Fig. 3 and particular order as described below.It below will be to Fig. 3
Shown in each step be described in detail.
Step S110, in detection cycle, the data collection station 200 for receiving tested user is acquired and is sent to be analyzed
Health data.
With the rise of intelligent wearable device, the persistent collection of the dynamical health data of magnanimity is possibly realized, and is formd dynamic
The healthy large database concept of state, the heart rate comprising user, blood oxygen saturation, respiratory rate, blood pressure, blood glucose, temperature, work in database
Momentum, sleep info etc..When the wearable product of user's long periods of wear, the historical data of the past period contains individual certainly
Body rule, and embody its individual difference.Meanwhile the health data accumulation of a large number of users, it can therefrom extract different groups
Health data rule.
It is compared when using user's individual data items and itself historical data rule, group's historical data rule in large database concept
When, in case of gradual and paroxysmal deviation, then may imply that the health status of user generates certain variation, at this time for
User generates healthy early warning information, and consulting profession medical staff or other early intervention measures are taken early convenient for user.It is this
Dynamical health method for early warning based on big data, avoids the differences such as human body individual difference, audience age, region, weather and leads
The risk of previous Universal Criterion failure when the health data analysis of cause.This for healthy early warning device warning algorithm it is adaptive
Raising with robustness has prodigious value.
In the present embodiment, the data collection station 200 includes a variety of data pick-ups, can be respectively used to obtain to wear and use
It is one or more in the acceleration information at family, pulse wave data, electro-physiological signals, human body impedance, shell temperature, blood glucose level data
Health data.Collected health data is sent to server 100 by the data collection station 200.The server 100 is right
In one detection cycle, such as one day or one week, the data collection station 200 of the tested user received acquires and what is sent waits for
Analysis health data carries out whether analyzing processing exception occurs with the health data for detecting tested user.The server 100 can
The step number of user, sleep quality data of user etc. are obtained according to the acceleration information received.It can be obtained according to pulse wave data
To user's heart rate data, blood oxygen saturation data, breath data and blood pressure etc..The electro-physiological signals include electrocardiosignal,
Electromyography signal, EEG signals etc..
Step S120 compares group's historical data in the health data to be analyzed and the history cycle of acquisition
To obtain the first deviation between the health data to be analyzed and group's historical data, wherein group's history
The health data that data are acquired by multiple data collection stations 200 is generated.
Step S130 compares the case history data in the health data to be analyzed and the history cycle of acquisition
To obtain the second deviation between the health data to be analyzed and the case history data, the case history data are
Health data of the tested user in history cycle is generated.
In the present embodiment, the server 100 can receive the health data that multiple data collection stations 200 are acquired and sent
And analyze it to obtain the statistical data of group, and it can also be directed to each data collection station 200 respectively, it is single
The health data of each data collection station 200 is solely counted to obtain personal statistical data.
In the present embodiment, server 100 can carry out the health data received in the history cycle before detection cycle
Statistical analysis is to obtain group's historical data of the health data based on multiple data collection stations 200 in history cycle.Its
In, for group's historical data, which can also be the period with the detection cycle same period, not limit specifically this
System.And the case history data of the health data based on its corresponding data collection station 200 for each user.It examines
Consider and is directed to each user in the prior art often using changeless early warning rule, but in actual conditions, due to difference
User is because of its constitution difference, so the standard of health data is also different.Early warning rule in the prior art does not form specific aim
Ground, customization ground early warning scheme, lead to the problem of the early warning inaccuracy caused by individual difference.In the present embodiment in view of it is above-mentioned because
Element, therefore using case history data of the tested user certainly in history cycle as one of which references object, it is pre- to improve
Alert accuracy rate.In addition, if user itself is chronically at unsound state, if only using the case history data of user itself as
With reference to then possibly to find the unhealthy condition in time and be difficult to make accurate early warning.It therefore, will be multiple in the present embodiment
Group's historical data is also included in tested user's by user's health data in history cycle with constituting group's historical data
In the reference data of early warning detection.Health data is analysed to compare with reality with case history data and group's historical data
Existing early warning.
