CN104750880B - A kind of resistance to cool ability method for early warning of human body based on big data and system - Google Patents
A kind of resistance to cool ability method for early warning of human body based on big data and system Download PDFInfo
- Publication number
- CN104750880B CN104750880B CN201510209572.5A CN201510209572A CN104750880B CN 104750880 B CN104750880 B CN 104750880B CN 201510209572 A CN201510209572 A CN 201510209572A CN 104750880 B CN104750880 B CN 104750880B
- Authority
- CN
- China
- Prior art keywords
- disease
- happening
- data
- resistance
- cool
- 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.)
- Active
Links
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This application discloses a kind of resistance to cool ability method for early warning of human body based on big data and system, and first with the resistance to cool big data of human body, training obtains classification of diseases device.Then disease type and corresponding disease probability of happening after user's perspiration are predicted with the classification of diseases device.For each disease type, when disease probability of happening is more than or equal to default probability of happening threshold value, think that user is not resistant to rising or falling for the shell temperature of now way, operation is reminded in the early warning that now control performs disease type corresponding with the disease probability of happening, and the measure of suffering from cold is prevented accordingly to remind user to take.When disease probability of happening is less than default probability of happening threshold value, then do not remind deliberately, user itself resistance of leaving deacclimatizes the change of this temperature, cultivates its resistance to cool ability.With this, realize and allow user to be gone to tackle the temperature change of body according to the actual conditions of itself resistance, itself resistance to cool ability is cultivated, so as to improve the purpose of fitness.
Description
Technical field
The application is related to data classification and field of computer technology, resistance to cool more particularly to a kind of human body based on big data
Ability method for early warning and system.
Background technology
Perspiration is body discharges and a kind of physiological function of regulation body temperature, and perspiring has point of physiology and pathology, as weather is scorching
Perspiration category physiological phenomenon when heat and large amount of exercise.How most common the perspiration of causes for pathological is two kinds：One kind is night sweat, is occurred
Do not feel and perspire in nighttime sleep.Another kind is spontaneous perspiration, is occurred on daytime, not because the thick or hot and sweat of working, wear the clothes is from going out,
Or somewhat move, sweat all over.The reduction of body surface temperature is the inevitable phenomenon after perspiring, and causes disease due to perspiring to suffer from cold
The problem of disease is common in life.
Perspiration how is effectively tackled to suffer from cold then and not as so simple in the imagination.On the one hand, guarantor is taken after suffering from cold in time
Warm measure effectively can prevent human body from suffering from cold as added clothing, avoid possible disease；On the other hand, human body passes through in nature
The evolution of up to ten thousand years, itself possess and be resistant to the body regulating power (i.e. resistance to cool ability) that a certain degree of temperature reduces, if excessively
Warming measure is taken, then may reduce this ability itself possessed of human body.This phenomenon in child's developmental process particularly
Substantially：In the family having, parent is to the excessive care of child so that child is lived in the environment similar to greenhouse, the time one
It is long then easily lose the resistance to cool ability of child in itself so as to be very easy to suffer from cold in the environment that child can not look after out of doors etc.
It is sick；And in some families, child is in " extensive " state, and parent allows it to receive a certain degree of exercise of suffering from cold, on the contrary
Can effectively cultivate child in itself to the tolerance suffered from cold after perspiration.But how to hold this degree is very tired in itself
Difficult thing.As some parents ignore child's own bodies condition and by some in society so-called " wolf father ", " brave mother " in pole
In end ring border cultivate child's resistance influence and go the treatment loosened to child of blindness, often lead to child suffer from cold for a long time and
Cause great body illness.
Based on this, a kind of temperature change that user can be allowed to remove reply body according to the actual conditions of itself resistance is needed badly
Change, itself resistance to cool ability is cultivated, so as to improve the method for fitness.
The content of the invention
In view of this, this application provides a kind of resistance to cool ability method for early warning of human body based on big data and system, to allow
User goes to tackle the temperature change of body according to the actual conditions of itself resistance, itself resistance to cool ability is cultivated, so as to improve body
Voxel matter.
In order to solve the above technical problems, the application provides a kind of resistance to cool ability method for early warning of human body based on big data, bag
Include：
The resistance to cool big data of human body is determined, and using the resistance to cool big data of the human body as training data, the ginseng of Study strategies and methods
Number, obtains classification of diseases device；
Wherein, the resistance to cool big data of the human body be goal-selling crowd the resistance to cool record data of N bars, every resistance to cool note
Record data include the personal data of target individual corresponding with the resistance to cool record data of this in the target group, data of suffering from cold and
Disease data；The personal data include user's mark generation of target individual corresponding with resistance to this cool record data
Code；
User's authentication code of user is determined, and obtains personal data corresponding with user's authentication code of the user,
Current shell temperature reduces related data and current environmental temperature data；
By the personal data corresponding with user's authentication code of the user, current shell temperature reduces related data
And current environmental temperature data are as test data, the classification of diseases device is input to, prediction obtains disease type and corresponding
Disease probability of happening；Wherein, the disease type comprises at least：Common cold type and diarrhoea type；
For each type in the disease type, when disease probability of happening is more than or equal to default probability of happening threshold value
When, operation is reminded in the early warning that control performs disease type corresponding with the disease probability of happening, to remind user to take accordingly
Prevent the measure of suffering from cold.
In the above method, it is preferred that when the default probability of happening threshold value of each type in the disease type is equal, institute
State after prediction obtains disease type and corresponding disease probability of happening, in addition to：
Descending sort is carried out to the disease probability of happening that prediction obtains；
It is determined that the disease probability of happening to rank the first；
When the disease probability of happening to rank the first is less than corresponding default probability of happening threshold value, do not do deliberately
Remind, to cultivate the resistance to cool ability of user, train its fitness.
In the above method, it is preferred that the control performs the prompting of disease type corresponding with the disease probability of happening
Operation, including：
Using the disease type corresponding with the disease probability of happening, generate corresponding early warning and remind instruction；
The early warning is sent to source of early warning and reminds instruction, is instructed so that the source of early warning performs to remind with the early warning
It is corresponding to remind operation.
In the above method, it is preferred that described using the resistance to cool big data of the human body as training data, the ginseng of Study strategies and methods
Number, is obtained in classification of diseases device, the grader is random forest grader.
Present invention also provides a kind of resistance to cool ability early warning system of human body based on big data, including：
Classifier training unit, for determining the resistance to cool big data of human body, and using the resistance to cool big data of the human body as training
Data, the parameter of Study strategies and methods, obtain classification of diseases device；
Wherein, the resistance to cool big data of the human body be goal-selling crowd the resistance to cool record data of N bars, every resistance to cool note
Record data include the personal data of target individual corresponding with the resistance to cool record data of this in the target group, data of suffering from cold and
Disease data；The personal data include user's mark generation of target individual corresponding with resistance to this cool record data
Code；
User profile determining unit, for determining user's authentication code of user, and obtain and marked with the user of the user
Know personal data corresponding to code, current shell temperature reduces related data and current environmental temperature data；
Disease forecasting unit, for by the personal data corresponding with user's authentication code of the user, working as precursor
Table temperature reduces related data and current environmental temperature data as test data, is input to the classification of diseases device, measures in advance
To disease type and corresponding disease probability of happening；Wherein, the disease type comprises at least：Common cold type and diarrhoea
Type；
First early warning reminding unit, for for each type in the disease type, when disease probability of happening is more than
Or during equal to default probability of happening threshold value, behaviour is reminded in the early warning that control performs disease type corresponding with the disease probability of happening
Make, the measure of suffering from cold is prevented accordingly to remind user to take.
In said system, it is preferred that also include：
Second early warning reminding unit, the disease probability of happening for being obtained to prediction carry out descending sort；Determine ranking
One disease probability of happening；When the disease probability of happening to rank the first is more than or equal to corresponding default probability of happening threshold value
When, control performs the prompting operation of disease type corresponding with the disease probability of happening to rank the first.
In said system, it is preferred that the first early warning reminding unit includes：
Instruction generation unit, for utilizing the disease type corresponding with the disease probability of happening, generation is accordingly
Instruction is reminded in early warning；
Instruction sending unit, instruction is reminded for sending the early warning to source of early warning, so that the source of early warning performs
Corresponding remind of instruction is reminded to operate with the early warning.
In said system, it is preferred that the source of early warning is smart machine.
In said system, it is preferred that the source of early warning is smart mobile phone.
In said system, it is preferred that the source of early warning is Intelligent bracelet.
As shown in the above, a kind of resistance to cool ability method for early warning of human body based on big data and system provided in application
In, the intelligent predicting to resistance to cool ability after user's perspiration is realized, first with by largely gathering going out for goal-selling crowd
The resistance to cool big data of human body that the resistance to cool data of sweat are formed, training obtain classification of diseases device.Then can be directly with the classification of diseases device
To predict disease type and corresponding disease probability of happening after user's perspiration.For each disease type, when disease probability of happening
During more than or equal to default probability of happening threshold value, it is believed that user is not resistant to rising or falling for the shell temperature of now way,
Operation is reminded in the early warning that now control performs disease type corresponding with the disease probability of happening, to remind user to increase and decrease to do
The measures such as clothing avoid the possible disease from occurring.When disease probability of happening is less than default probability of happening threshold value, then do not carve
Meaning is reminded, and user itself resistance of leaving deacclimatizes the change of this temperature, cultivates its resistance to cool ability.With this, realize and allow use
Family is gone to tackle the temperature change of body according to the actual conditions of itself resistance, itself resistance to cool ability is cultivated, so as to improve body
The purpose of quality.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of application, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of flow chart of the resistance to cool ability method for early warning embodiment 1 of human body based on big data of the application；
Fig. 2 is a kind of flow chart of the resistance to cool ability method for early warning embodiment 2 of human body based on big data of the application；
Fig. 3 is a kind of flow chart of the resistance to cool ability method for early warning embodiment 3 of human body based on big data of the application；
Fig. 4 is that a kind of structured flowchart of the resistance to cool ability early warning system embodiment 1 of human body based on big data of the application is illustrated
Figure.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present application, the technical scheme in the embodiment of the present application is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only some embodiments of the present application, rather than whole embodiments.It is based on
Embodiment in the application, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of the application protection.
The core of the application is to provide a kind of resistance to cool ability method for early warning of human body based on big data and system, to allow user
Gone to tackle the temperature change of body according to the actual conditions of itself resistance, cultivate itself resistance to cool ability, so as to improve body element
Matter.
In order that those skilled in the art more fully understand application scheme, with reference to the accompanying drawings and detailed description
The application is described in further detail.
With reference to figure 1, a kind of flow of the resistance to cool ability method for early warning embodiment 1 of human body based on big data of the application is shown
Figure, this method specifically may include steps of：
Step S100, the resistance to cool big data of human body is determined, and using the resistance to cool big data of the human body as training data, study point
The parameter of class device, obtain classification of diseases device；
Wherein, the resistance to cool big data of the human body be goal-selling crowd the resistance to cool record data of N bars, every resistance to cool note
Record data include the personal data of target individual corresponding with the resistance to cool record data of this in the target group, data of suffering from cold and
Disease data；The personal data include user's mark generation of target individual corresponding with resistance to this cool record data
Code；
Specifically, the application uses random forest grader in high-precision classification device, and instruction is used as using the resistance to cool big data of human body
Practice data, the parameter of Study strategies and methods.Certainly, except random forest grader, other high precision machines learning algorithms also may be used
To use, for example grader, the application such as deep learning neutral net, the learning machine that transfinites do not do considered critical.
After the parameter of grader determines, then classifier training is completed, and is obtained classification of diseases device and be can be used for actual prediction.
Step S101, user's authentication code of user is determined, and is obtained corresponding with user's authentication code of the user
Personal data, current shell temperature reduce related data and current environmental temperature data；
Step S102, by the personal data corresponding with user's authentication code of the user, current shell temperature drop
Low related data and current environmental temperature data are input to the classification of diseases device, prediction obtains disease class as test data
Type and corresponding disease probability of happening；Wherein, the disease type comprises at least：Common cold type and diarrhoea type；
In the application, it can be obtained by user's body surface humiture monitoring device and be dropped with the current shell temperature of the user
Low related data, user's body surface humiture monitoring device can be miniature label type wireless senser, and it is close to user's underwear,
Shell temperature reduces related data, initial temperature, lowest temperature such as destination object after the perspiration of collection target group can be monitored
Degree, duration etc..Certainly, the application is not carried out sternly to the mode of the current shell temperature reduction related data of acquisition user
Lattice limit, as long as what can be got can just use；
Step S103, for each type in the disease type, judge whether disease probability of happening is more than or equal to
Default probability of happening threshold value, if it is, into step S104；Otherwise, into step S105；
In the application, for different types of disease in disease type, we can preset the disease of each type
Probability of happening threshold value, certainly, these default probability of happening threshold values can be it is consistent equal or unequal,
This can be set according to actual conditions, and the application does not do considered critical；
Step S104, when disease probability of happening is more than or equal to default probability of happening threshold value, control performs and the disease
Operation is reminded in the early warning of disease type corresponding to probability of happening, prevents the measure of suffering from cold accordingly to remind user to take, for example increase
The measure such as subtract clothing, wipe the sweat.
Step S105, when disease probability of happening is less than default probability of happening threshold value, related data is only recorded, is not done deliberately
Remind, to cultivate the resistance to cool ability of user, train its fitness.
To sum up step S101 and step S102, specifically, using the classification of diseases device trained, by miniature label type without
Current shell temperature reduces related data after line Sensor monitoring gathers the perspiration of certain specific objective (user), by the body of the user
Table temperature reduces related data, personal data and current environmental temperature data as input, then output can automatically for classification of diseases device
The disease type and corresponding probability of happening that can occur.
In practical application, the resistance to cool big data of human body is obtained by herein below：
(1) target group is determined, gathers its related personal data, such as age, sex, body weight, existing disease history, shape
Into target group's individual database；
(2) after by being close to the perspiration of miniature label type wireless senser monitoring collection target group of target individual underwear
Shell temperature reduces situation, and records specific data (including the initial temperature of destination object, minimum temperature, duration etc.)；
The information such as local environment temperature are gathered simultaneously, these data are associated with user's authentication code of each target individual, with
Just these corresponding data are got by user's authentication code in the future；
(3) after target individual is perspired, record whether it occurs disease or the symptoms such as fever, if occurring, record
Its disease specific type；If do not occur, then it is assumed that it is the generation that human body itself resistance prevents disease, and to a certain extent
Improve or consolidated this species resistance of user；
(4) by the cool situation resistance to each time of each target individual in target group (including personal data, data of suffering from cold with
And follow-up disease data) stored as a resistance to cool training sample.When sample population quantity exceedes certain threshold value and sample
This quantity reaches certain threshold value, then the formation resistance to cool large database concept of human body, and the data in the resistance to cool large database concept of the human body are human body
Resistance to cool big data.
To sum up, it will be seen that step S100 is classification of diseases device training process, step S101 to step S105 is to make
With the classification of diseases device process trained, specifically, applying for a kind of resistance to cool ability early warning of human body based on big data of offer
In method, the intelligent predicting of resistance to cool ability after being perspired to user is realized, for each disease type, when disease probability of happening is big
When default probability of happening threshold value, it is believed that user is not resistant to rising or falling for the shell temperature of now way, this
When control perform the early warning of corresponding with disease probability of happening disease type and remind and operate, make increase and decrease clothing to remind user
The measures such as thing avoid the possible disease from occurring.When disease probability of happening is less than default probability of happening threshold value, then do not make deliberately
Remind, user itself resistance of leaving deacclimatizes the change of this temperature, cultivates its resistance to cool ability.With this, realize and allow user
Gone to tackle the temperature change of body according to the actual conditions of itself resistance, cultivate itself resistance to cool ability, so as to improve body element
The purpose of matter.
With reference to figure 2, a kind of flow of the resistance to cool ability method for early warning embodiment 2 of human body based on big data of the application is shown
Figure, problem is preset for the probability of happening threshold value of each type in disease type, we can use comparison simple
The method of single uniform threshold, i.e., all types of probability of happening threshold values are set to identical value (such as 20%), now, in disease type
In each type default probability of happening threshold value it is equal in the case of, specifically, prediction in step s 102 obtains disease type
And after corresponding disease probability of happening, execution can also be controlled to remind operation in the following manner：
Step S200, descending sort is carried out to the disease probability of happening that prediction obtains；
Step S201, the disease probability of happening to rank the first is determined；
Whether the disease probability of happening to be ranked the first described in step S202, judging is less than corresponding default probability of happening
Threshold value, if it is, into step S203；Otherwise, into step S204；
Step S203, when the disease probability of happening to rank the first is less than corresponding default probability of happening threshold value, only
Related data is recorded, does not do and deliberately reminds, to cultivate the resistance to cool ability of user, train its fitness；
Step S204, when the disease probability of happening to rank the first is more than or equal to corresponding default probability of happening threshold value
When, control performs the prompting operation of disease type corresponding with the disease probability of happening that this ranks the first, and sends alarm, reminds and use
The measure for preventing from suffering from cold such as changed one's clothes even if family or its guardian remove clothing segment or take, otherwise it is assumed that shell temperature
Reduce within user's tolerance range, user will temper its constitution on the premise of disease not occurring.
Certainly, must subsequently check be number two, the 3rd and disease probability of happening afterwards whether be more than or equal to it is respective
Default probability of happening, with reference to the above, and then perform corresponding content；
Specifically, after classification of diseases device exports the disease type that may occur and its corresponding probability of happening automatically,
These disease probability of happening are carried out with descending arrangement (such as common cold 2.5%, suffer from diarrhea 1.8%...), due in disease type
The default probability of happening threshold value of each type is equal, when the disease probability of happening to rank the first is less than corresponding default hair
During raw probability threshold value, illustrate the disease probability of happening of other (rank the first, second ...) also less than corresponding
Default probability of happening threshold value, so, related data now need to be only recorded, does not do and deliberately reminds, it is with this it is possible to prevente effectively from right
The execution of some invalid operations, and then improve whole control and perform the efficiency for reminding operation.
With reference to figure 3, a kind of flow of the resistance to cool ability method for early warning embodiment 3 of human body based on big data of the application is shown
Figure, specifically, it can be performed by following steps in step S104 and/or step S203, control is performed and occurred with the disease
Operation is reminded in the early warning of disease type corresponding to probability, to remind user to change clothing：
Step S300, using the disease type corresponding with the disease probability of happening, generate corresponding early warning and remind
Instruction；
Step S301, send the early warning to source of early warning and remind instruction so that the source of early warning perform with it is described pre-
Alert remind reminds operation corresponding to instruction.
In the application, in order to ensure the good Experience Degree of user, the source of early warning is smart machine, and the smart machine can
To be smart mobile phone or tablet personal computer, or Intelligent bracelet, intelligent watch, intelligent ring etc., the application is not strict
Limit, as long as facilitating user or guardian to find there is prompting action just to use in time, enter below by taking smart mobile phone as an example
Row explanation；
The transmission means of instruction is reminded for early warning, specifically, can be wirelessly to the hand of user or guardian
Machine (APP) sends early warning and reminds instruction, reminds corresponding remind of instruction to operate with the early warning to perform by this mobile phone；
Operated for reminding, can send prompt tone, it may also be said to be that display reminding information or both sent carries
Showing sound display reminding information again, the application does not do considered critical, as long as the mode of user or guardian can be reminded all
It can use.
It is corresponding with a kind of resistance to cool ability method for early warning embodiment 1 of human body based on big data of above-mentioned the application, the application
A kind of resistance to cool ability early warning system embodiment 1 of human body based on big data is additionally provided, with reference to figure 4, the system 400 can include
Following content：
Classifier training unit 401, for determining the resistance to cool big data of human body, and using the resistance to cool big data of the human body as instruction
Practice data, the parameter of Study strategies and methods, obtain classification of diseases device；
Wherein, the resistance to cool big data of the human body be goal-selling crowd the resistance to cool record data of N bars, every resistance to cool note
Record data include the personal data of target individual corresponding with the resistance to cool record data of this in the target group, data of suffering from cold and
Disease data；The personal data include user's mark generation of target individual corresponding with resistance to this cool record data
Code；
User profile determining unit 402, for determining user's authentication code of user, and obtain the user with the user
Personal data corresponding to authentication code, current shell temperature reduce related data and current environmental temperature data；
Disease forecasting unit 403, for by the personal data corresponding with user's authentication code of the user, currently
Shell temperature reduces related data and current environmental temperature data as test data, is input to the classification of diseases device, predicts
Obtain disease type and corresponding disease probability of happening；Wherein, the disease type comprises at least：Common cold type and drawing tripe
Subtype；
First early warning reminding unit 404, for for each type in the disease type, when disease probability of happening is big
When default probability of happening threshold value, the early warning that control performs disease type corresponding with the disease probability of happening is reminded
Operation, the measure of suffering from cold is prevented accordingly to remind to take.
In the application, the first early warning reminding unit 404 can include：
Instruction generation unit, for utilizing the disease type corresponding with the disease probability of happening, generation is accordingly
Instruction is reminded in early warning；
Instruction sending unit, instruction is reminded for sending the early warning to source of early warning, so that the source of early warning performs
Corresponding remind of instruction is reminded to operate with the early warning.
In the application, the source of early warning is smart machine, and the smart machine can be smart mobile phone, or intelligence
Bracelet.
To sum up, based on practical application, for classification of diseases device training process and the classification of diseases device process trained is used,
For example：
(1) classification of diseases device is trained
As sent out multiple miniature label type wireless sensers to the student of all middle and primary schools and kindergarten in the range of certain city
Gather student the resistance to cool data of perspiration, and information specific with student, perspire suffer from cold after disease a situation arises and there and then
The data such as temperature form resistance to cool large database concept together.Further, using random forest as prediction grader, using resistance to cool
Big data trains grader (i.e. the parameters of Study strategies and methods) as training sample.During specific classifier training,
Species so that disease occurs is used as output (to avoid parameter excessive, often only using common disease as output category), other numbers
According to as input, after algorithmic statement meets (for example algorithm iteration number reaches certain number), that is, the classification trained
Device, that is, obtain classification of diseases device.
(2) using the classification of diseases device trained
It is resistance to cool to gather the perspiration of student for the miniature label type wireless senser of student's wearing of certain local bottom class of kindergarten
Data, after miniature label type wireless senser collects data, as the input of grader, if disease possibility occurs
Reach certain threshold value, then warning data is pushed to the current guardian i.e. mobile phone of kindergarener of user by information transmission modular
On, otherwise do not make any processing.After teacher receives warning information, then user's body is determined according to the ID of warning information
Part, increase and decrease clothing for it according to actual conditions or wipe the sweat, avoid it from suffering from cold.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference with other embodiments, between each embodiment identical similar part mutually referring to.
For system class embodiment, because it is substantially similar to embodiment of the method, so describing fairly simple, related part is joined
See the part explanation of embodiment of the method.
The resistance to cool ability method for early warning of a kind of human body based on big data provided herein and system are carried out above
It is discussed in detail.Specific case used herein is set forth to the principle and embodiment of the application, above example
Illustrate that being only intended to help understands the present processes and its core concept.It should be pointed out that the common skill for the art
For art personnel, on the premise of the application principle is not departed from, some improvement and modification can also be carried out to the application, these change
Enter and modification is also fallen into the application scope of the claims.
Claims (10)
- A kind of 1. resistance to cool ability method for early warning of human body based on big data, it is characterised in that including：The resistance to cool big data of human body is determined, and using the resistance to cool big data of the human body as training data, the parameter of Study strategies and methods, is obtained To classification of diseases device；Wherein, the resistance to cool big data of the human body be goal-selling crowd the resistance to cool record data of N bars, every resistance to cool record number According to personal data, data of suffering from cold and the disease for including target individual corresponding with the resistance to cool record data of this in the target group Data；The personal data include user's authentication code of target individual corresponding with resistance to this cool record data；User's authentication code of user is determined, and obtains personal data corresponding with user's authentication code of the user, currently Shell temperature reduces related data and current environmental temperature data；By the personal data corresponding with user's authentication code of the user, current shell temperature reduces related data and worked as Preceding ambient temperature data is input to the classification of diseases device, prediction obtains disease type and corresponding disease as test data Probability of happening；Wherein, the disease type comprises at least：Common cold type and diarrhoea type；For each type in the disease type, when disease probability of happening is more than or equal to default probability of happening threshold value, Operation is reminded in the early warning that control performs disease type corresponding with the disease probability of happening, corresponding anti-to remind user to take Only suffer from cold measure.
- 2. the method as described in claim 1, it is characterised in that when the default probability of happening of each type in the disease type When threshold value is equal, after the prediction obtains disease type and corresponding disease probability of happening, in addition to：Descending sort is carried out to the disease probability of happening that prediction obtains；It is determined that the disease probability of happening to rank the first；When the disease probability of happening to rank the first is less than corresponding default probability of happening threshold value, does not do and deliberately carry Wake up, to cultivate the resistance to cool ability of user, train its fitness.
- 3. the method as described in claim 1, it is characterised in that the control performs disease corresponding with the disease probability of happening The prompting operation of sick type, including：Using the disease type corresponding with the disease probability of happening, generate corresponding early warning and remind instruction；The early warning is sent to source of early warning and reminds instruction, reminds instruction corresponding with the early warning so that the source of early warning performs Prompting operation.
- 4. the method as described in claims 1 to 3 any one, it is characterised in that described to make the resistance to cool big data of the human body For training data, the parameter of Study strategies and methods, obtain in classification of diseases device, the grader is random forest grader.
- A kind of 5. resistance to cool ability early warning system of human body based on big data, it is characterised in that including：Classifier training unit, for determining the resistance to cool big data of human body, and using the resistance to cool big data of the human body as training data, The parameter of Study strategies and methods, obtain classification of diseases device；Wherein, the resistance to cool big data of the human body be goal-selling crowd the resistance to cool record data of N bars, every resistance to cool record number According to personal data, data of suffering from cold and the disease for including target individual corresponding with the resistance to cool record data of this in the target group Data；The personal data include user's authentication code of target individual corresponding with resistance to this cool record data；User profile determining unit, for determining user's authentication code of user, and obtain and identify generation with the user of the user Personal data corresponding to code, current shell temperature reduce related data and current environmental temperature data；Disease forecasting unit, for by the personal data corresponding with user's authentication code of the user, current body surface temperature Degree reduces related data and current environmental temperature data as test data, is input to the classification of diseases device, prediction obtains disease Sick type and corresponding disease probability of happening；Wherein, the disease type comprises at least：Common cold type and diarrhoea class Type；First early warning reminding unit, for for each type in the disease type, when disease probability of happening is more than or waits When default probability of happening threshold value, operation is reminded in the early warning that control performs disease type corresponding with the disease probability of happening, The measure of suffering from cold is prevented to remind user to take accordingly.
- 6. system as claimed in claim 5, it is characterised in that also include：Second early warning reminding unit, the disease probability of happening for being obtained to prediction carry out descending sort；It is determined that rank the first Disease probability of happening；When the disease probability of happening to rank the first is more than or equal to corresponding default probability of happening threshold value, Control performs the prompting operation of disease type corresponding with the disease probability of happening to rank the first.
- 7. system as claimed in claim 5, it is characterised in that the first early warning reminding unit includes：Instruction generation unit, for utilizing the disease type corresponding with the disease probability of happening, generate corresponding early warning Remind instruction；Instruction sending unit, instruction is reminded for sending the early warning to source of early warning, so that the source of early warning performs and institute State early warning and remind prompting operation corresponding to instruction.
- 8. system as claimed in claim 7, it is characterised in that the source of early warning is smart machine.
- 9. system as claimed in claim 8, it is characterised in that the source of early warning is smart mobile phone.
- 10. system as claimed in claim 8, it is characterised in that the source of early warning is Intelligent bracelet.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510209572.5A CN104750880B (en) | 2015-04-28 | 2015-04-28 | A kind of resistance to cool ability method for early warning of human body based on big data and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510209572.5A CN104750880B (en) | 2015-04-28 | 2015-04-28 | A kind of resistance to cool ability method for early warning of human body based on big data and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104750880A CN104750880A (en) | 2015-07-01 |
| CN104750880B true CN104750880B (en) | 2018-03-02 |
Family
ID=53590564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510209572.5A Active CN104750880B (en) | 2015-04-28 | 2015-04-28 | A kind of resistance to cool ability method for early warning of human body based on big data and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104750880B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446765B (en) * | 2016-07-26 | 2019-09-03 | 重庆大学 | A kind of health status evaluation system based on multidimensional physiology big data deep learning |
| CN109240745B (en) * | 2018-08-01 | 2023-04-11 | 福建天泉教育科技有限公司 | Instruction distribution method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101073495A (en) * | 2007-06-15 | 2007-11-21 | 东华大学 | Embedded clothing intelligent device and method for estimating human-body sub-health |
| CN101766479A (en) * | 2008-12-30 | 2010-07-07 | 上海欣唐电子有限公司 | Remote health monitoring system based on portable monitoring terminal with wireless communication function |
| KR20140014445A (en) * | 2012-07-24 | 2014-02-06 | 주식회사 제이시스메디칼 | Apparatus for outputting dual laser |
| CN103763437A (en) * | 2014-01-23 | 2014-04-30 | 惠州Tcl移动通信有限公司 | Mobile terminal achieving method and system and mobile terminal with health reminding function |
| CN104287706A (en) * | 2014-10-29 | 2015-01-21 | 云南大学 | Human health state real-time monitoring, diagnosis and treatment recommendation system |
-
2015
- 2015-04-28 CN CN201510209572.5A patent/CN104750880B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101073495A (en) * | 2007-06-15 | 2007-11-21 | 东华大学 | Embedded clothing intelligent device and method for estimating human-body sub-health |
| CN101766479A (en) * | 2008-12-30 | 2010-07-07 | 上海欣唐电子有限公司 | Remote health monitoring system based on portable monitoring terminal with wireless communication function |
| KR20140014445A (en) * | 2012-07-24 | 2014-02-06 | 주식회사 제이시스메디칼 | Apparatus for outputting dual laser |
| CN103763437A (en) * | 2014-01-23 | 2014-04-30 | 惠州Tcl移动通信有限公司 | Mobile terminal achieving method and system and mobile terminal with health reminding function |
| CN104287706A (en) * | 2014-10-29 | 2015-01-21 | 云南大学 | Human health state real-time monitoring, diagnosis and treatment recommendation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104750880A (en) | 2015-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | SPHA: Smart personal health advisor based on deep analytics | |
| US10114453B2 (en) | Smart wearable devices and methods with power consumption and network load optimization | |
| Morgan et al. | Is the Theory of Planned Behaviour an appropriate model for human fertility? | |
| Cook et al. | CASAS: A smart home in a box | |
| Gambhir et al. | The diagnosis of dengue disease: An evaluation of three machine learning approaches | |
| CN103279687B (en) | A kind of personalized health service system based on context-aware | |
| Kviesis et al. | Application of fuzzy logic for honey bee colony state detection based on temperature data | |
| CN103281953A (en) | Patient monitoring system and method for monitoring the physiological status of a patient | |
| CN113196415A (en) | Method and apparatus for predicting the evolution of a visually relevant parameter over time | |
| CN113261067A (en) | Method and device for establishing a model for predicting the evolution of a visually relevant parameter over time | |
| Rodrigues et al. | Dengue in Cape Verde: vector control and vaccination | |
| CN104750880B (en) | A kind of resistance to cool ability method for early warning of human body based on big data and system | |
| CN109714995A (en) | Intelligence sensing clothes | |
| Chaminda et al. | A smart reminder system for complex human activities | |
| Moulik et al. | Prioritized payload tuning mechanism for wireless body area network-based healthcare systems | |
| CN106446552A (en) | Prediction method and prediction system for sleep disorder based on incremental neural network model | |
| CN106297217A (en) | Baby dressing based reminding method and device | |
| Adhitya et al. | The BIOdress: a body-worn interface for environmental embodiment | |
| CN105069728A (en) | Emotion inference method based on wireless sensor network | |
| Urda et al. | Energy-efficient reprogramming in wsn using constructive neural networks. | |
| NTAWUZUMUNSI et al. | Design and implementation of smart bees hiving & monitoring system | |
| Padma et al. | Analysis of Current Smart Wearable Trends using Internet of Medical Things | |
| Ali | Situational awareness through IoT sensors: A smart healthcare system as a use case | |
| Cooper et al. | Decision making | |
| CN106372442A (en) | Dental ulcer prediction method and system based on incremental neural network model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |