CN108154930A - Fetal weight Forecasting Methodology and device - Google Patents
Fetal weight Forecasting Methodology and device Download PDFInfo
- Publication number
- CN108154930A CN108154930A CN201711416456.6A CN201711416456A CN108154930A CN 108154930 A CN108154930 A CN 108154930A CN 201711416456 A CN201711416456 A CN 201711416456A CN 108154930 A CN108154930 A CN 108154930A
- Authority
- CN
- China
- Prior art keywords
- pregnant woman
- value
- weight
- fetal weight
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention provides a kind of fetal weight Forecasting Methodology and device, wherein method include:Establish the fetal weight prediction model of the physical parameter of pregnant woman and the correspondence of fetal weight;The first input parameter is obtained, obtains the second input parameter, according to the first input parameter and the second input parameter, calculates and obtains pregnant woman's changes of weight value and pregnant woman's body fat changing value;According to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight prediction model, fetal weight predicted value is obtained.The above method and device, fetal weight can be predicted according to pregnant woman's changes of weight value and pregnant woman's body fat changing value, it is participated in without professional medical instrument and medical professional, and Forecasting Methodology has no effect to pregnant woman and foetus health, it can repeated detection, entire prediction process is simple and convenient, convenient for universal.
Description
Technical field
The present invention relates to health care technology field more particularly to a kind of fetal weight Forecasting Methodology and devices.
Background technology
When before the infant is born can be to the assessment of development of fetus situation and as childbirth is determined to the estimation of fetal weight
Between and mode reference.Currently more accurately Estimation of fetal weight measuring method be using ultrasonic examination obtain about tire
Biometric (biometric) parameter of youngster, the estimation of fetal weight is carried out with empirical equation model.
But the accuracy of ultrasonic examination only has 85%, and since pregnant woman cannot frequently use ultrasound examination, and
And ultrasound examination needs to be diagnosed using special equipment and medical practitioner so that can not be general to the Forecasting Methodology of fetal weight
And so as to which real-time nutrition guide and suggestion can not be done to the development of pregnant and lying-in women and fetus, the best tune of development of fetus is delayed
Whole opportunity.
Invention content
The present invention provides a kind of fetal weight Forecasting Methodology and device, to solve forecast body weight of the prior art to fetus
The technical issues of mode is complicated and inconvenient.
First aspect present invention provides a kind of fetal weight Forecasting Methodology, including:
Establish the fetal weight prediction model of the physical parameter of pregnant woman and the correspondence of fetal weight;Wherein, the object
It manages parameter and includes pregnant woman's changes of weight value and pregnant woman's body fat changing value;
The first input parameter is obtained, wherein, first input parameter includes pregnant woman's Current body mass value and pregnant woman works as precursor
Fat value;
The second input parameter is obtained, wherein, second input parameter includes pregnant woman's history weight value and pregnant woman's history body
Fat value;
According to the first input parameter and the second input parameter, calculate and obtain pregnant woman's changes of weight value and the variation of pregnant woman's body fat
Value;
According to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight prediction model, fetus is obtained
Forecast body weight value.
Further, the fetal weight prediction model of the physical parameter of pregnant woman and the correspondence of fetal weight is established, is had
Body includes:
Obtain the physical parameter of pregnant woman and corresponding practical fetal weight;
It is preserved using the physical parameter of pregnant woman with corresponding practical fetal weight as an effective sample;
Multiple effective samples are obtained, and multiple effective samples are preserved to storage device;
Multiple effective samples in storage device are trained by supervision type machine learning algorithm, to obtain fetus body
Weight prediction model.
Further, the effective sample acquiring way further includes:
By the physical parameter of pregnant woman and the correspondence of all numbers of pregnancy, the correspondence of fetal weight and all numbers of pregnancy,
To obtain the correspondence of the physical parameter of pregnant woman and fetal weight.
Further, the fetal weight prediction model is expressed as with expression formula:W=x1*(Δa)+x2*(Δb)+x3*
(Δ c), wherein, W is fetal weight predicted value, and Δ a is pregnant woman's changes of weight value, and Δ b is pregnant woman's body fat changing value, and Δ c is tire
Youngster's weight standard value, x1、x2And x3Value according to supervision type machine learning algorithm in storage device multiple effective samples carry out
It is determined after training.
Further, the first input parameter is obtained to specifically include:
Pregnant woman is measured using body fat scale, is surveyed with obtaining pregnant woman's Current body mass measured value and the current body fat of pregnant woman
Magnitude;
Pregnant woman's metrical information is uploaded in storage device, pregnant woman's metrical information includes pregnant woman ID, pregnant woman works as precursor
Resurvey magnitude, the current bodily fat measurement value of pregnant woman and time of measuring;
Pregnant woman's Current body mass measured value and the current bodily fat measurement value of the pregnant woman are used according to history valid data
Trend prediction algorithm is modified, to obtain pregnant woman's Current body mass value and the current body fat value of pregnant woman, by pregnant woman's Current body mass value and
The current body fat value of pregnant woman as the first input parameter, wherein, the history valid data be storage device in store it is described pregnant
All revised pregnant woman's Current body mass measured values and the current bodily fat measurement value of the pregnant woman corresponding to woman ID;Pregnant woman works as
Previous body weight value is to the revised value of pregnant woman's Current body mass measured value, and the current body fat value of pregnant woman is current bodily fat measurement value to pregnant woman
Revised value.
Second aspect of the present invention provides a kind of fetal weight prediction meanss, including:
Fetal weight prediction model establishes module, for establishing the correspondence of the physical parameter of pregnant woman and fetal weight
Fetal weight prediction model;Wherein, the physical parameter includes pregnant woman's changes of weight value and pregnant woman's body fat changing value;
First acquisition module, for obtaining the first input parameter, wherein, first input parameter works as precursor including pregnant woman
Weight values and the current body fat value of pregnant woman;
Second acquisition module, for obtaining the second input parameter, wherein, second input parameter includes pregnant woman's history body
Weight values and pregnant woman's history body fat value;
Computing module, for according to the first input parameter and the second input parameter, calculate obtain pregnant woman's changes of weight value and
Pregnant woman's body fat changing value;
Prediction module, for being predicted according to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight
Model obtains fetal weight predicted value.
Further, fetal weight prediction model is established module and is specifically included:
First acquisition submodule, for obtaining the physical parameter of pregnant woman and corresponding practical fetal weight;
Effective sample acquisition submodule, for having the physical parameter of pregnant woman with corresponding practical fetal weight as one
Imitate Sample preservation;
Submodule is preserved, for obtaining multiple effective samples, and multiple effective samples are preserved to storage device;
Fetal weight prediction model setting up submodule, for passing through supervision type machine learning algorithm to more in storage device
A effective sample is trained, to obtain fetal weight prediction model.
Further, effective sample acquisition submodule further includes:
By the physical parameter of pregnant woman and the correspondence of all numbers of pregnancy, the correspondence of fetal weight and all numbers of pregnancy,
To obtain the correspondence of the physical parameter of pregnant woman and fetal weight.
Further, the fetal weight prediction model is expressed as with expression formula:W=x1*(Δa)+x2*(Δb)+x3*
(Δ c), wherein, W is fetal weight predicted value, and Δ a is pregnant woman's changes of weight value, and Δ b is pregnant woman's body fat changing value, and Δ c is tire
Youngster's weight standard value, x1、x2And x3Value according to supervision type machine learning algorithm in storage device multiple effective samples carry out
It is determined after training.
Further, the first acquisition module specifically includes:
Submodule is measured, pregnant woman is measured for passing through body fat scale, to obtain pregnant woman's Current body mass measured value
With the current bodily fat measurement value of pregnant woman;
Submodule is uploaded, for pregnant woman's metrical information to be uploaded in storage device, pregnant woman's metrical information includes pregnant
Woman ID, pregnant woman's Current body mass measured value, the current bodily fat measurement value of pregnant woman and time of measuring;
Submodule is corrected, for current to pregnant woman's Current body mass measured value and the pregnant woman according to history valid data
Bodily fat measurement value is modified using trend prediction algorithm, will be pregnant to obtain pregnant woman's Current body mass value and the current body fat value of pregnant woman
Woman's Current body mass value and the current body fat value of pregnant woman as the first input parameter, wherein, the history valid data be storage device
All revised pregnant woman's Current body mass measured values and the pregnant woman corresponding to the pregnant woman ID of middle storage work as precursor
Fat measured value;Pregnant woman's Current body mass value is to the revised value of pregnant woman's Current body mass measured value, and the current body fat value of pregnant woman is to pregnant
The current revised value of bodily fat measurement value of woman.
The present invention provides a kind of fetal weight Forecasting Methodology and device, pre-establishes the physical parameter and fetal weight of pregnant woman
Correspondence fetal weight prediction model, pregnant woman's Current body mass value and the current body fat value of pregnant woman are then obtained by measurement,
Again compared with pregnant woman's history weight value and pregnant woman's history body fat value, pregnant woman's changes of weight value and pregnant woman's body fat changing value are obtained,
Finally according to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight prediction model, fetal weight predicted value is obtained.On
Method and device is stated, fetal weight can be predicted according to pregnant woman's changes of weight value and pregnant woman's body fat changing value, nothing
Professional medical instrument and medical professional is needed to participate in, and Forecasting Methodology has no effect to pregnant woman and foetus health, it can be multiple
Detection, it is entire to predict that process is simple and convenient, convenient for universal.
Description of the drawings
The invention will be described in more detail below based on embodiments and refering to the accompanying drawings.Wherein:
Fig. 1 is the flow diagram of fetal weight Forecasting Methodology that the embodiment of the present invention one provides;
Fig. 2 is another flow diagram of fetal weight Forecasting Methodology that the embodiment of the present invention one provides;
Fig. 3 is the another flow diagram of fetal weight Forecasting Methodology that the embodiment of the present invention one provides;
Fig. 4 is a structure diagram of fetal weight prediction meanss provided by Embodiment 2 of the present invention.
In the accompanying drawings, identical component uses identical reference numeral.Attached drawing is not drawn according to practical ratio.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is the flow diagram of fetal weight Forecasting Methodology that the embodiment of the present invention one provides;As shown in Figure 1, this
Embodiment provides a kind of fetal weight Forecasting Methodology, including step 101- steps 105.
Wherein, step 101, the fetal weight prediction mould of the physical parameter of pregnant woman and the correspondence of fetal weight is established
Type;Wherein, physical parameter includes pregnant woman's changes of weight value and pregnant woman's body fat changing value.
Specifically, an object of the present invention be when predicting fetal weight, reduce prediction complexity and specially
Industry, and the injury of any possibility is not caused to pregnant woman and fetal body health.Therefore, in the present embodiment, foundation
Fetal weight prediction model is made of the physical parameter of pregnant woman and the correspondence of fetal weight, and physical parameter includes pregnant woman's weight
Changing value and pregnant woman's body fat changing value.The weight and body fat of pregnant woman can be measured, and measured by body fat scale
Journey is simple and convenient, and harmless to the body.Physical parameter may also include the body indexs such as protein, bone amount, moisture.
Step 102, the first input parameter is obtained, wherein, first input parameter includes pregnant woman's Current body mass value and pregnant
The current body fat value of woman.
Specifically, when needing to predict fetal weight, pregnant woman's Current body mass value is measured by body fat scale and pregnant woman works as
Preceding body fat value, pregnant woman's weight value that pregnant woman's Current body mass value currently measures (the current body fat value of pregnant woman is similarly).
Step 103, the second input parameter is obtained, wherein, second input parameter includes pregnant woman's history weight value and pregnant
Woman's history body fat value.
Specifically, due to physical parameter be pregnant woman's changes of weight value and pregnant woman's body fat changing value, obtain pregnant woman work as
After previous body weight value and the current body fat value of pregnant woman, pregnant woman's history weight value and pregnant woman's history body fat value should be also obtained, to calculate
Pregnant woman's changes of weight value and pregnant woman's body fat changing value.Preferably, the weight that pregnant woman's history weight value measures at pregnancy initial stage for pregnant woman
Value, the body fat value that pregnant woman's history body fat value is measured for pregnant woman's pregnancy initial stage (such as being pregnant in one month).Pregnant woman's history weight value
It can be stored in advance in storage device with pregnant woman's history body fat value, can not also be limited herein by being manually entered.
Step 104, it according to the first input parameter and the second input parameter, calculates and obtains pregnant woman's changes of weight value and pregnant woman's body
Fat changing value.
The absolute value of the difference of pregnant woman's Current body mass value and pregnant woman's history weight value is asked for, and is become as pregnant woman's weight
Change value;The absolute value of the difference of the current body fat value of pregnant woman and pregnant woman's history body fat value is asked for, and is changed as pregnant woman's body fat
Value.
Step 105, according to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight prediction model,
Obtain fetal weight predicted value.
After pregnant woman's changes of weight value and pregnant woman's body fat changing value is obtained, predicted according to fetal weight prediction model,
To obtain fetal weight predicted value.
Fetal weight Forecasting Methodology in the present embodiment, according to pregnant woman's changes of weight value and pregnant woman's body fat changing value come
Fetal weight is predicted, is participated in without professional medical instrument and medical professional, and Forecasting Methodology is to pregnant woman and fetus
Health has no effect, can repeated detection.Entire prediction process is simple and convenient, convenient for universal.
Further, as shown in Fig. 2, step 101 specifically includes step 1011- steps 1012.
Wherein, step 1011, the physical parameter of pregnant woman and corresponding practical fetal weight are obtained.The detections such as B ultrasound can be passed through
Means obtain the correspondence between the physical parameter of pregnant woman and fetal weight, since the fetal weight obtained according to B ultrasound is accurate
Rate is higher, therefore, will be used as practical fetal weight by the fetal weight that B ultrasound obtains, with subsequently to establish fetal weight prediction
Model provides accuracy rate higher training sample.
Step 1012, it is preserved using the physical parameter of pregnant woman with corresponding practical fetal weight as an effective sample.
Further, the acquisition of effective sample except through the mode that direct B ultrasound measures obtain the physical parameter of pregnant woman with
The correspondence of practical fetal weight, effective sample acquiring way further include:Pass through the physical parameter of pregnant woman and all numbers of pregnancy
The correspondence of correspondence, fetal weight and all numbers of pregnancy, to obtain, the physical parameter of pregnant woman is corresponding with fetal weight to close
System.
It is corresponding with all numbers of pregnancy according to the existing fetal weight correspondence of number all with pregnancy, the physical parameter of pregnant woman
The big datas such as relationship, to obtain the physical parameter of pregnant woman and corresponding practical fetal weight.
Step 1013, multiple effective samples are obtained, and multiple effective samples are preserved to storage device, for subsequently establishing
Fetal weight prediction model uses.
Step 1014, multiple effective samples in storage device are trained by supervision type machine learning algorithm, with
Obtain fetal weight prediction model.
Multiple effective samples are trained by supervision type machine learning algorithm and preset Numerical Boundary, tire can be obtained
Youngster's forecast body weight model.Effective sample is more, and the forecasting accuracy for the fetal weight prediction model that training obtains is higher.
Further, the fetal weight prediction model is expressed as with expression formula:W=x1*(Δa)+x2*(Δb)+x3*
(Δ c), wherein, W is fetal weight predicted value, and Δ a is pregnant woman's changes of weight value, and Δ b is pregnant woman's body fat changing value, and Δ c is tire
Youngster's weight standard value, x1、x2And x3Value according to supervision type machine learning algorithm in storage device multiple effective samples carry out
It is determined after training.
According to the statistics and regression forecasting of data, establish fetal weight and pregnant woman's changes of weight value, body fat changing value it
Between correlativity, complicated nonlinear multivariable problem is deduced and carrys out operation for simple multi head linear equation.Due to number of individuals
According to time of measuring and actual measured results dynamic change, and collected conceptual data can also gradually increase, or more
State the coefficient x in expression1、x2And x3It is a dynamic value, it specifically need to be according to supervision type machine learning algorithm in storage device
Multiple effective samples determine after being trained.
Further, as shown in figure 3, step 102 specifically includes step 1021- steps 1023.
Wherein, step 1021, pregnant woman is measured using body fat scale, with obtain pregnant woman's Current body mass measured value and
The current bodily fat measurement value of pregnant woman.
Specifically, pregnant woman's Current body mass value and the current body fat value of pregnant woman are acquired by body fat scale, human body fat
Fat scale can be carried out data transmission by the wireless telecom equipment that itself includes with smart machine, for example, body fat scale collect it is pregnant
After woman's Current body mass value and the current body fat value of pregnant woman, equipment is by pregnant woman's Current body mass value of acquisition and pregnant woman by radio communication
Current body fat value is sent to smart machine, and smart machine can be mobile phone, computer, ipad etc., and pregnant woman is worked as precursor by smart machine
The storage device or the special storage device for being used to store effective sample that weight values and the current body fat value of pregnant woman are uploaded onto the server
In, it does not limit herein.
Step 1022, pregnant woman's metrical information is uploaded in storage device, pregnant woman's metrical information includes pregnant woman ID, pregnant
Woman's Current body mass measured value, the current bodily fat measurement value of pregnant woman and time of measuring.
Specifically, the pregnant woman of fetal weight prediction is carried out using this method for each, for the first time in use, can be to be somebody's turn to do
Pregnant woman sets an exclusive identification code (being realized such as by registration), i.e. pregnant woman ID.Work as to pregnant woman's Current body mass value and pregnant woman
When preceding body fat value is stored, time of measuring should be also stored simultaneously, so as to current to pregnant woman subsequently according to the sequence of time of measuring
Weight value and the current body fat value of pregnant woman are analyzed.
Further, be also stored with pregnant woman's essential information in storage device, pregnant woman's essential information include pregnant woman ID, the age,
The essential informations such as height.Further, pregnant woman's essential information further includes weight value (i.e. pregnant woman's history that pregnant woman measures at pregnancy initial stage
Weight value) and pregnant woman be pregnant the body fat value (i.e. pregnant woman's history body fat value) that measures of initial stage.
Step 1023, pregnant woman's Current body mass measured value and the current bodily fat measurement value of pregnant woman are used according to history valid data
Trend prediction algorithm is modified, to obtain pregnant woman's Current body mass value and the current body fat value of pregnant woman, by pregnant woman's Current body mass value and
The current body fat value of pregnant woman as the first input parameter, wherein, the history valid data be storage device in store it is described pregnant
All revised pregnant woman's Current body mass measured values and the current bodily fat measurement value of the pregnant woman corresponding to woman ID;Pregnant woman works as
Previous body weight value is to the revised value of pregnant woman's Current body mass measured value, and the current body fat value of pregnant woman is current bodily fat measurement value to pregnant woman
Revised value.
Since the pregnant woman's Current body mass measured value measured and the current bodily fat measurement value of pregnant woman are it is possible that deviation, is
So that more accurate to the prediction of fetal weight, it is necessary first to pregnant woman's Current body mass measured value and the current bodily fat measurement of pregnant woman
Value is modified, and the pregnant woman had previously measured the history valid data being stored in storage device and carried out according to specific correcting mode
It corrects, if there is no the history valid data of the pregnant woman in storage device, is according to the age of the pregnant woman, height and pregestational weight
The pregnant woman selects historical data template, and data based on the historical data module are pre-stored big data.
Embodiment two
The present embodiment is the device embodiment of embodiment one, for performing the method in embodiment one.
Fig. 4 is a structure diagram of fetal weight prediction meanss provided by Embodiment 2 of the present invention, as shown in figure 4, this
Embodiment provides a kind of fetal weight prediction meanss, and module 201, the first acquisition module are established including fetal weight prediction model
202nd, the second acquisition module 203, computing module 204 and prediction module 205.
Wherein, fetal weight prediction model establishes module 201, for establishing pair of the physical parameter of pregnant woman and fetal weight
The fetal weight prediction model that should be related to;Wherein, the physical parameter includes pregnant woman's changes of weight value and pregnant woman's body fat changing value.
First acquisition module 202, for obtaining the first input parameter, wherein, first input parameter is worked as including pregnant woman
Previous body weight value and the current body fat value of pregnant woman.
Second acquisition module 203, for obtaining the second input parameter, wherein, second input parameter is gone through including pregnant woman
History weight value and pregnant woman's history body fat value.
Computing module 204, for according to the first input parameter and the second input parameter, calculating and obtaining pregnant woman's changes of weight value
With pregnant woman's body fat changing value.
Prediction module 205, for pre- according to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight
Model is surveyed, obtains fetal weight predicted value.
Since the present embodiment is to can be found in the note in embodiment one with one corresponding device embodiment of embodiment, specific details
It carries, details are not described herein.
Further, fetal weight prediction model is established module 201 and is specifically included:
First acquisition submodule, for obtaining the physical parameter of pregnant woman and corresponding practical fetal weight;
Effective sample acquisition submodule, for having the physical parameter of pregnant woman with corresponding practical fetal weight as one
Imitate Sample preservation;
Submodule is preserved, for obtaining multiple effective samples, and multiple effective samples are preserved to storage device;
Fetal weight prediction model setting up submodule, for passing through supervision type machine learning algorithm to more in storage device
A effective sample is trained, to obtain fetal weight prediction model.
Further, effective sample acquisition submodule further includes:
By the physical parameter of pregnant woman and the correspondence of all numbers of pregnancy, the correspondence of fetal weight and all numbers of pregnancy,
To obtain the correspondence of the physical parameter of pregnant woman and fetal weight.
Further, fetal weight prediction model is expressed as with expression formula:Fetal weight prediction model is represented with expression formula
For:W=x1*(Δa)+x2*(Δb)+x3* (Δ c), wherein, W be fetal weight predicted value, Δ a be pregnant woman's changes of weight value, Δ
B be pregnant woman's body fat changing value, Δ c be fetal weight standard value, x1、x2And x3Value according to supervision type machine learning algorithm to depositing
Multiple effective samples in storage equipment determine after being trained.
Further, the first acquisition module 202 specifically includes:
Submodule is measured, pregnant woman is measured for passing through body fat scale, to obtain pregnant woman's Current body mass measured value
With the current bodily fat measurement value of pregnant woman;
Submodule is uploaded, for pregnant woman's metrical information to be uploaded in storage device, pregnant woman's metrical information includes pregnant
Woman ID, pregnant woman's Current body mass measured value, the current bodily fat measurement value of pregnant woman and time of measuring;
Submodule is corrected, for current to pregnant woman's Current body mass measured value and the pregnant woman according to history valid data
Bodily fat measurement value is modified using trend prediction algorithm, to obtain pregnant woman's Current body mass value and the current body fat value of pregnant woman, and will
Pregnant woman's Current body mass value and the current body fat value of pregnant woman as the first input parameter, wherein, the history valid data for storage set
All revised pregnant woman's Current body mass measured values and the pregnant woman corresponding to the pregnant woman ID of standby middle storage are current
Bodily fat measurement value;Pregnant woman's Current body mass value is to the revised value of pregnant woman's Current body mass measured value, and the current body fat value of pregnant woman is pair
The current revised value of bodily fat measurement value of pregnant woman.
It should be understood that disclosed embodiment of this invention is not limited to specific structure disclosed herein, processing step
Or material, and the equivalent substitute for these features that those of ordinary skill in the related art are understood should be extended to.It should also manage
Solution, term as used herein is used only for the purpose of describing specific embodiments, and is not intended to limit.
" one embodiment " or " embodiment " mentioned in specification means the special characteristic described in conjunction with the embodiments, structure
Or characteristic is included at least one embodiment of the present invention.Therefore, the phrase " reality that specification various places throughout occurs
Apply example " or " embodiment " same embodiment might not be referred both to.
In addition, described feature, structure or characteristic can be attached to one or more in fact in any other suitable manner
It applies in example.In above description, some concrete details, such as material etc., to provide to the embodiment of the present invention are provided
Comprehensive understanding.However, those skilled in the relevant art are readily apparent that, the present invention is without said one or multiple concrete details
Realize or can also be used the realizations such as other methods, component, material.In other examples, known structure, material or operation
It is not shown or described in detail in order to avoid obscuring various aspects of the invention.
Although above-mentioned example is used to illustrate principle of the present invention in one or more application, for the technology of this field
For personnel, in the case of without departing substantially from the principle of the present invention and thought, hence it is evident that can in form, the details of usage and implementation
It is upper that various modifications may be made and does not have to make the creative labor.Therefore, the present invention is defined by the appended claims.
Claims (10)
1. a kind of fetal weight Forecasting Methodology, which is characterized in that including:
Establish the fetal weight prediction model of the physical parameter of pregnant woman and the correspondence of fetal weight;Wherein, the physics ginseng
Number includes pregnant woman's changes of weight value and pregnant woman's body fat changing value;
The first input parameter is obtained, wherein, first input parameter includes pregnant woman's Current body mass value and the current body fat value of pregnant woman;
The second input parameter is obtained, wherein, second input parameter includes pregnant woman's history weight value and pregnant woman's history body fat value;
According to the first input parameter and the second input parameter, calculate and obtain pregnant woman's changes of weight value and pregnant woman's body fat changing value;
According to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight prediction model, fetal weight is obtained
Predicted value.
2. the according to the method described in claim 1, it is characterized in that, physical parameter for establishing pregnant woman pass corresponding with fetal weight
The fetal weight prediction model of system, specifically includes:
Obtain the physical parameter of pregnant woman and corresponding practical fetal weight;
It is preserved using the physical parameter of pregnant woman with corresponding practical fetal weight as an effective sample;
Multiple effective samples are obtained, and multiple effective samples are preserved to storage device;
Multiple effective samples in storage device are trained by supervision type machine learning algorithm, it is pre- to obtain fetal weight
Survey model.
3. according to the method described in claim 1, it is characterized in that, the effective sample acquiring way further includes:
By the physical parameter of pregnant woman and the correspondence of all numbers of pregnancy, the correspondence of fetal weight and all numbers of pregnancy, to obtain
Obtain the physical parameter of pregnant woman and the correspondence of fetal weight.
4. according to the method described in claim 2, it is characterized in that, the fetal weight prediction model is expressed as with expression formula:W
=x1*(Δa)+x2*(Δb)+x3* (Δ c), wherein, W is fetal weight predicted value, and Δ a is pregnant woman's changes of weight value, and Δ b is
Pregnant woman's body fat changing value, Δ c be fetal weight standard value, x1、x2And x3Value according to supervision type machine learning algorithm to storage set
Multiple effective samples in standby determine after being trained.
5. according to the described method of any one of claim 1-4, which is characterized in that obtain the first input parameter and specifically include:
Pregnant woman is measured using body fat scale, to obtain pregnant woman's Current body mass measured value and the current bodily fat measurement of pregnant woman
Value;
Pregnant woman's metrical information is uploaded in storage device, pregnant woman's metrical information includes pregnant woman ID, pregnant woman's Current body mass is surveyed
Magnitude, the current bodily fat measurement value of pregnant woman and time of measuring;
Trend is used to pregnant woman's Current body mass measured value and the current bodily fat measurement value of the pregnant woman according to history valid data
Prediction algorithm is modified, to obtain pregnant woman's Current body mass value and the current body fat value of pregnant woman, and by pregnant woman's Current body mass value and pregnant
The current body fat value of woman as the first input parameter, wherein, the history valid data are the pregnant woman that stores in storage device
All revised pregnant woman's Current body mass measured values and the current bodily fat measurement value of the pregnant woman corresponding to ID;Pregnant woman is current
Weight value is to the revised value of pregnant woman's Current body mass measured value, and the current body fat value of pregnant woman is current bodily fat measurement value is repaiied to pregnant woman
Value after just.
6. a kind of fetal weight prediction meanss, which is characterized in that including:
Fetal weight prediction model establishes module, for establishing the fetus of the correspondence of the physical parameter of pregnant woman and fetal weight
Forecast body weight model;Wherein, the physical parameter includes pregnant woman's changes of weight value and pregnant woman's body fat changing value;
First acquisition module, for obtaining the first input parameter, wherein, first input parameter includes pregnant woman's Current body mass value
With the current body fat value of pregnant woman;
Second acquisition module, for obtaining the second input parameter, wherein, second input parameter includes pregnant woman's history weight value
With pregnant woman's history body fat value;
Computing module, for according to the first input parameter and the second input parameter, calculating and obtaining pregnant woman's changes of weight value and pregnant woman
Body fat changing value;
Prediction module, for according to pregnant woman's changes of weight value, pregnant woman's body fat changing value and fetal weight prediction model,
Obtain fetal weight predicted value.
7. device according to claim 6, which is characterized in that fetal weight prediction model is established module and specifically included:
First acquisition submodule, for obtaining the physical parameter of pregnant woman and corresponding practical fetal weight;
Effective sample acquisition submodule, for using the physical parameter of pregnant woman with corresponding practical fetal weight as an effective sample
This preservation;
Submodule is preserved, for obtaining multiple effective samples, and multiple effective samples are preserved to storage device;
Fetal weight prediction model setting up submodule has multiple in storage device for passing through supervision type machine learning algorithm
Effect sample is trained, to obtain fetal weight prediction model.
8. device according to claim 6, which is characterized in that effective sample acquisition submodule further includes:
By the physical parameter of pregnant woman and the correspondence of all numbers of pregnancy, the correspondence of fetal weight and all numbers of pregnancy, to obtain
Obtain the physical parameter of pregnant woman and the correspondence of fetal weight.
9. device according to claim 7, which is characterized in that the fetal weight prediction model is expressed as with expression formula:W
=x1*(Δa)+x2*(Δb)+x3* (Δ c), wherein, W is fetal weight predicted value, and Δ a is pregnant woman's changes of weight value, and Δ b is
Pregnant woman's body fat changing value, Δ c be fetal weight standard value, x1、x2And x3Value according to supervision type machine learning algorithm to storage set
Multiple effective samples in standby determine after being trained.
10. according to the device described in any one of claim 6-9, which is characterized in that the first acquisition module specifically includes:
Submodule is measured, pregnant woman is measured for passing through body fat scale, to obtain pregnant woman's Current body mass measured value and pregnant
The current bodily fat measurement value of woman;
Upload submodule, for pregnant woman's metrical information to be uploaded in storage device, pregnant woman's metrical information include pregnant woman ID,
Pregnant woman's Current body mass measured value, the current bodily fat measurement value of pregnant woman and time of measuring;
Correct submodule, for according to history valid data to pregnant woman's Current body mass measured value and the current body fat of the pregnant woman
Measured value is modified using trend prediction algorithm, to obtain pregnant woman's Current body mass value and the current body fat value of pregnant woman, and by pregnant woman
Current body mass value and the current body fat value of pregnant woman as the first input parameter, wherein, the history valid data be storage device in
All revised pregnant woman's Current body mass measured values and the current body fat of the pregnant woman corresponding to the pregnant woman ID of storage
Measured value;Pregnant woman's Current body mass value is to the revised value of pregnant woman's Current body mass measured value, and the current body fat value of pregnant woman is to pregnant woman
The revised value of current bodily fat measurement value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711416456.6A CN108154930A (en) | 2017-12-25 | 2017-12-25 | Fetal weight Forecasting Methodology and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711416456.6A CN108154930A (en) | 2017-12-25 | 2017-12-25 | Fetal weight Forecasting Methodology and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108154930A true CN108154930A (en) | 2018-06-12 |
Family
ID=62464456
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711416456.6A Pending CN108154930A (en) | 2017-12-25 | 2017-12-25 | Fetal weight Forecasting Methodology and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108154930A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1284649A (en) * | 1999-08-12 | 2001-02-21 | 株式会社百利达 | Body weight balance for pregnant woman |
CN1398573A (en) * | 2001-07-24 | 2003-02-26 | 株式会社百利达 | Body fat measuring system and health system for pregnant woman |
CN1572236A (en) * | 2003-05-30 | 2005-02-02 | 株式会社百利达 | Body composition management apparatus for pregnant woman |
CN105167742A (en) * | 2015-05-22 | 2015-12-23 | 上海更多网络科技有限公司 | Fetus body weight adaptive estimation method and fetus body weight adaptive estimation system |
CN106650222A (en) * | 2016-10-21 | 2017-05-10 | 大连千松科技有限公司 | Pregnancy health state management method and device based on Internet |
CN206576894U (en) * | 2016-08-11 | 2017-10-24 | 北京春闱科技有限公司 | The fetus-voice meter of function is detected with body weight |
-
2017
- 2017-12-25 CN CN201711416456.6A patent/CN108154930A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1284649A (en) * | 1999-08-12 | 2001-02-21 | 株式会社百利达 | Body weight balance for pregnant woman |
CN1398573A (en) * | 2001-07-24 | 2003-02-26 | 株式会社百利达 | Body fat measuring system and health system for pregnant woman |
CN1572236A (en) * | 2003-05-30 | 2005-02-02 | 株式会社百利达 | Body composition management apparatus for pregnant woman |
CN105167742A (en) * | 2015-05-22 | 2015-12-23 | 上海更多网络科技有限公司 | Fetus body weight adaptive estimation method and fetus body weight adaptive estimation system |
CN206576894U (en) * | 2016-08-11 | 2017-10-24 | 北京春闱科技有限公司 | The fetus-voice meter of function is detected with body weight |
CN106650222A (en) * | 2016-10-21 | 2017-05-10 | 大连千松科技有限公司 | Pregnancy health state management method and device based on Internet |
Non-Patent Citations (3)
Title |
---|
于晓妮 等: ""孕期孕妇体重增长与胎儿出生体重相关性研究"", 《临床医学》 * |
李昆 等: ""基于深度神经网络的胎儿体重预测"", 《计算机科学》 * |
黄春燕: ""孕妇BMI变化对胎儿体重及分娩结局的影响研究"", 《药物与人》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105167742B (en) | A kind of fetal weight adaptive estimation method and system | |
CN105615901A (en) | Emotion monitoring method and system | |
US11484225B2 (en) | Rehabilitation evaluation apparatus, rehabilitation evaluation method, and rehabilitation evaluation program | |
CN105808970A (en) | Online cognitive assessment system and assessment method | |
CN102314712B (en) | Pelvis modeling and pelvis parameter measurement method based on three-dimensional imaging technology | |
Roman-Liu et al. | Comparison of risk assessment procedures used in OCRA and ULRA methods | |
CN110009605A (en) | A kind of stone age prediction technique and system based on deep learning | |
Jezewski et al. | Evaluating the fetal heart rate baseline estimation algorithms by their influence on detection of clinically important patterns | |
US9949663B1 (en) | Apparatus and method for the analysis of the change of body composition and hydration status and for dynamic indirect individualized measurement of components of the human energy metabolism | |
US20230298760A1 (en) | Systems, devices, and methods for determining movement variability, illness and injury prediction and recovery readiness | |
WO2020187987A1 (en) | Population-level gaussian processes for clinical time series forecasting | |
CN112712882A (en) | Method and system for improving intensive care management level | |
Dobratulin et al. | The efficiency of deep learning algorithms for detecting anatomical reference points on radiological images of the head profile | |
CN113499046A (en) | Dynamic blood pressure real-time monitoring device, system and storage medium | |
CN108154930A (en) | Fetal weight Forecasting Methodology and device | |
CN113869090A (en) | Fall risk assessment method and device | |
JP2015111438A (en) | Biological information evaluation system and evaluation method | |
CN115553757B (en) | Method and equipment for intelligently screening effective ground reaction force in gait process | |
CN110033846B (en) | Obstetrical clinical auxiliary sequential labor device, control method and computer program | |
JP2011115393A (en) | Skin feature determination system, skin feature determination method, and skin feature determination program | |
CN116631622A (en) | AI-based pregnant woman characteristic-related fetal weight prediction method and system | |
CN113870980A (en) | Visual obstetrical image examination processing method and device | |
Røislien et al. | Functional limits of agreement: a method for assessing agreement between measurements of gait curves | |
CN115299901A (en) | Traditional Chinese medicine pulse condition map generation method based on wrist type sphygmomanometer detection data | |
CN110215211B (en) | Individual height measuring and analyzing method and system, readable storage medium and terminal |
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 |