In the present embodiment, in order to more comprehensively analyze health data, health data can be handled with
Various forms of group's historical datas are obtained with basic as a comparison.Optionally, time-domain analysis can be carried out to health data, please join
Fig. 4 is read, group's historical data of time domain can be obtained by following steps:
Step S210 obtains the number for each data collection station 200 in multiple data collection stations 200
According to the health data of each sampled point of the acquisition terminal 200 in each subcycle of the history cycle.
The health data of the corresponding sampled point of multiple subcycles is carried out mean value computation by step S220, each to obtain
First average value of the health data of the identical sampled point of subcycle.
Corresponding first average value of multiple tested users is carried out mean value computation, to obtain each sampled point by step S230
Group's historical data.
It is generated it can be seen from the above, group's historical data is the health data based on multiple users.It, can in the present embodiment
The data first acquired respectively for the data collection station 200 of each user are analyzed, then count point of multiple users
Result is analysed to obtain group's historical data.
In the present embodiment, the history cycle can be one day, either one month one week, be not specifically limited to this.
It, can be all by the history in order to which the health data to user every day is analyzed such as when the history cycle is one week
Phase is divided into multiple subcycles, wherein the subcycle can be one day.
If the subcycle is one day, it may include that multiple sampled points, sample frequency can be 2 points in the subcycle
Clock or 10 minutes, are not restricted this.The server 100 can receive data collection station 200 in each sampled point and be sent out
The health data sent.In this way, then having multiple health datas for the identical sampled point of multiple subcycles in history cycle.Example
Such as, respectively there are one health datas for 12 points in each subcycle, if history cycle includes 7 subcycles, in history cycle
7 12 points of health data is shared, can multiple health datas be subjected to mean value computation, to obtain the identical sampling of each subcycle
First average value of the health data of point.In this way, can avoid subsequently individually carrying out comparing with the data in some subcycle making
At the insecure problem of data.It should be noted that the above-mentioned elaboration to history cycle and subcycle is merely illustrative,
When implementing, other set-up modes can be used, this present embodiment is not specifically limited.
After carrying out analyzing processing to health data for each data collection station 200, multiple data can be adopted
The analysis and processing result for collecting terminal 200 carries out mean value computation, to obtain group's historical data of multiple users.In the above described manner
In the case of obtaining group's historical data, in the present embodiment, referring to Fig. 5, step S120 may include following sub-step:
Step S121, for each sampled point, according to the group of the group's historical data and multiple sampled points of the sampled point
The variance of body historical data is equivalent to be worth to data upper limit value and data lower limiting value.
Whether step S122 detects the health data for corresponding to the sampled point in the health data to be analyzed in institute
It states between data lower limiting value and the data upper limit value, if being not at, calculates the health data to be analyzed and the data
Difference between lower limiting value or the data upper limit value is to obtain the first deviation.
After through the above steps, Data Integration by multiple users in multiple subcycles is equivalent to a subcycle
Interior, in the present embodiment, the detection cycle is consistent with the subcycle, and the even described subcycle is one day, then the detection week
Phase is also one day.For group's historical data of each sampled point in group's historical data of above-mentioned acquisition, this can be adopted
Group's historical data of collection point adds the variance equivalence value of group's historical data of the multiple sampled points obtained to obtain in data
Limit value, and the variance that group's historical data of the collection point is subtracted to group's historical data of multiple sampled points of acquisition is equivalent
Value is to obtain data lower limiting value.Wherein, the variance equivalence value can be multiplied by 2 or variance for the multiple value of variance, such as variance yields
Value is multiplied by 3 etc., is not restricted specifically.
In the present embodiment, the health data to be analyzed includes multiple health datas, and each health data corresponds to detection week
Each sampled point in phase, the health data that each sampled point can be obtained and the data upper limit value obtained according to group's historical data
It is compared with data lower limiting value.Fig. 6 show data upper limit value, data lower limiting value and history mean value distribution schematic diagram.
Wherein, the data lower limiting value, data upper limit value and history mean value can be generated based on case history data, can also be base
It is generated in group's historical data.If the health data is not between the data upper limit value and the data lower limiting value, can
Make further detection.If the health data is more than the data upper limit value, the health data and the data can be calculated
Difference between upper limit value, using the difference as the first deviation between health data to be analyzed and group's historical data.If
The health data is less than the data lower limiting value, then can calculate the difference between the data lower limiting value and the health data
Value, using the difference as the first deviation between health data to be analyzed and group's historical data.Wherein, first deviation
It can be the deviation for single-point, can also be the statistical value to the deviation of each sampled point in entire detection cycle.
In addition, other than the above-mentioned health data in history cycle carries out time-domain analysis, may be used also in the present embodiment
Frequency-domain analysis is carried out to the health data in history cycle, referring to Fig. 7, group's history number can be obtained by following steps
According to:
Step S310 obtains the number for each data collection station 200 in multiple data collection stations 200
According to the health data of each sampled point of the acquisition terminal 200 in each subcycle of the history cycle, multiple health are counted
The occurrence number of the identical health data of numerical value in data.
Step S320 carries out mean value computation to the statistical result of multiple subcycles, healthy in the history cycle to obtain
The numeric distribution situation of data.
The numeric distribution situation of the health data of multiple data collection stations 200 is carried out mean value and sought by step S330, with
Obtain group's historical data.
In the present embodiment, for each user, in each subcycle of its history cycle, the subcycle can get
The health data of interior each sampled point, and the occurrence number of the identical health data of numerical value in the subcycle is counted, to obtain
The occurrence number of the health data of each numerical value.The statistical result of multiple subcycles in history cycle is subjected to mean value meter again
It calculates, the numeric distribution situation of health data in history cycle so can be obtained.
Through the above steps, it can get the numerical value of the health data in the history cycle of each data collection station 200
The result of multiple data collection stations 200 can be carried out mean value and sought, to obtain going through based on the group of multiple users by distribution situation
History data.
In the present embodiment, when obtaining group's historical data in this way, referring to Fig. 8, following sub-step can be passed through
Obtain the first deviation between data to be analyzed and group's historical data:
Step S123, draw group's historical data the first data graphs and health data to be analyzed second
Data graphs.
Step S124 obtains the deviation value of second data graphs and first data graphs, according to described
Deviate the first deviation being worth between the health data to be analyzed and group's historical data.
In the present embodiment, in order to intuitively show health data distribution situation, it can be drawn according to obtained group's historical data
First data graphs.Data to be analyzed in obtained detection cycle are obtained to the numerical value point of data to be analyzed in a manner described
After cloth situation, the second data graphs are drawn further according to the numeric distribution situation.According to the first data graphs and the second data
Deviation between histogram is worth to the first deviation between health data to be analyzed and group's historical data.Fig. 9 is shown
The schematic diagram of first data graphs or the second data graphs provided in this embodiment.
In the present embodiment, the peak value in second data graphs and first data graphs can be obtained respectively
According to this and centre data according to, median numbers.Wherein, intermediate value data are that histogram is divided into two and the number of the area equation on both sides
Value.Centre data is the position where the barycenter in histogram.Peak-data, median numbers are according to this and centre data reflects user
The strength range of health data within one period is distributed.This distribution has substantial connection with the health status of user, when by
The histogram feature value for surveying user has significantly with respect to the distribution situation of the history cycle of its own the either history cycle of group
When difference, there is exception in the health status of possible tested user, need to remind user.
Optionally, according to the difference of the peak-data of second data graphs and first data graphs, in
At least one of the difference of Value Data, difference of centre data obtain health data to be analyzed and group's historical data it
Between the first deviation.The first deviation can be obtained according to any one in above-mentioned three kinds of differences or two kinds of weightings are folded
The first deviation is obtained after adding, or obtains the first deviation after above-mentioned three kinds of weighted differences are superimposed.To this present embodiment
In be not specifically limited, can be adjusted according to actual conditions.
Wherein, the centre data can be obtained by following formula:
Wherein, Hcenter is the centre data, and Hmin is first data graphs or the second data histogram
Abscissa minimum value in figure, Hmax are abscissa maximum number in first data graphs or second data graphs
Value, H are each health data numerical value in first data graphs or second data graphs, and P (H) is corresponding strong
The occurrence number of health value data.
In addition, other than the deviation of above-mentioned detection single-point is to obtain the first deviation, it, can also basis in the present embodiment
Whole departure degree obtains the first deviation.It, can be respectively to second data graphs and first number in the present embodiment
It is normalized according to histogram.Between the second data graphs and the first data graphs after acquisition normalized
Not lap, lap is not the deviation for indicating the second data graphs relative to the first data graphs for this.According to this
The first deviation between the health data to be analyzed and group's historical data does not can be obtained in lap.Shown in Figure 10
For the schematic diagram of the first data graphs and the second data graphs after normalized.
By above step, the first deviation between health data to be analyzed and group's historical data is can get, is needed
Illustrate, the acquisition modes and health data to be analyzed for the case history data of tested user and case history data
The acquisition modes of second deviation respectively with the acquisition modes of group historical data and health data to be analyzed and group's history number
According to the first deviation acquisition modes it is similar, be to be directed to multiple users, and case history difference lies in group's historical data
Data are to be directed to tested user.Therefore, the obtaining step of second deviation can refer to foregoing description, not another herein
One repeats.
Step S140, being determined according to the relationship between first deviation and second deviation and predetermined threshold value is
The warning information is back to the data collection station 200 or described by no generation warning information if generating warning information
Early warning end 300.
In the present embodiment, obtain through the above steps data to be analyzed and group's historical data the first deviation and with
After second deviation of case history data.It can determine a need for generating early warning according to the relationship of the two and predetermined threshold value
Information.First deviation and the second deviation can be weighted to superposition to obtain stack result.Whether detect stack result again
More than predetermined threshold value, if being more than predetermined threshold value, judgement needs to generate warning information, and warning information is fed back to tested user
Data collection station 200 or early warning associated with the data collection station 200 of tested user end 300.The early warning end 300 can
Think the smart mobile phone that the tested user is held, such as notifies the meter of user or tested user by way of sending short messages
Calculation machine, such as notify user by way of sending out mail.The early warning end 300 can also be to be acquired eventually with the data of the tested user
The electric terminal for holding the household of the 200 associated tested users to be held, in this way, can notify the household of tested user to carry in time
The household that wakes up pays close attention to the health status of tested user, to avoid danger situation.
In addition, in addition to above-mentioned stack result and predetermined threshold value according to the first deviation and the second deviation relationship with
Determine a need for generating except warning information, in the present embodiment, also can according to the relationship of the first deviation and predetermined threshold value or
Person is the relationship of the second deviation and predetermined threshold value to determine a need for generating warning information.Can according to the first deviation and
The relationship of at least one of second deviation and predetermined threshold value is to determine a need for generating warning information.In this regard, this implementation
Example is not specifically limited, and can be accordingly arranged according to demand.
In addition, in the present embodiment, group's historical data and the case history data can also be updated into Mobile state, i.e.,
The health data to be analyzed obtained in detection cycle can be added into historical data, to realize to group's historical data and individual
The update of historical data.In this way, the real-time of historical data can be ensured to improve the robustness of system.
In conclusion a kind of method for early warning of the embodiment of the present application offer and electronic equipment, by will be received in detection cycle
To the health data to be analyzed of tested user compared respectively with group's historical data in history cycle to obtain first
Deviation, and be compared with the case history data in history cycle to obtain the second deviation.Wherein, group's history
The health data that data are acquired by multiple data collection stations 200 is generated, which is going through according to tested user
Health data in the history period generates.And according to the relationship between the first deviation and the second deviation and predetermined threshold value with determination
Whether warning information is generated.The early warning scheme is using group's historical data and case history data as pre- to realize with reference to object
Alert, early warning caused by avoiding individual difference exclusive or individual that from cannot being found in time because being chronically at abnormality is inaccurate to be lacked
It falls into.In addition, can also dynamically update reference subject, the real-time of historical data has been ensured to improve the robustness of system.
In embodiment provided herein, it should be understood that disclosed device and method, it can also be by other
Mode realize.The apparatus embodiments described above are merely exemplary, for example, the flow chart and block diagram in attached drawing are shown
Architectural framework in the cards, function and the behaviour of devices in accordance with embodiments of the present invention, method and computer program product
Make.In this regard, each box in flowchart or block diagram can represent a part for a module, section or code, institute
The part for stating module, section or code includes one or more executable instructions for implementing the specified logical function.
It should also be noted that at some as in the realization method replaced, the function of being marked in box can also be to be different from attached drawing
The sequence marked occurs.For example, two continuous boxes can essentially be basically executed in parallel, they sometimes can also be by
Opposite sequence executes, this is depended on the functions involved.It is also noted that each box in block diagram and or flow chart,
And the combination of the box in block diagram and or flow chart, function or the dedicated of action as defined in executing can be used to be based on hardware
System realize, or can realize using a combination of dedicated hardware and computer instructions.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or equipment including a series of elements includes not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including institute
State in the process, method, article or equipment of element that there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should be noted that:Similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and is explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (10)
1. a kind of method for early warning, which is characterized in that be applied to the server communicated to connect with data collection station and early warning end, institute
The method of stating includes:
In detection cycle, health data to be analyzed that the data collection station for receiving tested user is acquired and sent;
Group's historical data in the health data to be analyzed and the history cycle of acquisition is compared to be waited for described in acquisition
Analyze the first deviation between health data and group's historical data, wherein group's historical data is by multiple numbers
The health data acquired according to acquisition terminal is generated;
Case history data in the health data to be analyzed and the history cycle of acquisition are compared to be waited for described in acquisition
The second deviation between health data and the case history data is analyzed, the case history data are the tested user
Health data in history cycle is generated;
Determined whether to generate early warning letter according to the relationship between first deviation and second deviation and predetermined threshold value
The warning information is back to the data collection station or the early warning end by breath if generating warning information.
2. method for early warning according to claim 1, which is characterized in that the method further includes:
Group's historical data and the case history data are updated according to the health data.
3. method for early warning according to claim 1, which is characterized in that the history cycle includes multiple subcycles, described
Group's historical data is obtained by following steps:
For each data collection station in multiple data collection stations, the data collection station is obtained in the history
The health data of each sampled point in each subcycle in period;
The health data of the corresponding sampled point of multiple subcycles is subjected to mean value computation, is adopted with obtaining the identical of each subcycle
First average value of the health data of sampling point;
Corresponding first average value of multiple data collection stations is subjected to mean value computation, to obtain group's history of each sampled point
Data;
The detection cycle is consistent with the subcycle, it is described will be in the health data to be analyzed and the history cycle of acquisition
Group's historical data is compared to obtain the first deviation between the health data to be analyzed and group's historical data
The step of value, including:
For each sampled point, according to the side of group's historical data of the sampled point and group's historical data of multiple sampled points
Difference is equivalent to be worth to data upper limit value and data lower limiting value;
Detect whether the health data in the health data to be analyzed corresponding to the sampled point is in the data lower limiting value
Between the data upper limit value, if being not at, the health data to be analyzed and the data lower limiting value or described are calculated
Difference between data upper limit value is to obtain the first deviation.
4. method for early warning according to claim 1, which is characterized in that the history cycle includes multiple subcycles, described
Group's historical data is obtained by following steps:
For each tested user in multiple tested users, each height of the acquisition tested user in the history cycle
The health data of each sampled point in period;
Count the occurrence number of the identical health data of numerical value in multiple health datas;
Mean value computation is carried out to the statistical result of multiple subcycles, to obtain the numeric distribution of health data in the history cycle
Situation;
The numeric distribution situation of the health data of multiple data collection stations is carried out mean value to seek, to obtain group's history number
According to;
Group's historical data by the health data to be analyzed and the history cycle of acquisition is compared to obtain
The step of stating the first deviation between health data to be analyzed and group's historical data, including:
Draw the first data graphs of group's historical data and the second data graphs of health data to be analyzed;
The deviation value for obtaining second data graphs and first data graphs is worth to described according to the deviation
The first deviation between health data to be analyzed and group's historical data.
5. method for early warning according to claim 4, which is characterized in that it is described obtain second data graphs with it is described
The deviation value of first data graphs is worth to the health data to be analyzed and group's historical data according to the deviation
Between the first deviation the step of, including:
Obtain respectively second data graphs and peak-data in first data graphs, median numbers according to this and in
Calculation evidence;
According to the difference of the peak-data of second data graphs and first data graphs, the difference of intermediate value data
At least one of value, difference of centre data obtain between health data to be analyzed and group's historical data first partially
Difference.
6. method for early warning according to claim 5, which is characterized in that the centre data is obtained by following formula:
Wherein, Hcenter is the centre data, and Hmin is in first data graphs or second data graphs
Abscissa minimum value, Hmax are abscissa greatest measure in first data graphs or second data graphs, H
For each health data in first data graphs or second data graphs, P (H) is corresponding health data
Occurrence number.
7. method for early warning according to claim 4, which is characterized in that it is described obtain second data graphs with it is described
The deviation value of first data graphs is worth to the health data to be analyzed and group's historical data according to the deviation
Between the first deviation the step of, including:
Second data graphs and first data graphs are normalized respectively;
The not lap between the second data graphs and the first data graphs after normalized is obtained, to obtain
State the first deviation between health data to be analyzed and group's historical data.
8. method for early warning according to claim 1, which is characterized in that described according to first deviation and described second
Relationship between deviation and predetermined threshold value determines whether the step of generating warning information, including:
First deviation and second deviation are weighted superposition and obtain stack result, the stack result is detected
Whether it is more than predetermined threshold value, needs to generate warning information if more than judgement if predetermined threshold value.
9. method for early warning according to claim 1, which is characterized in that the health data includes acceleration information, pulse
At least one of wave number evidence, electro-physiological signals, human body impedance, shell temperature and blood glucose level data.
10. a kind of electronic equipment, which is characterized in that including:
Memory;
One or more processors;And
One or more programs, wherein one or more of programs are stored in the memory and are configured to by institute
One or more processors execution is stated, described program is used for the step of perform claim requires 1-9 any one method for early warning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810281536.3A CN108511067B (en) | 2018-04-02 | 2018-04-02 | Early warning method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810281536.3A CN108511067B (en) | 2018-04-02 | 2018-04-02 | Early warning method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108511067A true CN108511067A (en) | 2018-09-07 |
CN108511067B CN108511067B (en) | 2020-12-08 |
Family
ID=63379528
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810281536.3A Active CN108511067B (en) | 2018-04-02 | 2018-04-02 | Early warning method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108511067B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109490675A (en) * | 2018-12-27 | 2019-03-19 | 上海辛格林纳新时达电机有限公司 | Method for early warning, electronic equipment and test macro |
CN110473633A (en) * | 2019-08-19 | 2019-11-19 | 泰康保险集团股份有限公司 | Health information management method, device, medium and electronic equipment |
CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
CN112256754A (en) * | 2020-10-19 | 2021-01-22 | 柳州市妇幼保健院 | Ultrasonic detection analysis system and method based on standard model |
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 |
CN116807467A (en) * | 2023-07-12 | 2023-09-29 | 徐州市永康电子科技有限公司 | Blood oxygen saturation monitoring and early warning system and method based on finger-clipping pulse oximeter |
CN116807467B (en) * | 2023-07-12 | 2024-05-14 | 徐州市永康电子科技有限公司 | Blood oxygen saturation monitoring and early warning system and method based on finger-clipping pulse oximeter |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104207753A (en) * | 2013-02-15 | 2014-12-17 | 迈克尔·L·谢尔登 | Personal health monitoring system |
US20150220839A1 (en) * | 2012-09-07 | 2015-08-06 | Hugh Macnaught | Comparison of user experience with experience of larger group |
CN105718732A (en) * | 2016-01-20 | 2016-06-29 | 华中科技大学同济医学院附属协和医院 | Medical data collection and analysis method and system |
CN106030592A (en) * | 2014-02-19 | 2016-10-12 | 国际商业机器公司 | Developing health information feature abstractions from intra-individual temporal variance heteroskedasticity |
CN107122587A (en) * | 2017-03-22 | 2017-09-01 | 上海商保通健康科技有限公司 | Layer-stepping personalized health trend evaluation system based on big data |
CN107145704A (en) * | 2017-03-27 | 2017-09-08 | 西安电子科技大学 | Health medical treatment monitoring, evaluating system and its method for a kind of Community-oriented |
-
2018
- 2018-04-02 CN CN201810281536.3A patent/CN108511067B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150220839A1 (en) * | 2012-09-07 | 2015-08-06 | Hugh Macnaught | Comparison of user experience with experience of larger group |
CN104207753A (en) * | 2013-02-15 | 2014-12-17 | 迈克尔·L·谢尔登 | Personal health monitoring system |
CN106030592A (en) * | 2014-02-19 | 2016-10-12 | 国际商业机器公司 | Developing health information feature abstractions from intra-individual temporal variance heteroskedasticity |
CN105718732A (en) * | 2016-01-20 | 2016-06-29 | 华中科技大学同济医学院附属协和医院 | Medical data collection and analysis method and system |
CN107122587A (en) * | 2017-03-22 | 2017-09-01 | 上海商保通健康科技有限公司 | Layer-stepping personalized health trend evaluation system based on big data |
CN107145704A (en) * | 2017-03-27 | 2017-09-08 | 西安电子科技大学 | Health medical treatment monitoring, evaluating system and its method for a kind of Community-oriented |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109490675A (en) * | 2018-12-27 | 2019-03-19 | 上海辛格林纳新时达电机有限公司 | Method for early warning, electronic equipment and test macro |
CN109490675B (en) * | 2018-12-27 | 2022-06-28 | 上海辛格林纳新时达电机有限公司 | Early warning method, electronic device and test system |
CN110473633A (en) * | 2019-08-19 | 2019-11-19 | 泰康保险集团股份有限公司 | Health information management method, device, medium and electronic equipment |
CN111143350A (en) * | 2019-11-27 | 2020-05-12 | 深圳壹账通智能科技有限公司 | Enterprise data monitoring method and device, computer equipment and storage medium |
CN112256754A (en) * | 2020-10-19 | 2021-01-22 | 柳州市妇幼保健院 | Ultrasonic detection analysis system and method based on standard model |
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 |
CN116807467A (en) * | 2023-07-12 | 2023-09-29 | 徐州市永康电子科技有限公司 | Blood oxygen saturation monitoring and early warning system and method based on finger-clipping pulse oximeter |
CN116807467B (en) * | 2023-07-12 | 2024-05-14 | 徐州市永康电子科技有限公司 | Blood oxygen saturation monitoring and early warning system and method based on finger-clipping pulse oximeter |
Also Published As
Publication number | Publication date |
---|---|
CN108511067B (en) | 2020-12-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108511067A (en) | Method for early warning and electronic equipment | |
US11350868B2 (en) | Electrocardiogram information processing method and electrocardiogram workstation system | |
EP2330554A1 (en) | Method and system for generating history of behavior | |
EP3241492B1 (en) | Heart rate detection method and device | |
CN106725383A (en) | Sleep state judgement system and method based on action and heart rate | |
WO2012129413A1 (en) | Apparatus and method for measuring physiological signal quality | |
CN108847288A (en) | A kind of healthy early warning method and apparatus | |
TW201224825A (en) | Physiological signal detection system capable of showing emotions, device and emotional display method | |
CN109285606A (en) | A kind of health control method and system based on big data intelligent algorithm | |
Altini et al. | Combining wearable accelerometer and physiological data for activity and energy expenditure estimation | |
Kusserow et al. | Modeling arousal phases in daily living using wearable sensors | |
US20200060546A1 (en) | A System and Method for Monitoring Human Performance | |
US20210393210A1 (en) | Methods and systems for adaptable presentation of sensor data | |
WO2020147149A1 (en) | Method and apparatus for correcting heart rate, and storage medium | |
CN108670242A (en) | A kind of method and system of smartwatch detection health data | |
CN109480852A (en) | Sign monitoring method, system, wearable signal collecting device | |
CN109953756A (en) | Atrial fibrillation monitoring system and wearable device | |
US10159438B2 (en) | Determining resting heart rate using wearable device | |
CN106326672A (en) | Falling into sleep detecting method and system | |
CN116720493A (en) | Physiological data processing method, device, electronic equipment and storage medium | |
JP2020048622A (en) | Biological state estimation apparatus | |
KR101809149B1 (en) | Apparatus for determining circulatory disease and method thereof | |
JP7257381B2 (en) | Judgment system and judgment method | |
CN106940720A (en) | Multi-source information processing method and system based on healthy Internet of Things | |
Maneshti et al. | IoT-Enabled Low-Cost Fog Computing System with Online Machine Learning for Accurate and Low-Latency Heart Monitoring in Rural Healthcare Settings |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |