CN107252323A - Forecasting Methodology, device and the user equipment of determining female physiological periodicity - Google Patents
Forecasting Methodology, device and the user equipment of determining female physiological periodicity Download PDFInfo
- Publication number
- CN107252323A CN107252323A CN201710413820.7A CN201710413820A CN107252323A CN 107252323 A CN107252323 A CN 107252323A CN 201710413820 A CN201710413820 A CN 201710413820A CN 107252323 A CN107252323 A CN 107252323A
- Authority
- CN
- China
- Prior art keywords
- temperature
- data
- physiological
- training data
- physiological period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0012—Ovulation-period determination
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0012—Ovulation-period determination
- A61B2010/0019—Ovulation-period determination based on measurement of temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B10/00—Other methods or instruments for diagnosis, e.g. instruments for taking a cell sample, for biopsy, for vaccination diagnosis; Sex determination; Ovulation-period determination; Throat striking implements
- A61B10/0012—Ovulation-period determination
- A61B2010/0029—Ovulation-period determination based on time measurement
Abstract
This disclosure relates to the Forecasting Methodology and device of a kind of determining female physiological periodicity, wherein, a kind of Forecasting Methodology of determining female physiological periodicity includes：Intercept the trigger action of user in predicting physiological period, generation physiological period prediction instruction；Predict that instruction triggers carry out the acquisition of temperature data according to the physiological period；Feature extraction, which is carried out, for the temperature data got obtains physiological characteristic sequence；In the physiological period forecast model built in advance, physiological period prediction is carried out using the physiological characteristic sequence as the input of the physiological period forecast model, output obtains physiological period.The Forecasting Methodology and device of a kind of determining female physiological periodicity provided using the disclosure can effectively improve the accuracy rate of physiological period prediction.
Description
Technical field
This disclosure relates to field of medical technology, more particularly to a kind of Forecasting Methodology of determining female physiological periodicity, device and user
Equipment.
Background technology
In the prior art, average value of the Forecasting Methodology of determining female physiological periodicity generally using history physiological period is used as prediction
Value, but the predicted value is easily influenceed by many factors such as mood, weather, health status, and cause the accuracy rate of prediction
It is relatively low.
Therefore, having also been proposed a kind of basal body temperature by women to predict the Forecasting Methodology of determining female physiological periodicity, through grinding
Study carefully and show, the basal body temperature and ovarian function of women is closely related, can predict physiological period by the change of basal body temperature.
However, the measurement request of basal body temperature is more strict, i.e., after long period sleep, wakes up and do not appointed
What before activity, sublingual body temperature is measured.In actually measurement, it is difficult to ensure whether the measurement of basal body temperature meets
State strict requirements.If basal body temperature has measurement error, physiological period can not be still predicted exactly.
From the foregoing, it will be observed that how to predict that determining female physiological periodicity is still urgent problem to be solved exactly.
The content of the invention
In order to solve the above-mentioned technical problem, a purpose of the disclosure is to provide a kind of prediction side of determining female physiological periodicity
Method, device and user equipment.
Wherein, the technical scheme that the disclosure is used for：
A kind of Forecasting Methodology of determining female physiological periodicity, including：Intercept the trigger action of user in predicting physiological period, generation life
Manage period forecasting instruction；Predict that instruction triggers carry out the acquisition of temperature data according to the physiological period；For the body got
Warm data carry out feature extraction and obtain physiological characteristic sequence；In the physiological period forecast model built in advance, with the physiology
Characteristic sequence carries out physiological period prediction as the input of the physiological period forecast model, and output obtains physiological period.It is a kind of
The prediction meanss of determining female physiological periodicity, including：Directive generation module, the trigger action for intercepting user in predicting physiological period,
Generate physiological period prediction instruction；Temperature data acquisition module, for predicting that instruction triggers carry out body according to the physiological period
The acquisition of warm data；Fisrt feature extraction module, physiology spy is obtained for carrying out feature extraction for the temperature data got
Levy sequence；Physiological period prediction module, in the physiological period forecast model built in advance, with the physiological characteristic sequence
Physiological period prediction is carried out as the input of the physiological period forecast model, output obtains physiological period.
Be stored with computer-readable instruction on a kind of user equipment, including processor and memory, the memory, described
The Forecasting Methodology of determining female physiological periodicity as described above is realized when computer-readable instruction is by the computing device.
A kind of computer-readable recording medium, is stored thereon with computer program, and the computer program is held by processor
The Forecasting Methodology of determining female physiological periodicity as described above is realized during row.
Compared with prior art, the disclosure has the advantages that：
Physiological characteristic sequence is obtained by carrying out feature extraction to the temperature data got, and then in the life built in advance
Manage in period forecasting model, physiological period prediction carried out using the physiological characteristic sequence as the input of physiological period forecast model,
Obtain physiological period.
That is, this method is to be based on body temperature and not basal body temperature, the degree of accuracy of measurement is higher, in addition, for body
Temperature carries out physiological period prediction, the support with mathematical algorithm by the physiological period forecast model built in advance, it is to avoid simple
Ground is effectively improved the accuracy rate of prediction using the average value of history physiological period as predicted value.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the implementation for meeting the disclosure
Example, and be used in specification to explain the principle of the disclosure together.
Fig. 1 is a kind of hardware block diagram of user equipment according to an exemplary embodiment；
Fig. 2 is a kind of flow chart of the Forecasting Methodology of determining female physiological periodicity according to an exemplary embodiment；
Fig. 3 is that Fig. 2 corresponds to flow chart of the step 310 in one embodiment in embodiment；
Fig. 4 is the flow chart of the Forecasting Methodology of another determining female physiological periodicity according to an exemplary embodiment；
Fig. 5 is that Fig. 4 corresponds to flow chart of the step 450 in one embodiment in embodiment；
Fig. 6 is the principle schematic of default mathematical modeling in Fig. 5 correspondence embodiments；
Fig. 7 is that a kind of Forecasting Methodology of determining female physiological periodicity implements schematic diagram in an application scenarios；
Fig. 8 is a kind of block diagram of the prediction meanss of determining female physiological periodicity according to an exemplary embodiment；
Fig. 9 is that Fig. 8 corresponds to block diagram of the temperature data acquisition module 710 in one embodiment in embodiment；
Figure 10 is the block diagram of the prediction meanss of another determining female physiological periodicity according to an exemplary embodiment；
Figure 11 is that Figure 10 corresponds to block diagram of the model construction module 850 in one embodiment in embodiment.
Pass through above-mentioned accompanying drawing, it has been shown that the clear and definite embodiment of the disclosure, will hereinafter be described in more detail, these accompanying drawings
It is not intended to limit the scope that the disclosure is conceived by any mode with word description, but is by reference to specific embodiment
Those skilled in the art illustrate the concept of the disclosure.
Embodiment
Here explanation will be performed to exemplary embodiment in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the disclosure.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the disclosure.
As it was previously stated, in the prior art the Forecasting Methodology of determining female physiological periodicity still suffer from prediction accuracy rate it is not high lack
Fall into.
Based on this, disclosure spy proposes a kind of prediction side of the determining female physiological periodicity for the accuracy rate for effectively improving prediction
Method.This method is realized by computer program, corresponding, corresponding to the prediction meanss of constructed determining female physiological periodicity
Computer-readable instruction is stored in the memory of user equipment, in order to carry out the prediction of determining female physiological periodicity.
Fig. 1 is a kind of hardware block diagram of user equipment 100 according to an exemplary embodiment.Need explanation
It is that the user equipment 100 is an example for adapting to the disclosure, it is impossible to be considered to provide use scope of this disclosure
Any limitation.The user equipment 100 can not be construed to need to rely on or must be exemplary with what is shown in Fig. 1
One or more component in user equipment 100.
The hardware configuration of the user equipment 100 can produce larger difference because of the difference of configuration or performance, such as Fig. 1 institutes
Show, user equipment 100 includes：Power supply 110, at least interface 130, a storage medium 150 and an at least central processing unit
(CPU, Central Processing Units) 170.
Wherein, power supply 110 is used to provide operating voltage for each hardware device on user equipment 100.
Interface 130 includes at least one wired or wireless network interface 131, at least a string and translation interface 133, at least one defeated
Enter output interface 135 and at least usb 1 37 etc., be used for and external device communication.
The carrier that storage medium 150 is stored as resource, can be random storage medium, disk or CD etc., thereon
The resource stored includes operating system 151, application program 153 and data 155 etc., storage mode can be of short duration storage or
Permanently store.Wherein, operating system 151 is used to managing and controlling each hardware device and the application program on user equipment 100
153, to realize calculating and processing of the central processing unit 170 to mass data 155, it can be Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..Application program 153 is to be based on completing at least one on operating system 151
The computer program of item particular job, it can include an at least module (not shown in figure 1), and each module can be wrapped respectively
Contain the sequence of operations instruction to user equipment 100.Data 155 can be stored in photo in disk, picture etc..
Central processing unit 170 can include the processor more than one or more, and be set to storage be situated between by bus
Matter 150 communicates, for computing and the mass data 155 in processing storage medium 150.
As described in detail above, storage will be read by central processing unit 170 by being applicable the user equipment 100 of the disclosure
The form of the sequence of operations instruction stored in medium 150 realizes the Forecasting Methodology of determining female physiological periodicity.
In addition, also can equally realize the disclosure by hardware circuit or hardware circuit combination software instruction, therefore, realize
The disclosure is not limited to any specific hardware circuit, software and both combinations.
Referring to Fig. 2, in one exemplary embodiment, a kind of Forecasting Methodology of determining female physiological periodicity is applied to shown in Fig. 1
User equipment 100, the Forecasting Methodology of this kind of determining female physiological periodicity can perform by user equipment 100, can include following step
Suddenly：
Step 310, the trigger action of user in predicting physiological period, generation physiological period prediction instruction are intercepted.
For user equipment, the prediction entrance of a determining female physiological periodicity will be provided the user, allow the user to lead to
The trigger action carried out in the prediction entrance is crossed, the prediction of determining female physiological periodicity is carried out.
For example, prediction entrance can be the virtual key on the human-computer interaction interface that user equipment is provided, when
During the prediction of user's determining female physiological periodicity to be carried out, the virtual key is will click on, the clicking operation is user in predicting physiology week
The trigger action of phase.
User equipment is listening to user after the trigger action that prediction entrance is carried out, i.e., by responding the trigger action
Physiology period forecasting instruction is generated, and then predicts that instruction proceeds by the prediction of determining female physiological periodicity according to the physiological period.
Step 330, predict that instruction triggers carry out the acquisition of temperature data according to physiological period.
In the present embodiment, temperature data characterizes the temperature of female body, i.e. women body temperature.
Further, women body temperature is according to the different slightly differences of measuring point.For example, the normal range (NR) of axillary temperature is
36.1 DEG C~37 DEG C, oral temperature is then 36.3 DEG C~37.2 DEG C.
Further, women body temperature can slightly change in the presence of internal and external factor in normal range (NR).For example,
Afternoon is of a relatively high compared with morning women body temperature, or, can also there be women body temperature after having meal or moving mildly raises, and or
Person, women is in the onset of ovulation or gestational period body temperature also a little higher than normal range (NR).
Further, temperature data is pre-stored in user equipment, thus, just can be obtained in user equipment
To the temperature data prestored.For example, temperature data can be stored in a user device by the form of user log files.
Step 350, carry out feature extraction for the temperature data got and obtain physiological characteristic sequence.
In order to carry out the prediction of determining female physiological periodicity, it is necessary to know the feature distribution of physiological period.
As it was previously stated, women is in the onset of ovulation or a little higher than normal range (NR) of gestational period body temperature.Thus, it is raw in the present embodiment
Knowing for the feature distribution in reason cycle will be realized by the feature extraction of temperature data.
Specifically, characteristic extraction procedure includes the low temperature high temperature in temperature data is averaging processing, to temperature data
Carry out difference processing, temperature data is normalized etc..
By the feature extraction carried out to temperature data, the physiology for just having obtained the feature distribution for reflecting physiological period is special
Sequence is levied, and then is conducive to carrying out the prediction of follow-up determining female physiological periodicity according to physiological characteristic sequence.
Step 370, in the physiological period forecast model built in advance, predicted using physiological characteristic sequence as physiological period
The input of model carries out physiological period prediction, and output obtains physiological period.
Physiological period forecast model is to be built to obtain in advance according to the feature distribution of physiological period.That is, with life
The feature distribution in reason cycle is just exportable to obtain physiological period as input.
After having obtained reflecting the physiological characteristic sequence of feature distribution of physiological period, just it can be predicted by physiological period
Model prediction obtains physiological period.
Further, the time relationship of 142 days is differed with ovulation period with reference to physiological period, will also be calculated by physiological period
Ovulation period is obtained, to meet the forecast demand that user is different.
By process as described above, physiological period prediction is carried out using physiological period forecast model so that female pathology
The prediction in cycle possesses the support of mathematical algorithm, so as to be effectively improved the accuracy rate of prediction.
Referring to Fig. 3, in one exemplary embodiment, step 310 may comprise steps of：
Step 311, temperature curve is drawn according to the temperature recording prestored.
The body temperature of user's measurement will be recorded by the form of user log files, that is to say, that user log files
In at least have recorded time of measuring corresponding to the body temperature and the body temperature of measurement.
Specifically, the temperature recording operation that user device responsive user is carried out for the body temperature triggering of measurement, generates body temperature
Record, and the temperature recording of generation is stored into user log files.
Thus, temperature recording can correspondingly be got by reading user log files.Temperature recording includes measurement
Body temperature and the body temperature corresponding to time of measuring.
After temperature recording is got, the drafting of temperature curve just can be carried out according to temperature recording.
Specifically, using body temperature as ordinate, using the time as abscissa, then corresponding to the body temperature measured and the body temperature
Time of measuring be to constitute a coordinate points, by straight line connection be that drafting obtains temperature curve by some coordinate points.
Step 313, smoothing denoising processing is carried out to temperature curve.
It is appreciated that because the time of measuring of measurement of bldy temperature is that compartment of terrain is discrete, being obtained by straight line connection coordinate point
To temperature curve there is essentially and lack, i.e., do not carry out the time body temperature corresponding in temperature curve of measurement of bldy temperature without
Method ensures accuracy.
Therefore, in the present embodiment, smoothing denoising processing is carried out to temperature curve by smoothing denoising algorithm, filtering body temperature is bent
Exceptional value and missing values in line, eliminate the localised waving of temperature curve, are effectively guaranteed what is measured in temperature curve with this
The accuracy and integrality of body temperature, and then be conducive to the follow-up accuracy for improving prediction.
Wherein, smoothing denoising algorithm can be mean filter, medium filtering, the denoising based on Wavelet transformation, total variation
(TV, Total Variation) denoising etc. method, is not limited herein.
Step 315, in the temperature curve that smoothing denoising processing is obtained, the body temperature for obtaining meeting default extraction conditions is extracted
Data.
Wherein, preset extraction conditions and include extracting on a time period, extract by temperature range etc..
Extracted after smoothing denoising processing is completed, in temperature curve that just can be after handling and obtain temperature data.
In the presence of above-described embodiment, the continuity of the time of measurement of bldy temperature is realized, that is, has been filtered in temperature curve
Missing values, it is ensured that the integrality of temperature curve, meanwhile, the exceptional value filtered in temperature curve is handled by smoothing denoising,
Eliminate the localised waving of temperature curve, it is ensured that the accuracy of temperature curve, the accurate of follow-up raising prediction is conducive to this
Property.
In one exemplary embodiment, before step 330, method as described above can also comprise the following steps：
Sample classification is carried out to temperature data according to default class condition, the corresponding sample type mark of temperature data is determined
Know.
Wherein, presetting class condition includes at least one of temperature curve type, measuring section.
What it is firstly the need of explanation is temperature curve type, is obtained because temperature data is extracted in temperature curve, should
Temperature curve type corresponds to temperature data, and the temperature curve type reflects point of the body temperature measured in temperature curve
Cloth.
Specifically, temperature curve type includes the distribution of normal two-phase, abnormal two-phase distribution and single-phase distribution.
Further, the distribution of abnormal two-phase include profile amplitude rise it is slow, decline slow, heave amplitude less than 0.3 etc.
Deng.
Single-phase distribution includes profile amplitude is relatively low, higher, curve waveform is serrated etc..
Secondly it should be noted that measuring section, the time of measuring that the measuring section is to user measures body temperature is related
's.
As it was previously stated, women body temperature is in the presence of internal and external factor, can slightly it change in normal range (NR).For example, under
Noon is of a relatively high compared with morning women body temperature.
Therefore, measuring section can be divided for morning, afternoon, evening, ensured with this in same time of measuring
Body temperature fluctuation in section is smaller.
That is, measuring section includes morning hours section, the period in the afternoon the period in the evening.
It should be appreciated that if the distribution of body temperature is different, the feature of the physiological period of physiological period forecast model reflection is divided
Cloth is difference.
Therefore, sample classification can be carried out according to above-mentioned default class condition, with this corresponding sample of determination temperature data
Type identification, and then the physiological period forecast model for being conducive to being subsequently used for physiological period prediction is relative with sample type mark
Answer, the accuracy rate of prediction is improved with this.
Correspondingly, before step 370, method as described above can also comprise the following steps：
Associative search is identified to corresponding physiological period forecast model according to sample type.
By the cooperation of above-described embodiment, sample classification is carried out to temperature data so that different sample type marks can
Associative search is to different physiological period forecast models, in order to subsequently carry out physiology according to different physiological period forecast models
Period forecasting, so as to further be conducive to improving the accuracy rate predicted.
Further, in one exemplary embodiment, sample classification is carried out to temperature data according to default class condition, really
Determine before the corresponding sample type identification of steps of temperature data, method as described above can also comprise the following steps：
Data cleansing is carried out to temperature data according to the data format of default feature extraction algorithm, obtains meeting data format
Temperature data.
Default feature extraction algorithm is for carrying out feature extraction to temperature data, according to default feature extraction algorithm
Data format carries out data cleansing to temperature data, and the data format for causing temperature data is met into default feature extraction algorithm
Data format, and then be conducive to carrying out feature to the temperature data for meeting data format subsequently through default feature extraction algorithm
Extract.
Correspondingly, step 330 may comprise steps of：
Call default feature extraction algorithm to carry out feature extraction to the temperature data for meeting data format, obtain physiological characteristic
Sequence.
In one exemplary embodiment, after step 330, method as described above can also comprise the following steps：
Influence factor feature is added to physiological characteristic sequence.
As it was previously stated, determining female physiological periodicity prediction easily by mood, weather, many factors of health status shadow
Ring, and cause the accuracy rate of prediction relatively low.
Therefore, after physiological characteristic sequence is obtained, influence factor feature being added into physiological characteristic sequence, ensured with this
Various dimensions prediction to determining female physiological periodicity, is conducive to improving the accuracy rate predicted.
Wherein, influence factor feature is used to characterize can produce the influence factor of influence to physiological period.The influence factor bag
Female age, weather, mood, health status etc. are included, correspondingly, the influence factor feature includes female age feature, region
Feature, history physiological period feature.
Further, regional feature reflects the weather in geographical position residing for women etc..
History physiological period feature includes history physiological period, reflects mood, health status of women etc..
The acquisition process of influence factor feature is specifically included：Collection can produce the influence factor of influence to physiological period, and
Feature Conversion is carried out to those influence factors and obtains influence factor feature.
Under the cooperation of above-described embodiment, the various dimensions prediction based on influence factor feature is realized, with this further
Improve the accuracy rate of prediction.
Referring to Fig. 4, in one exemplary embodiment, method as described above can also comprise the following steps：
Step 410, training data is obtained.
Before the prediction of determining female physiological periodicity is carried out, in order to build physiological period forecast model, it is necessary to training data
It is used as the training basis of the physiological period forecast model.Accurate life can be just accessed by obtaining substantial amounts of training data
Period forecasting model is managed, and then more accurately carries out the prediction of determining female physiological periodicity.
In the present embodiment, training data is obtained by being locally extracted in local user log files.
As it was previously stated, storing temperature recording in user log files, temperature recording includes the body temperature of measurement and is somebody's turn to do
Time of measuring corresponding to body temperature.
Thus, body temperature extraction is carried out for the temperature recording included in user log files, just can be obtained according to extracting
Body temperature generates training data.
Certainly, in other application scene, user equipment can also be by interacting, by storage server with storage server
The middle training data obtained in other users equipment.
Step 430, feature extraction is carried out for the training data acquired, obtains the corresponding feature sequence of training data
Row.
As it was previously stated, physiological period forecast model is to build to obtain in advance by the feature distribution to physiological period, therefore
And, before the structure of physiological period forecast model is carried out, it is necessary first to carry out feature extraction for training data.
Further, the training data acquired is magnanimity, correspondingly, and characteristic sequence is corresponding with training data
, that is, carry out after feature extraction, obtain the characteristic sequence corresponding to each training data.
Step 450, model foundation and training are carried out according to the corresponding characteristic sequence of training data, obtains physiological period prediction
Model.
After the corresponding characteristic sequence of each training data is got, that is, the input that model is set up and trained is obtained.
That is, carrying out model foundation and training using the corresponding characteristic sequence of training data as input, it can access and reflect
The physiological period forecast model of the feature distribution of physiological period.
Under the cooperation of above-described embodiment, the advance structure of physiological period forecast model is realized so that follow-up women life
The prediction in reason cycle possesses the support of mathematical algorithm, so as to be conducive to improving the accuracy rate predicted.
In addition, it is ensured that the structure of physiological period forecast model is to be based on a large amount of training datas, i.e., real temperature data,
And then constitute the premise of physiological period Accurate Prediction.
In one exemplary embodiment, after step 410, method as described above can also comprise the following steps：
Sample classification is carried out to training data according to default class condition, the corresponding sample type mark of training data is determined
Know.
As it was previously stated, default class condition includes at least one of temperature curve type, measuring section.
Wherein, temperature curve type includes the distribution of normal two-phase, abnormal two-phase distribution and single-phase distribution.
Further, the distribution of abnormal two-phase include profile amplitude rise it is slow, decline slow, heave amplitude less than 0.3 etc.
Deng.
Single-phase distribution includes profile amplitude is relatively low, higher, curve waveform is serrated etc..
Measuring section includes morning hours section, the period in the afternoon the period in the evening.
Correspondingly, the sample type of training data also include the distribution of normal two-phase, the distribution of abnormal two-phase and single-phase distribution with
The periods in the morning such as and the period in the afternoon the period in the evening.,.
Further, after step 450, method as described above can also comprise the following steps：
Sample type mark is associated storage with physiological period forecast model.
For example, temperature curve type is distributed for normal two-phase, then the sample type of training data is normal two-phase
Distribution, correspondingly, the feature distribution for the physiological period that physiological period forecast model is reflected is related to the distribution of normal two-phase
's.
By the cooperation of embodiment as described above, when sample type identifies difference, carry out used in physiological period prediction
Physiological period forecast model also will be otherwise varied, so as to effectively further improve the accuracy rate of prediction.
Further, in one exemplary embodiment, sample classification is carried out to training data according to default class condition, really
Determine before the corresponding sample type identification of steps of training data, method as described above can also comprise the following steps：
Data cleansing is carried out to training data according to the data format of default feature extraction algorithm, obtains meeting data format
Training data.
Default feature extraction algorithm is for carrying out feature extraction to training data, according to default feature extraction algorithm
Data format carries out data cleansing to training data, and the data format for causing training data is met into default feature extraction algorithm
Data format, and then be conducive to carrying out feature to the training data for meeting data format subsequently through default feature extraction algorithm
Extract.
Correspondingly, step 430 may comprise steps of：
Call default feature extraction algorithm to carry out feature extraction to the training data for meeting data format, obtain training data
Corresponding characteristic sequence.
Referring to Fig. 5, in one exemplary embodiment, step 450 may comprise steps of：
Step 451, the modeling of training data corresponding characteristic sequence is obtained treating training pattern using default mathematical modeling.
In the present embodiment, modeling is to reflect that training data is corresponding by the mathematic(al) structure of default mathematics model description
Characteristic sequence.
Default mathematical modeling is not limited herein, using default mathematical modeling as HMM (Hidden Markov Model,
Hidden Markov model) illustration of-GMM (Gaussian Mixture Model, mixed Gauss model) model.
Wherein, HMM model uses 3 state bands from topological structure of the ring without leap, the i.e. corresponding characteristic sequence of training data
State description is carried out by HMM model.As shown in fig. 6, the corresponding characteristic sequence of training data is divided into 3 states, wherein,
Each state Si, i=1,2,3 can only jump to its own and adjacent NextState Si+1, aijRepresent by state SiRedirect
To state SjTransition probability.
Further, for each state, it is modeled using GMM model, obtains that the spy of physiological period can be reflected
That levies distribution treats training pattern.
In other words, the corresponding relation between state and characteristic sequence is established, in order to make subsequently through training
Obtain set up corresponding relation to be optimal, that is, obtain physiological period forecast model.
Step 453, the parameter for treating training pattern carries out random initializtion, and using EM algorithm to random initial
Change obtained parameter and be iterated optimization.
It is appreciated that causing the corresponding relation between state and characteristic sequence to be optimal by training, that is, cause feature
Sequence belongs to the maximum probability of some corresponding states.
That is, in order to know that characteristic sequence belongs to the maximum probability of some corresponding states, training pattern will be treated
Parameter is trained.
Specifically, it is right by EM algorithm (Expectation Maximization Algorithm, EM algorithm)
Treat that the parameter of training pattern is iterated optimization, with the determination value for the parameter for obtaining treating training pattern, the determination value is to be characterized
Sequence belongs to the maximum probability of some corresponding states.
Wherein, the starting stage optimized in parameter iteration, the parameter for treating training pattern carries out random initializtion, should
The parameter that random initializtion is obtained is used as initial training parameter.
Further, the iterative optimization procedure each time of EM algorithm includes following two steps：
E steps, the probability distribution for the parameter for treating training pattern is calculated based on current training parameter；
M steps, corresponding parameter when the probability distribution of the parameter of training pattern expects maximum, the ginseng can be made by calculating
Number is the parameter after optimizing.
Parameter after optimization can not make to treat that training pattern restrains, then be trained parameter more with the parameter after optimization
Newly, the process of iteration optimization is continued.
Parameter after optimization makes to treat that training pattern restrains, then redirects into step 455.
Step 455, parameter after optimization makes to treat that training pattern restrains, then judges convergent to treat training pattern as physiology week
Phase forecast model.
After training obtains physiological period forecast model, it is possible to reflect women by the physiological period forecast model
The feature distribution of physiological period corresponding to body temperature, just can be predicted by women body temperature with this and obtains corresponding physiological period.
In addition, the physiological period forecast model that training is obtained is corresponding with the sample type of training data so that not same
The training data of this type can model the physiological period forecast models different with training respectively, be effectively guaranteed prediction
Precision.
Fig. 7 is that a kind of Forecasting Methodology of determining female physiological periodicity implements schematic diagram in an application scenarios, in conjunction with Fig. 1
The Forecasting Methodology stream of shown user equipment and application scenarios shown in Fig. 7 to determining female physiological periodicity in each embodiment of the disclosure
Journey is been described by.
By performing step 601 to step 605, the structure of physiological period forecast model is carried out.
By performing step 606 to step 610, the extraction of physiological characteristic sequence is carried out to the temperature data of input.
And by performing step 611, using physiological characteristic sequence as mode input, carried out by physiological period forecast model
Physiological period is predicted, obtains physiological period 612 and the onset of ovulation 613.
In each embodiment of the disclosure, the structure of physiological period forecast model is carried out using machine learning algorithm so that female
The prediction of property physiological period possesses the support of mathematical algorithm, it is to avoid simply the average value using history physiological period is used as prediction
Value, the accuracy rate of prediction is effectively improved with this.
Following is disclosure device embodiment, can be used for the prediction side for performing the determining female physiological periodicity involved by the disclosure
Method.For the details not disclosed in disclosure device embodiment, the prediction of the determining female physiological periodicity involved by the disclosure refer to
Embodiment of the method.
Referring to Fig. 8, in one exemplary embodiment, a kind of prediction meanss 700 of determining female physiological periodicity include but not limited
In：Directive generation module 710, temperature data acquisition module 730, fisrt feature extraction module 750 and physiological period prediction module
770。
Wherein, directive generation module 710 is used for the trigger action for intercepting user in predicting physiological period, and generation physiological period is pre-
Survey instruction.
Temperature data acquisition module 730 is used to predict that instruction triggers carry out the acquisition of temperature data according to physiological period.
Fisrt feature extraction module 750 is used to obtain physiological characteristic sequence for the temperature data progress feature extraction got
Row.
Physiological period prediction module 770 is used in the physiological period forecast model built in advance, with physiological characteristic sequence
Physiological period prediction is carried out as the input of physiological period forecast model, output obtains physiological period.
Referring to Fig. 9, in one exemplary embodiment, temperature data acquisition module 710 includes but is not limited to：Temperature curve
Drawing unit 711, temperature curve processing unit 713 and temperature data extraction unit 715.
Wherein, temperature curve drawing unit 711 is used to draw temperature curve according to the temperature recording prestored.
Temperature curve processing unit 713 is used to carry out smoothing denoising processing to temperature curve.
Temperature data extraction unit 715, which is used to be handled in obtained temperature curve by smoothing denoising, extracts temperature data.
In one exemplary embodiment, device as described above also includes but is not limited to：Temperature recording generation module and body
Warm record storage module.
Wherein, temperature recording generation module is used to respond the temperature recording behaviour that user is carried out for the body temperature triggering of measurement
Make, generate temperature recording.Time of measuring corresponding to body temperature of the temperature recording comprising measurement and the body temperature.
Temperature recording memory module is used to store the temperature recording of generation to user log files.
In one exemplary embodiment, device as described above also includes but is not limited to：First sample sort module.
Wherein, first sample sort module is used to carry out sample classification to temperature data according to default class condition, it is determined that
The corresponding sample type mark of temperature data.
Correspondingly, device as described above also includes but is not limited to：Associative search module.
Wherein, associative search module is used to identify associative search to corresponding physiological period prediction mould according to sample type
Type.
In one exemplary embodiment, device 700 as described above also includes but is not limited to：Data cleansing module.
Wherein, data cleansing module is used to carry out data to temperature data according to the data format of default feature extraction algorithm
Cleaning, obtains meeting the temperature data of data format.
Correspondingly, fisrt feature extraction module 730 includes but is not limited to：Fisrt feature extraction unit.
Wherein, fisrt feature extraction unit is used for the temperature data for calling default feature extraction algorithm to meeting data format
Feature extraction is carried out, physiological characteristic sequence is obtained.
In one exemplary embodiment, device 700 as described above also includes but is not limited to：Feature conversion module and influence
Factor feature add module.
Wherein, feature conversion module is used to gather influence factor, and carries out feature conversion to influence factor.
Influence factor feature add module is used to the influence factor feature that feature conversion is obtained being added to physiological characteristic sequence
Row.Influence factor feature is used to characterize can produce the influence factor of influence to physiological period.
Referring to Fig. 10, in one exemplary embodiment, device 700 as described above also includes but is not limited to：Train number
According to acquisition module 810, second feature extraction module 830 and model construction module 850.
Wherein, training data acquisition module 810 is used to obtain training data.
Second feature extraction module 830 is used to carry out feature extraction for the training data acquired, obtains training number
According to corresponding characteristic sequence.
Model construction module 850 is used to carry out model foundation and training according to the corresponding characteristic sequence of training data, obtains
Physiological period forecast model.
In one exemplary embodiment, training data acquisition module includes but is not limited to：Journal file read module.
Wherein, journal file read module is used to carry for the temperature recording progress body temperature included in user log files
Take, training data is generated according to the body temperature that extraction is obtained.
In one exemplary embodiment, device 700 as described above also includes but is not limited to：Second sample classification module.
Wherein, the second sample classification module is used to carry out sample classification to training data according to default class condition, it is determined that
The corresponding sample type mark of training data.
Correspondingly, device as described above also includes but is not limited to：Associated storage module.
Wherein, associated storage module is used to sample type mark being associated storage with physiological period forecast model.
In one exemplary embodiment, device as described above also includes but is not limited to：Second data cleansing module.
Wherein, the second data cleansing module is used to carry out training data according to the data format of default feature extraction algorithm
Data cleansing, obtains meeting the training data of data format.
Correspondingly, second feature extraction module includes but is not limited to：Second feature extraction unit.
Wherein, second feature extraction unit is used for the training data for calling default feature extraction algorithm to meeting data format
Feature extraction is carried out, the corresponding characteristic sequence of training data is obtained.
Figure 11 is referred to, in one exemplary embodiment, model construction module 850 includes but is not limited to：Modeling unit
851st, training unit 853 and model generation unit 855.
Wherein, modeling unit 851 is used to obtain the modeling of training data corresponding characteristic sequence using default mathematical modeling
Treat training pattern.
The parameter that training unit 853 is used to treat training pattern carries out random initializtion, and utilizes EM algorithm pair
The parameter that random initializtion is obtained is iterated optimization.
The parameter that model generation unit 855 is used for after optimization makes to treat training pattern convergence, then judges convergent to wait to train
Model is physiology period forecasting model.
It should be noted that the prediction meanss for the determining female physiological periodicity that above-described embodiment is provided are carrying out female pathology week
During the prediction processing of phase, only with the division progress of above-mentioned each functional module for example, in practical application, can as needed and
Above-mentioned functions are distributed and completed by different functional modules, i.e., the internal structure of the prediction meanss of determining female physiological periodicity will be divided into
Different functional module, to complete all or part of function described above.
In addition, the prediction meanss and the Forecasting Methodology of determining female physiological periodicity of the determining female physiological periodicity that above-described embodiment is provided
Embodiment belong to same design, wherein modules perform the concrete mode of operation and carried out in embodiment of the method in detail
Thin description, here is omitted.
In one exemplary embodiment, a kind of user equipment, including processor and memory.
Wherein, be stored with computer-readable instruction on memory, and the computer-readable instruction is realized when being executed by processor
As above the Forecasting Methodology of the determining female physiological periodicity in each embodiment.
In one exemplary embodiment, a kind of computer-readable recording medium, is stored thereon with computer program, the calculating
The Forecasting Methodology of the determining female physiological periodicity in each embodiment as above is realized when machine program is executed by processor.
The preferable examples embodiment of the above, the only disclosure, the embodiment for being not intended to limit the disclosure, this
Field those of ordinary skill can very easily carry out corresponding flexible or repair according to the central scope and spirit of the disclosure
Change, therefore the protection domain of the disclosure should be defined by the protection domain required by claims.
Claims (27)
1. a kind of Forecasting Methodology of determining female physiological periodicity, it is characterised in that including：
Intercept the trigger action of user in predicting physiological period, generation physiological period prediction instruction；
Predict that instruction triggers carry out the acquisition of temperature data according to the physiological period；
Feature extraction, which is carried out, for the temperature data got obtains physiological characteristic sequence；
In the physiological period forecast model built in advance, the physiological period forecast model is used as using the physiological characteristic sequence
Input carry out physiological period prediction, output obtain physiological period.
2. the method as described in claim 1, it is characterised in that the acquisition temperature data, including：
Temperature curve is drawn according to the temperature recording prestored；
Smoothing denoising processing is carried out to the temperature curve；
In the temperature curve that smoothing denoising processing is obtained, the temperature data for obtaining meeting default extraction conditions is extracted.
3. method as claimed in claim 2, it is characterised in that the temperature recording that the basis prestores draw temperature curve it
Before, methods described also includes：
The temperature recording operation that user is carried out for the body temperature triggering of measurement is responded, temperature recording, the temperature recording bag is generated
Containing the time of measuring corresponding to the body temperature of measurement and the body temperature；
The temperature recording of generation is stored to user log files.
4. the method as described in claim 1, it is characterised in that the temperature data progress feature extraction for getting is obtained
To before physiological characteristic sequence, methods described also includes：
Sample classification is carried out to the temperature data according to default class condition, the corresponding sample type of the temperature data is determined
Mark；
Correspondingly, it is described in the physiological period forecast model built in advance, the physiology is used as using the physiological characteristic sequence
The input of period forecasting model carries out physiological period prediction, and output is obtained before physiological period, and methods described also includes：
Associative search is identified to corresponding physiological period forecast model according to the sample type.
5. method as claimed in claim 4, it is characterised in that the default class condition includes temperature curve type, measurement
At least one of period.
6. method as claimed in claim 4, it is characterised in that described to be carried out according to default class condition to the temperature data
Sample classification, is determined before the corresponding sample type mark of the temperature data, methods described also includes：
Data cleansing is carried out to the temperature data according to the data format of default feature extraction algorithm, obtains meeting the data
The temperature data of form；
Correspondingly, the temperature data progress feature extraction for getting obtains physiological characteristic sequence, including：
Call the default feature extraction algorithm to carry out feature extraction to the temperature data for meeting the data format, obtain described
Physiological characteristic sequence.
7. the method as described in claim 1, it is characterised in that the temperature data progress feature extraction for getting is obtained
To after physiological characteristic sequence, methods described also includes：
Influence factor is gathered, and feature conversion is carried out to the influence factor；
Feature is converted to obtained influence factor feature and is added to the physiological characteristic sequence, the influence factor feature is used for table
The influence factor of influence can be produced to the physiological period by levying.
8. method as claimed in claim 7, it is characterised in that the influence factor feature includes female age feature, region
At least one of feature, history physiological period feature.
9. the method as described in any one of claim 1 to 8, it is characterised in that methods described also includes：
Obtain training data；
Feature extraction is carried out for the training data acquired, the corresponding characteristic sequence of the training data is obtained；
Model foundation and training are carried out according to the corresponding characteristic sequence of the training data, the physiological period prediction mould is obtained
Type.
10. method as claimed in claim 9, it is characterised in that the acquisition training data, including：
Body temperature extraction is carried out for the temperature recording included in user log files, the body temperature generation training number obtained according to extraction
According to.
11. method as claimed in claim 9, it is characterised in that the training data progress feature for acquiring is carried
Take, obtain before the corresponding characteristic sequence of the training data, methods described also includes：
Sample classification is carried out to the training data according to default class condition, the corresponding sample type of the training data is determined
Mark；
Correspondingly, it is described that model foundation and training are carried out according to the corresponding characteristic sequence of the training data, obtain the physiology
After period forecasting model, methods described also includes：
Sample type mark is associated storage with physiological period forecast model.
12. method as claimed in claim 11, it is characterised in that the default class condition includes temperature curve type, surveyed
Measure at least one of period.
13. method as claimed in claim 11, it is characterised in that the basis is preset class condition and entered to the training data
Row sample classification, is determined before the corresponding sample type mark of the training data, methods described also includes：
Data cleansing is carried out to the training data according to the data format of default feature extraction algorithm, obtains meeting the data
The training data of form；
Correspondingly, the training data for acquiring carries out feature extraction, obtains the corresponding feature of the training data
Sequence, including：
Call the default feature extraction algorithm to carry out feature extraction to the training data for meeting the data format, obtain described
The corresponding characteristic sequence of training data.
14. method as claimed in claim 9, it is characterised in that described to be entered according to the corresponding characteristic sequence of the training data
Row model is set up and trained, and obtains the physiological period forecast model, including：
The modeling of the training data corresponding characteristic sequence is obtained treating training pattern using default mathematical modeling；
To the parameter progress random initializtion for treating training pattern, and random initializtion is obtained using EM algorithm
Parameter is iterated optimization；
Parameter after optimization make it is described treat that training pattern restrains, then judge convergent to treat that training pattern is pre- as the physiological period
Survey model.
15. a kind of prediction meanss of determining female physiological periodicity, it is characterised in that including：
Directive generation module, the trigger action for intercepting user in predicting physiological period, generation physiological period prediction instruction；
Temperature data acquisition module, for predicting that instruction triggers carry out the acquisition of temperature data according to the physiological period；
Fisrt feature extraction module, physiological characteristic sequence is obtained for carrying out feature extraction for the temperature data got；
Physiological period prediction module, in the physiological period forecast model built in advance, being made with the physiological characteristic sequence
Physiological period prediction is carried out for the input of the physiological period forecast model, output obtains physiological period.
16. device as claimed in claim 15, it is characterised in that the temperature data acquisition module includes：
Temperature curve drawing unit, for drawing temperature curve according to the temperature recording prestored；
Temperature curve processing unit, for carrying out smoothing denoising processing to the temperature curve；
Temperature data extraction unit, in the temperature curve that smoothing denoising processing is obtained, extraction to obtain meeting default extraction
The temperature data of condition.
17. device as claimed in claim 16, it is characterised in that described device also includes：
Temperature recording generation module, for responding the temperature recording operation that user is carried out for the body temperature triggering of measurement, generates body
Temperature record, the time of measuring corresponding to body temperature of the temperature recording comprising measurement and the body temperature；
Temperature recording memory module, for the temperature recording of generation to be stored to user log files.
18. device as claimed in claim 15, it is characterised in that described device also includes：
First sample sort module, for carrying out sample classification to the temperature data according to default class condition, it is determined that described
The corresponding sample type mark of temperature data；
Correspondingly, described device also includes：
Associative search module, for identifying associative search to corresponding physiological period forecast model according to the sample type.
19. device as claimed in claim 18, it is characterised in that described device also includes：
First data cleansing module, data are carried out for the data format according to default feature extraction algorithm to the temperature data
Cleaning, obtains meeting the temperature data of the data format；
Correspondingly, the fisrt feature extraction module includes：
Fisrt feature extraction unit, for calling the default feature extraction algorithm to meeting the temperature data of the data format
Feature extraction is carried out, the physiological characteristic sequence is obtained.
20. device as claimed in claim 15, it is characterised in that described device also includes：
Feature conversion module, feature conversion is carried out for gathering influence factor, and to the influence factor；
Influence factor feature add module, the physiological characteristic sequence is added to for feature to be converted to obtained influence factor feature
Row, the influence factor feature is used to characterize can produce the influence factor of influence to the physiological period.
21. the device as described in any one of claim 15 to 20, it is characterised in that described device also includes：
Training data acquisition module, for obtaining training data；
Second feature extraction module, for carrying out feature extraction for the training data acquired, obtains the training data
Corresponding characteristic sequence；
Model construction module, for carrying out model foundation and training according to the corresponding characteristic sequence of the training data, obtains institute
State physiological period forecast model.
22. method as claimed in claim 21, it is characterised in that the training data acquisition module includes：
Journal file read module, for carrying out body temperature extraction for the temperature recording that is included in user log files, according to carrying
The body temperature generation training data obtained.
23. device as claimed in claim 21, it is characterised in that described device also includes：
Second sample classification module, for carrying out sample classification to the training data according to default class condition, it is determined that described
The corresponding sample type mark of training data；
Correspondingly, described device also includes：
Associated storage module, for sample type mark to be associated into storage with physiological period forecast model.
24. device as claimed in claim 23, it is characterised in that described device also includes：
Second data cleansing module, data are carried out for the data format according to default feature extraction algorithm to the training data
Cleaning, obtains meeting the training data of the data format；
Correspondingly, the second feature extraction module includes：
Second feature extraction unit, for calling the default feature extraction algorithm to meeting the training data of the data format
Feature extraction is carried out, the corresponding characteristic sequence of the training data is obtained.
25. device as claimed in claim 21, it is characterised in that the model construction module includes：
Modeling unit, for obtaining mould to be trained to the modeling of the training data corresponding characteristic sequence using default mathematical modeling
Type；
Training unit, the parameter for treating training pattern to described carries out random initializtion, and using EM algorithm to
The parameter that machine initialization is obtained is iterated optimization；
Model generation unit, for parameter after optimization make it is described treat that training pattern restrains, then judge convergent mould to be trained
Type is the physiological period forecast model.
26. a kind of user equipment, it is characterised in that including：
Processor；And
Be stored with computer-readable instruction on memory, the memory, and the computer-readable instruction is held by the processor
The Forecasting Methodology of the determining female physiological periodicity as any one of claim 1 to 14 is realized during row.
27. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the computer program
The Forecasting Methodology of the determining female physiological periodicity as any one of claim 1 to 14 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710413820.7A CN107252323B (en) | 2017-06-05 | 2017-06-05 | Method and device for predicting female physiological cycle and user equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710413820.7A CN107252323B (en) | 2017-06-05 | 2017-06-05 | Method and device for predicting female physiological cycle and user equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107252323A true CN107252323A (en) | 2017-10-17 |
| CN107252323B CN107252323B (en) | 2020-06-26 |
Family
ID=60024384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710413820.7A Active CN107252323B (en) | 2017-06-05 | 2017-06-05 | Method and device for predicting female physiological cycle and user equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107252323B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108735297A (en) * | 2018-05-25 | 2018-11-02 | 上海夏先机电科技发展有限公司 | A kind of basal body temperature data predication method, system and terminal |
| CN108962388A (en) * | 2018-06-21 | 2018-12-07 | 杭州夏娃蕾迪康科技有限公司 | Cloud intelligent natural contraceptive system, devices and methods therefor suitable for Women of childbearing age |
| CN110236489A (en) * | 2019-04-28 | 2019-09-17 | 华为技术有限公司 | A kind of luteal function appraisal procedure and device |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1255321A (en) * | 1998-11-30 | 2000-06-07 | 光磊科技股份有限公司 | Physiological period indicator for women |
| JP2008264352A (en) * | 2007-04-24 | 2008-11-06 | Univ Of Aizu | Menstrual cycle estimation device and menstrual cycle estimation method |
| CN101785686A (en) * | 2009-01-23 | 2010-07-28 | 西江大学校产学协力团 | System for customized prediction of menstruation period or fertility period and calculation method therefor |
| JP5508610B1 (en) * | 2013-11-28 | 2014-06-04 | 楽天株式会社 | Information processing apparatus, information processing method, and information processing program |
| CN104224239A (en) * | 2014-10-17 | 2014-12-24 | 肖南 | Female physiological cycle monitoring method and system |
| JP2015079526A (en) * | 2011-08-12 | 2015-04-23 | 宸鴻科技（廈門）有限公司ＴＰＫ Ｔｏｕｃｈ Ｓｏｌｕｔｉｏｎｓ（Ｘｉａｍｅｎ）Ｉｎｃ． | Capacitive touch panel, and reduction method of visibility of metal jumper on capacitive touch panel |
| CN104714669A (en) * | 2013-12-14 | 2015-06-17 | 宋齐 | Mouse capable of detecting female physiological cycle |
| CN104887194A (en) * | 2015-06-25 | 2015-09-09 | 京东方科技集团股份有限公司 | Method and device for detecting physical signs |
| JP5775243B1 (en) * | 2015-02-20 | 2015-09-09 | 楽天株式会社 | Information processing apparatus, information processing method, and information processing program |
| CN104921711A (en) * | 2015-07-13 | 2015-09-23 | 上海温尔信息科技有限公司 | Female physiological cycle body temperature monitoring method |
| CN105249937A (en) * | 2015-11-09 | 2016-01-20 | 上海温尔信息科技有限公司 | Female natural contraception time monitoring method and device |
-
2017
- 2017-06-05 CN CN201710413820.7A patent/CN107252323B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1255321A (en) * | 1998-11-30 | 2000-06-07 | 光磊科技股份有限公司 | Physiological period indicator for women |
| JP2008264352A (en) * | 2007-04-24 | 2008-11-06 | Univ Of Aizu | Menstrual cycle estimation device and menstrual cycle estimation method |
| CN101785686A (en) * | 2009-01-23 | 2010-07-28 | 西江大学校产学协力团 | System for customized prediction of menstruation period or fertility period and calculation method therefor |
| JP2015079526A (en) * | 2011-08-12 | 2015-04-23 | 宸鴻科技（廈門）有限公司ＴＰＫ Ｔｏｕｃｈ Ｓｏｌｕｔｉｏｎｓ（Ｘｉａｍｅｎ）Ｉｎｃ． | Capacitive touch panel, and reduction method of visibility of metal jumper on capacitive touch panel |
| JP5508610B1 (en) * | 2013-11-28 | 2014-06-04 | 楽天株式会社 | Information processing apparatus, information processing method, and information processing program |
| CN104714669A (en) * | 2013-12-14 | 2015-06-17 | 宋齐 | Mouse capable of detecting female physiological cycle |
| CN104224239A (en) * | 2014-10-17 | 2014-12-24 | 肖南 | Female physiological cycle monitoring method and system |
| JP5775243B1 (en) * | 2015-02-20 | 2015-09-09 | 楽天株式会社 | Information processing apparatus, information processing method, and information processing program |
| CN104887194A (en) * | 2015-06-25 | 2015-09-09 | 京东方科技集团股份有限公司 | Method and device for detecting physical signs |
| CN104921711A (en) * | 2015-07-13 | 2015-09-23 | 上海温尔信息科技有限公司 | Female physiological cycle body temperature monitoring method |
| CN105249937A (en) * | 2015-11-09 | 2016-01-20 | 上海温尔信息科技有限公司 | Female natural contraception time monitoring method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108735297A (en) * | 2018-05-25 | 2018-11-02 | 上海夏先机电科技发展有限公司 | A kind of basal body temperature data predication method, system and terminal |
| CN108962388A (en) * | 2018-06-21 | 2018-12-07 | 杭州夏娃蕾迪康科技有限公司 | Cloud intelligent natural contraceptive system, devices and methods therefor suitable for Women of childbearing age |
| CN110236489A (en) * | 2019-04-28 | 2019-09-17 | 华为技术有限公司 | A kind of luteal function appraisal procedure and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107252323B (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110376457B (en) | Non-invasive load monitoring method and device based on semi-supervised learning algorithm | |
| CN109242164B (en) | Method and device for optimizing product path, computer storage medium and electronic equipment | |
| CN110610280A (en) | Short-term prediction method, model, device and system for power load | |
| CN107689008A (en) | A kind of user insures the method and device of behavior prediction | |
| CN111144468A (en) | Power consumer information labeling method and device, electronic equipment and storage medium | |
| CN110492480A (en) | Power distribution network topology identification method, device, computer equipment and readable storage medium storing program for executing | |
| WO2018222308A1 (en) | Time-based features and moving windows sampling for machine learning | |
| CN111723292B (en) | Recommendation method, system, electronic equipment and storage medium based on graph neural network | |
| CN112633573B (en) | Prediction method of active state and determination method of activity threshold | |
| CN107252323A (en) | Forecasting Methodology, device and the user equipment of determining female physiological periodicity | |
| CN106803799A (en) | A kind of performance test methods and device | |
| CN109409561A (en) | The construction method of Multiple Time Scales time series collaborative forecasting model | |
| CN115018119A (en) | Power load prediction method and system | |
| CN110020310A (en) | Method, apparatus, terminal and the storage medium of resource load | |
| WO2022084125A1 (en) | Federated learning | |
| US20230402125A1 (en) | Drug screening model construction method, a drug screening model construction device, a drug screening method, apparatus and a medium | |
| CN116561569A (en) | Industrial power load identification method based on EO feature selection and AdaBoost algorithm | |
| CN113779391A (en) | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium | |
| CN113298120A (en) | User risk prediction method and system based on fusion model and computer equipment | |
| CN110427562A (en) | Semantic label division methods, device and electronic equipment | |
| Xiao et al. | Enhanced-xgb: An online service resource demand forecasting method for colocation data centers | |
| CN112001760A (en) | Potential user mining method and device, electronic equipment and storage medium | |
| Gong et al. | Diversified and Compatible Web APIs Recommendation in IoT | |
| CN113095583B (en) | Data analysis method applied to service management and service management server | |
| CN111858572B (en) | Distributed data cleaning system and method based on data analysis |
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 | ||
| CB02 | Change of applicant information |
Address after: 361000 Area 1F-D1, Huaxun Building A, Software Park, Xiamen Torch High-tech Zone, Xiamen City, Fujian Province Applicant after: Xiamen Meishao Co., Ltd. Address before: Unit G03, Room 102, 22 Guanri Road, Phase II, Xiamen Software Park, Fujian Province Applicant before: XIAMEN MEIYOU INFORMATION SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |