CN107252323B - Method and device for predicting female physiological cycle and user equipment - Google Patents
Method and device for predicting female physiological cycle and user equipment Download PDFInfo
- Publication number
- CN107252323B CN107252323B CN201710413820.7A CN201710413820A CN107252323B CN 107252323 B CN107252323 B CN 107252323B CN 201710413820 A CN201710413820 A CN 201710413820A CN 107252323 B CN107252323 B CN 107252323B
- Authority
- CN
- China
- Prior art keywords
- body temperature
- physiological cycle
- data
- training data
- physiological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
The disclosure relates to a method and a device for predicting a female physiological cycle, wherein the method for predicting the female physiological cycle comprises the following steps: monitoring the trigger operation of a user for predicting a physiological cycle to generate a physiological cycle prediction instruction; acquiring body temperature data triggered according to the physiological cycle prediction instruction; performing feature extraction on the acquired body temperature data to obtain a physiological feature sequence; and in a pre-constructed physiological cycle prediction model, the physiological characteristic sequence is used as the input of the physiological cycle prediction model to predict the physiological cycle, and the physiological cycle is obtained through output. By adopting the method and the device for predicting the female physiological cycle, the accuracy of predicting the physiological cycle can be effectively improved.
Description
Technical Field
The present disclosure relates to the field of medical technologies, and in particular, to a method and an apparatus for predicting a female physiological cycle, and a user device.
Background
In the prior art, the average value of the historical physiological cycles is generally used as a predicted value in the prediction method of the female physiological cycles, but the predicted value is easily influenced by various factors such as mood, climate and health conditions, so that the prediction accuracy is low.
Therefore, a prediction method for predicting the physiological cycle of the female through the basal body temperature of the female is provided, and researches show that the basal body temperature of the female is closely related to the ovarian function, and the physiological cycle can be predicted through the change of the basal body temperature.
However, basal body temperature is more critical, i.e. sublingual body temperature is measured after a longer period of sleep, before waking up without any activity. In actual measurement, it is difficult to ensure whether the measurement of the basal body temperature satisfies the above-mentioned strict requirements. If there is a measurement error in the basal body temperature, the physiological cycle still cannot be accurately predicted.
From the above, how to accurately predict the physiological cycle of women still remains to be solved.
Disclosure of Invention
In order to solve the above technical problem, an object of the present disclosure is to provide a method and an apparatus for predicting a female physiological cycle, and a user equipment.
Wherein, the technical scheme who this disclosure adopted does:
a method of predicting a female physiological cycle, comprising: monitoring the trigger operation of a user for predicting a physiological cycle to generate a physiological cycle prediction instruction; acquiring body temperature data triggered according to the physiological cycle prediction instruction; performing feature extraction on the acquired body temperature data to obtain a physiological feature sequence; and in a pre-constructed physiological cycle prediction model, the physiological characteristic sequence is used as the input of the physiological cycle prediction model to predict the physiological cycle, and the physiological cycle is obtained through output. An apparatus for predicting a female physiological cycle, comprising: the instruction generation module is used for monitoring the trigger operation of the user for predicting the physiological cycle and generating a physiological cycle prediction instruction; the body temperature data acquisition module is used for acquiring body temperature data according to the physiological cycle prediction instruction; the first feature extraction module is used for performing feature extraction on the acquired body temperature data to obtain a physiological feature sequence; and the physiological cycle prediction module is used for predicting the physiological cycle by taking the physiological characteristic sequence as the input of the physiological cycle prediction model in a pre-constructed physiological cycle prediction model and outputting the physiological cycle.
A user device comprising a processor and a memory having stored thereon computer readable instructions which, when executed by the processor, implement a method of predicting a female physiological cycle as described above.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method of predicting a female physiological cycle as set forth above.
Compared with the prior art, the method has the following beneficial effects:
the physiological characteristic sequence is obtained by carrying out characteristic extraction on the obtained body temperature data, and then the physiological cycle is predicted by taking the physiological characteristic sequence as the input of a physiological cycle prediction model in a pre-constructed physiological cycle prediction model to obtain the physiological cycle.
In addition, the physiological cycle is predicted by a physiological cycle prediction model constructed in advance aiming at the body temperature, the method has the support of a mathematical algorithm, the average value of the historical physiological cycle is avoided being simply used as a predicted value, and the prediction accuracy is effectively improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a block diagram illustrating a hardware architecture of a user device in accordance with an exemplary embodiment;
FIG. 2 is a flow chart illustrating a method of predicting a female physiological cycle in accordance with an exemplary embodiment;
FIG. 3 is a flow diagram for one embodiment of step 310 in a corresponding embodiment of FIG. 2;
FIG. 4 is a flow chart illustrating another method of predicting a female physiological cycle in accordance with an exemplary embodiment;
FIG. 5 is a flow diagram for one embodiment of step 450 of the corresponding embodiment of FIG. 4;
FIG. 6 is a schematic diagram of a predetermined mathematical model in the corresponding embodiment of FIG. 5;
FIG. 7 is a schematic diagram of an implementation of a method for predicting a female physiological cycle in an application scenario;
FIG. 8 is a block diagram illustrating an apparatus for predicting a female physiological cycle in accordance with an exemplary embodiment;
FIG. 9 is a block diagram for one embodiment of a body temperature data acquisition module 710 in the corresponding embodiment of FIG. 8;
FIG. 10 is a block diagram illustrating another apparatus for predicting a female physiological cycle in accordance with an exemplary embodiment;
FIG. 11 is a block diagram for one embodiment of model building module 850 in a corresponding embodiment of FIG. 10.
While specific embodiments of the disclosure have been shown and described in detail in the drawings and foregoing description, such drawings and description are not intended to limit the scope of the disclosed concepts in any way, but rather to explain the concepts of the disclosure to those skilled in the art by reference to the particular embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
As mentioned above, the method for predicting the female physiological cycle in the prior art still has the defect of low accuracy of prediction.
Based on this, the present disclosure particularly proposes a method for predicting a female physiological cycle, which effectively improves the accuracy of prediction. The method is realized by a computer program, and corresponding computer readable instructions corresponding to the constructed device for predicting the female physiological cycle are stored in a memory of the user equipment so as to facilitate the prediction of the female physiological cycle.
Fig. 1 is a block diagram illustrating a hardware structure of a user equipment 100 according to an exemplary embodiment. It should be noted that the user equipment 100 is only an example adapted to the present disclosure, and should not be considered as providing any limitation to the scope of the present disclosure. The user device 100 also cannot be interpreted as needing to rely on or have to have one or more components of the exemplary user device 100 shown in fig. 1.
The hardware structure of the user equipment 100 may be greatly different due to different configurations or performances, as shown in fig. 1, the user equipment 100 includes: a power supply 110, an interface 130, at least one storage medium 150, and at least one Central Processing Unit (CPU) 170.
The power supply 110 is used to provide operating voltage for each hardware device on the user equipment 100.
The interface 130 includes at least one wired or wireless network interface 131, at least one serial-to-parallel conversion interface 133, at least one input/output interface 135, and at least one USB interface 137, etc. for communicating with external devices.
The storage medium 150 may be a random access medium, a magnetic disk or an optical disk as a carrier for storing resources, the resources stored thereon include an operating system 151, an application 153, data 155, and the like, and the storage mode may be a transient storage mode or a permanent storage mode. The operating system 151 is used for managing and controlling hardware devices and application programs 153 on the user device 100 to realize the computation and processing of the mass data 155 by the central processing unit 170, and may be Windows server, MacOS XTM, unix, linux, FreeBSDTM, or the like. The application 153 is a computer program that performs at least one specific task on the operating system 151, and may include at least one module (not shown in fig. 1), each of which may contain a series of operation instructions for the user equipment 100. The data 155 may be photographs, pictures, etc. stored in a disk.
The central processor 170 may include one or more processors and is configured to communicate with the storage medium 150 via a bus for computing and processing the mass data 155 in the storage medium 150.
As described in detail above, the user device 100 to which the present disclosure is applied will implement the prediction method of the female physiological cycle by the central processor 170 reading a series of operation instructions stored in the storage medium 150.
Furthermore, the present disclosure can be implemented equally as hardware circuitry or hardware circuitry in combination with software instructions, and thus implementation of the present disclosure is not limited to any specific hardware circuitry, software, or combination of both.
Referring to fig. 2, in an exemplary embodiment, a method for predicting a female physiological cycle is applied to the user device 100 shown in fig. 1, and the method for predicting a female physiological cycle may be performed by the user device 100 and may include the following steps:
and 310, monitoring the trigger operation of the user for predicting the physiological cycle, and generating a physiological cycle prediction instruction.
For the user device, a prediction entrance of the female physiological cycle is provided for the user, so that the user can predict the female physiological cycle through a triggering operation performed at the prediction entrance.
For example, the prediction entry may be a virtual key on a human-computer interface provided by the user equipment, and when the user wants to predict the female physiological cycle, the user clicks the virtual key, and the clicking operation is a triggering operation of the user on predicting the physiological cycle.
After the user equipment monitors the trigger operation of the user at the prediction entrance, a physiological cycle prediction instruction is generated by responding to the trigger operation, and then the female physiological cycle prediction is started according to the physiological cycle prediction instruction.
And step 330, acquiring body temperature data according to the physiological cycle prediction instruction.
In this embodiment, the body temperature data represents the temperature of the female body, i.e., the female body temperature.
Further, the body temperature of women slightly varies depending on the measurement site. For example, the normal range of axillary temperatures is 36.1 ℃ to 37 ℃ and oral temperatures are 36.3 ℃ to 37.2 ℃.
Furthermore, female body temperature may vary slightly within the normal range under the influence of internal and external factors. For example, the temperature of a female in the early morning of the afternoon may be relatively high, or may be slightly elevated after eating or exercising, or may be slightly higher than the normal range during ovulation or pregnancy.
Further, the body temperature data is pre-stored in the user device, so that the pre-stored body temperature data can be acquired by the user device. For example, the body temperature data may be stored in the user device in the form of a user log file.
And 350, performing feature extraction on the acquired body temperature data to obtain a physiological feature sequence.
In order to make a prediction of the female physiological cycle, the characteristic distribution of the physiological cycle needs to be known.
As previously mentioned, women have temperatures slightly above the normal range during ovulation or pregnancy. Thus, in the present embodiment, the learning of the feature distribution of the physiological cycle is realized by feature extraction of the body temperature data.
Specifically, the feature extraction process includes averaging low and high temperatures in the body temperature data, performing differential processing on the body temperature data, performing normalization processing on the body temperature data, and the like.
By means of feature extraction of the body temperature data, a physiological feature sequence reflecting feature distribution of a physiological cycle is obtained, and prediction of a subsequent female physiological cycle is facilitated according to the physiological feature sequence.
And 370, in the pre-constructed physiological cycle prediction model, performing physiological cycle prediction by taking the physiological characteristic sequence as the input of the physiological cycle prediction model, and outputting to obtain the physiological cycle.
The physiological cycle prediction model is constructed in advance according to the characteristic distribution of the physiological cycle. That is, the physiological cycle can be output by using the characteristic distribution of the physiological cycle as an input.
After a physiological characteristic sequence reflecting the characteristic distribution of the physiological cycle is obtained, the physiological cycle can be predicted and obtained through a physiological cycle prediction model.
Furthermore, the ovulation time is calculated from the physiological cycle by combining the time relation that the difference between the physiological cycle and the ovulation time is 142 days, so that different prediction requirements of users are met.
Through the process, the physiological cycle prediction is carried out by utilizing the physiological cycle prediction model, so that the prediction of the female physiological cycle has the support of a mathematical algorithm, and the prediction accuracy is effectively improved.
Referring to FIG. 3, in an exemplary embodiment, step 310 may include the steps of:
and 311, drawing a body temperature curve according to the pre-stored body temperature record.
The body temperature measured by the user is recorded in the form of a user log file, that is, at least the measured body temperature and the measurement time corresponding to the body temperature are recorded in the user log file.
Specifically, the user equipment responds to a body temperature recording operation triggered by the user for the measured body temperature, generates a body temperature record, and stores the generated body temperature record into a user log file.
Therefore, the body temperature record can be acquired correspondingly by reading the user log file. The body temperature record comprises the measured body temperature and the corresponding measuring time of the body temperature.
After the body temperature record is obtained, a body temperature curve can be drawn according to the body temperature record.
Specifically, the body temperature is taken as a vertical coordinate, the time is taken as a horizontal coordinate, the measured body temperature and the measuring time corresponding to the body temperature form a coordinate point, and the body temperature curve is obtained by connecting a plurality of coordinate points through straight lines.
And 313, performing smooth denoising processing on the body temperature curve.
It can be understood that, since the measurement time of the body temperature measurement is discontinuous at intervals, the body temperature curve obtained by connecting the coordinate points in a straight line has a substantial defect, that is, the body temperature corresponding to the time when the body temperature measurement is not performed in the body temperature curve cannot be guaranteed to be accurate.
Therefore, in the embodiment, the body temperature curve is subjected to smooth denoising processing through a smooth denoising algorithm, abnormal values and missing values in the body temperature curve are filtered, and local fluctuation of the body temperature curve is eliminated, so that the accuracy and integrity of the body temperature measured in the body temperature curve are effectively guaranteed, and the accuracy of prediction is improved subsequently.
The smoothing denoising algorithm may be, but not limited to, mean filtering, median filtering, wavelet transform based denoising, Total Variation (TV) denoising, and the like.
And 315, extracting the body temperature data meeting the preset extraction conditions from the body temperature curve obtained by the smooth denoising treatment.
Wherein the preset extraction conditions include extraction by time period, extraction by temperature interval, and the like.
After the smooth denoising processing is finished, body temperature data can be extracted from the processed body temperature curve.
Under the effect of the embodiment, the time continuity of body temperature measurement is realized, namely missing values in a body temperature curve are filtered, the integrity of the body temperature curve is ensured, meanwhile, abnormal values in the body temperature curve are filtered through smooth denoising, the local fluctuation of the body temperature curve is eliminated, the accuracy of the body temperature curve is ensured, and the accuracy of subsequent prediction is favorably improved.
In an exemplary embodiment, before step 330, the method as described above may further include the steps of:
and carrying out sample classification on the body temperature data according to preset classification conditions, and determining a sample type identifier corresponding to the body temperature data.
The preset classification condition comprises at least one of a body temperature curve type and a measurement time period.
First, a body temperature curve type is explained, since body temperature data is extracted from a body temperature curve, the body temperature curve type corresponds to the body temperature data, and the body temperature curve type reflects the distribution of the body temperature measured in the body temperature curve.
In particular, the body temperature profile types include normal biphasic profile, abnormal biphasic profile, and monophasic profile.
Further, the abnormal biphasic profile includes a curve with a slow ascending and descending amplitude, a descending and ascending amplitude lower than 0.3, and so on.
The single-phase distribution includes the curve with lower amplitude and higher amplitude, the curve with saw-toothed waveform, etc.
What should be mentioned next is a measurement period, which is related to the measurement time for the user to measure the body temperature.
As mentioned above, female body temperature can vary slightly within the normal range under the influence of both internal and external factors. For example, the body temperature of a woman is relatively high early in the afternoon.
For this reason, the measurement time periods may be divided for morning, afternoon, evening to ensure that the body temperature fluctuations within the same measurement time period are small.
That is, the measurement periods include a morning period, an afternoon period, and an evening period.
It should be understood that if the distribution of body temperature is different, the characteristic distribution of the physiological cycle reflected by the physiological cycle prediction model is different.
Therefore, the sample classification can be performed according to the preset classification conditions, so that the sample type identifier corresponding to the body temperature data is determined, and a physiological cycle prediction model for predicting a physiological cycle subsequently corresponds to the sample type identifier, so that the prediction accuracy is improved.
Accordingly, prior to step 370, the method as described above may further include the steps of:
and finding out the corresponding physiological cycle prediction model according to the sample type identification association.
Through the cooperation of the embodiment, the body temperature data is subjected to sample classification, so that different sample type identifications can be associated and found out to obtain different physiological cycle prediction models, and the physiological cycle prediction can be performed according to the different physiological cycle prediction models subsequently, thereby further being beneficial to improving the accuracy of the prediction.
Further, in an exemplary embodiment, before the step of sample classification of the body temperature data according to a preset classification condition and determining a sample type identifier corresponding to the body temperature data, the method as described above may further include the following steps:
and cleaning the body temperature data according to the data format of the preset feature extraction algorithm to obtain the body temperature data conforming to the data format.
The preset feature extraction algorithm is used for extracting features of the body temperature data, and the body temperature data is subjected to data cleaning according to the data format of the preset feature extraction algorithm, so that the data format of the body temperature data accords with the data format of the preset feature extraction algorithm, and the subsequent feature extraction of the body temperature data which accords with the data format through the preset feature extraction algorithm is facilitated.
Accordingly, step 330 may include the steps of:
and calling a preset feature extraction algorithm to extract features of the body temperature data conforming to the data format to obtain a physiological feature sequence.
In an exemplary embodiment, after step 330, the method as described above may further include the steps of:
the influencer features are added to the sequence of physiological features.
As mentioned above, the prediction of the female physiological cycle is easily influenced by various factors such as mood, climate and health condition, resulting in low accuracy of the prediction.
Therefore, after the physiological characteristic sequence is obtained, the influence factor characteristics are added to the physiological characteristic sequence, so that the multi-dimensional prediction of the female physiological cycle is ensured, and the accuracy of the prediction is improved.
Wherein the influencing factor characteristic is used for characterizing the influencing factor which can influence the physiological cycle. The influencing factors comprise female age, climate, emotion, health condition and the like, and correspondingly, the influencing factor characteristics comprise female age characteristics, regional characteristics and historical physiological cycle characteristics.
Further, the geographic characteristics reflect the climate, etc., of the geographic location in which the woman is located.
The historical physiological cycle characteristics include a historical physiological cycle reflecting the mood, health condition, and the like of the female.
The obtaining process of the influence factor characteristics specifically comprises the following steps: and acquiring influence factors influencing the physiological cycle, and performing characteristic conversion on the influence factors to obtain influence factor characteristics.
Under the cooperation of the embodiment, multi-dimensional prediction based on the influence factor characteristics is realized, so that the accuracy of prediction is further improved.
Referring to fig. 4, in an exemplary embodiment, the method as described above may further include the steps of:
at step 410, training data is obtained.
Before the prediction of the female physiological cycle is performed, training data is required to be used as a training basis for the physiological cycle prediction model in order to construct the physiological cycle prediction model. A relatively accurate physiological cycle prediction model can be obtained by acquiring a large amount of training data, so that the female physiological cycle can be predicted more accurately.
In this embodiment, the training data is extracted locally, that is, obtained from a local user log file.
As described above, the user log file stores a body temperature record, which includes the measured body temperature and the measurement time corresponding to the body temperature.
Therefore, the body temperature is extracted according to the body temperature records contained in the user log file, and the training data can be generated according to the extracted body temperature.
Of course, in other application scenarios, the user equipment may also obtain training data in other user equipment from the storage server through interaction with the storage server.
And 430, performing feature extraction on the obtained training data to obtain a feature sequence corresponding to the training data.
As described above, since the physiological cycle prediction model is obtained by previously constructing the feature distribution of the physiological cycle, it is necessary to extract features from training data before constructing the physiological cycle prediction model.
Further, the obtained training data is massive, and accordingly, the feature sequences correspond to the training data, that is, after feature extraction is performed, the feature sequence corresponding to each training data is obtained.
And step 450, establishing and training a model according to the characteristic sequence corresponding to the training data to obtain a physiological cycle prediction model.
And after the characteristic sequence corresponding to each training data is obtained, the input of model establishment and training is obtained. That is, a physiological cycle prediction model reflecting the characteristic distribution of the physiological cycle can be obtained by performing model building and training using the characteristic sequence corresponding to the training data as an input.
Under the cooperation of the embodiment, the physiological cycle prediction model is constructed in advance, so that the prediction of the subsequent female physiological cycle has the support of a mathematical algorithm, and the accuracy of the prediction is improved.
In addition, the construction of a physiological cycle prediction model is guaranteed to be based on a large amount of training data, namely real body temperature data, and therefore the premise of accurate prediction of the physiological cycle is formed.
In an exemplary embodiment, after step 410, the method as described above may further include the steps of:
and carrying out sample classification on the training data according to a preset classification condition, and determining a sample type identifier corresponding to the training data.
As described above, the preset classification condition includes at least one of a body temperature curve type and a measurement time period.
The body temperature curve types include normal biphasic distribution, abnormal biphasic distribution, and monophasic distribution, among others.
Further, the abnormal biphasic profile includes a curve with a slow ascending and descending amplitude, a descending and ascending amplitude lower than 0.3, and so on.
The single-phase distribution includes the curve with lower amplitude and higher amplitude, the curve with saw-toothed waveform, etc.
The measurement periods include morning, afternoon, and evening periods.
Accordingly, the sample types of the training data also include normal biphasic distribution, abnormal biphasic distribution, and monophasic distribution, as well as morning time periods, afternoon time periods, evening time periods, and the like.
Further, after step 450, the method as described above may further include the steps of:
and storing the sample type identification in association with the physiological cycle prediction model.
For example, if the body temperature curve type is normal biphasic distribution, the sample type of the training data is normal biphasic distribution, and accordingly, the feature distribution of the physiological cycle reflected by the physiological cycle prediction model is related to the normal biphasic distribution.
Through the matching of the embodiments, when the sample type identifications are different, the physiological cycle prediction models used for predicting the physiological cycle are also distinguished, so that the accuracy of prediction is further effectively improved.
Further, in an exemplary embodiment, before the step of performing sample classification on the training data according to a preset classification condition and determining a sample type identifier corresponding to the training data, the method as described above may further include the following steps:
and carrying out data cleaning on the training data according to the data format of the preset feature extraction algorithm to obtain the training data conforming to the data format.
The preset feature extraction algorithm is used for extracting features of the training data, and the training data are subjected to data cleaning according to the data format of the preset feature extraction algorithm, so that the data format of the training data conforms to the data format of the preset feature extraction algorithm, and the subsequent feature extraction of the training data conforming to the data format through the preset feature extraction algorithm is facilitated.
Accordingly, step 430 may include the steps of:
and calling a preset feature extraction algorithm to extract features of the training data conforming to the data format to obtain a feature sequence corresponding to the training data.
Referring to fig. 5, in an exemplary embodiment, step 450 may include the steps of:
and 451, modeling the feature sequence corresponding to the training data by using a preset mathematical model to obtain a model to be trained.
In this embodiment, the modeling reflects the feature sequence corresponding to the training data by using the mathematical structure described by the preset mathematical model.
The predetermined mathematical Model is not limited herein, and is exemplified by the predetermined mathematical Model being a Model of HMM (Hidden Markov Model) -GMM (Gaussian Mixture Model).
The HMM model uses a 3-state self-loop span-free topological structure, namely, a feature sequence corresponding to training data is subjected to state description through the HMM model. As shown in FIG. 6, the feature sequence corresponding to the training data is divided into 3 states, wherein each state Si,i＝1,2,3 can jump to itself and the next state Si+1，aijRepresents a state SiJump to state SjThe transition probability of (2).
Further, for each state, a GMM model is adopted for modeling, and a model to be trained, which can reflect the feature distribution of the physiological cycle, is obtained.
In other words, the modeling establishes the corresponding relation between the state and the characteristic sequence, so that the established corresponding relation is optimized through subsequent training, and the physiological cycle prediction model is obtained.
And 453, performing random initialization on the parameters of the model to be trained, and performing iterative optimization on the parameters obtained by the random initialization by using a maximum expectation algorithm.
It can be understood that the correspondence between the states and the feature sequences is optimized through training, i.e. the probability that the feature sequences belong to a corresponding state is maximized.
That is, in order to obtain the maximum probability that a feature sequence belongs to a corresponding state, the parameters of the model to be trained are trained.
Specifically, parameters of the model to be trained are iteratively optimized through an Expectation Maximization (EM) Algorithm to obtain a determined value of the parameters of the model to be trained, where the determined value is a maximum probability that the feature sequence belongs to a corresponding state.
In the initial stage of parameter iterative optimization, the parameters of the model to be trained are randomly initialized, and the parameters obtained by the random initialization are used as initial training parameters.
Further, each iterative optimization process of the maximum expectation algorithm comprises the following two steps:
e, calculating the probability distribution of the parameters of the model to be trained based on the current training parameters;
and M, calculating a parameter corresponding to the maximum expected probability distribution of the parameter of the model to be trained, wherein the parameter is the optimized parameter.
And when the optimized parameters can not make the model to be trained converge, updating the training parameters by using the optimized parameters, and continuing the iterative optimization process.
When the optimized parameters make the model to be trained converge, the step 455 is skipped.
And 455, when the optimized parameters make the model to be trained converge, determining that the converged model to be trained is a physiological cycle prediction model.
After the physiological cycle prediction model is obtained through training, the characteristic distribution of the physiological cycle corresponding to the female body temperature can be reflected through the physiological cycle prediction model, so that the corresponding physiological cycle can be predicted through the female body temperature.
In addition, the physiological cycle prediction model obtained by training corresponds to the sample type of the training data, so that the training data of different sample types can be respectively modeled and trained to obtain different physiological cycle prediction models, and the prediction precision is effectively ensured.
Fig. 7 is a schematic diagram of an implementation of a method for predicting a female physiological cycle in an application scenario, and a flow of the method for predicting a female physiological cycle in embodiments of the present disclosure is described with reference to the user equipment shown in fig. 1 and the application scenario shown in fig. 7.
By executing steps 601 to 605, a physiological cycle prediction model is constructed.
By executing the steps 606 to 610, the physiological characteristic sequence is extracted from the input body temperature data.
And by executing step 611, the physiological characteristic sequence is used as a model input, and the physiological cycle is predicted by the physiological cycle prediction model, so as to obtain a physiological cycle 612 and an ovulation cycle 613.
In the embodiments of the present disclosure, a machine learning algorithm is used to construct a physiological cycle prediction model, so that the prediction of the female physiological cycle has the support of a mathematical algorithm, and the simple use of the average value of the historical physiological cycle as a prediction value is avoided, thereby effectively improving the accuracy of the prediction.
The following are embodiments of the disclosed apparatus that may be used to perform the method for predicting a female physiological cycle according to the present disclosure. For details not disclosed in the embodiments of the disclosed device, please refer to the embodiments of the method for predicting the female physiological cycle in the present disclosure.
Referring to fig. 8, in an exemplary embodiment, an apparatus 700 for predicting a female physiological cycle includes, but is not limited to: an instruction generation module 710, a body temperature data acquisition module 730, a first feature extraction module 750, and a physiological cycle prediction module 770.
The instruction generating module 710 is configured to intercept a trigger operation of a user to predict a physiological cycle, and generate a physiological cycle prediction instruction.
The body temperature data acquisition module 730 is used for acquiring body temperature data according to the physiological cycle prediction instruction.
The first feature extraction module 750 is configured to perform feature extraction on the acquired body temperature data to obtain a physiological feature sequence.
The physiological cycle prediction module 770 is configured to predict a physiological cycle by using a physiological characteristic sequence as an input of a physiological cycle prediction model in a pre-constructed physiological cycle prediction model, and output the physiological cycle.
Referring to fig. 9, in an exemplary embodiment, the body temperature data acquisition module 710 includes, but is not limited to: a body temperature curve drawing unit 711, a body temperature curve processing unit 713, and a body temperature data extracting unit 715.
The body temperature curve drawing unit 711 is configured to draw a body temperature curve according to a pre-stored body temperature record.
The body temperature curve processing unit 713 is configured to perform smoothing denoising processing on the body temperature curve.
The body temperature data extraction unit 715 is configured to extract body temperature data from the body temperature curve obtained through the smoothing denoising processing.
In an exemplary embodiment, the apparatus as described above further includes, but is not limited to: the device comprises a body temperature record generating module and a body temperature record storage module.
The body temperature record generating module is used for responding to body temperature record operation triggered by a user aiming at the measured body temperature and generating a body temperature record. The body temperature record comprises the measured body temperature and the measuring time corresponding to the body temperature.
The body temperature record storage module is used for storing the generated body temperature record to a user log file.
In an exemplary embodiment, the apparatus as described above further includes, but is not limited to: a first sample classification module.
The first sample classification module is used for carrying out sample classification on the body temperature data according to preset classification conditions and determining a sample type identifier corresponding to the body temperature data.
Accordingly, the apparatus as described above further includes, but is not limited to: and an association searching module.
The correlation searching module is used for searching the corresponding physiological cycle prediction model according to the sample type identification correlation.
In an exemplary embodiment, the apparatus 700 as described above further includes, but is not limited to: and a data cleaning module.
The data cleaning module is used for cleaning the body temperature data according to the data format of the preset feature extraction algorithm to obtain the body temperature data conforming to the data format.
Accordingly, the first feature extraction module 730 includes, but is not limited to: a first feature extraction unit.
The first feature extraction unit is used for calling a preset feature extraction algorithm to perform feature extraction on the body temperature data conforming to the data format to obtain a physiological feature sequence.
In an exemplary embodiment, the apparatus 700 as described above further includes, but is not limited to: the system comprises a characteristic conversion module and an influence factor characteristic adding module.
The characteristic conversion module is used for collecting influence factors and performing characteristic conversion on the influence factors.
And the influence factor characteristic adding module is used for adding the influence factor characteristics obtained by characteristic conversion to the physiological characteristic sequence. The influential characteristics are used to characterize the influential factors that will have an effect on the physiological cycle.
Referring to fig. 10, in an exemplary embodiment, the apparatus 700 as described above further includes, but is not limited to: a training data acquisition module 810, a second feature extraction module 830, and a model construction module 850.
The training data obtaining module 810 is configured to obtain training data.
The second feature extraction module 830 is configured to perform feature extraction on the obtained training data to obtain a feature sequence corresponding to the training data.
The model building module 850 is used for building and training a model according to the feature sequence corresponding to the training data to obtain a physiological cycle prediction model.
In an exemplary embodiment, the training data acquisition module includes, but is not limited to: and a log file reading module.
The log file reading module is used for extracting the body temperature according to the body temperature records contained in the user log file and generating training data according to the extracted body temperature.
In an exemplary embodiment, the apparatus 700 as described above further includes, but is not limited to: a second sample classification module.
The second sample classification module is used for carrying out sample classification on the training data according to preset classification conditions and determining a sample type identifier corresponding to the training data.
Accordingly, the apparatus as described above further includes, but is not limited to: and associating the storage module.
The correlation storage module is used for performing correlation storage on the sample type identification and the physiological cycle prediction model.
In an exemplary embodiment, the apparatus as described above further includes, but is not limited to: and a second data cleaning module.
The second data cleaning module is used for cleaning the training data according to the data format of the preset feature extraction algorithm to obtain the training data conforming to the data format.
Accordingly, the second feature extraction module includes, but is not limited to: a second feature extraction unit.
The second feature extraction unit is used for calling a preset feature extraction algorithm to extract features of the training data conforming to the data format, and obtaining a feature sequence corresponding to the training data.
Referring to FIG. 11, in an exemplary embodiment, model build module 850 includes, but is not limited to: a modeling unit 851, a training unit 853, and a model generation unit 855.
The modeling unit 851 is configured to model the feature sequence corresponding to the training data by using a preset mathematical model to obtain a model to be trained.
The training unit 853 is configured to perform random initialization on parameters of the model to be trained, and perform iterative optimization on the parameters obtained through the random initialization by using a maximum expectation algorithm.
The model generating unit 855 is configured to determine that the converged model to be trained is a circadian cycle prediction model when the optimized parameters make the model to be trained converge.
It should be noted that, when the prediction device for a female physiological cycle provided in the above embodiment performs the prediction process of the female physiological cycle, the above-mentioned division of each functional module is merely exemplified, and in practical applications, the above-mentioned function allocation may be completed by different functional modules according to needs, that is, the internal structure of the prediction device for a female physiological cycle is divided into different functional modules to complete all or part of the above-mentioned functions.
In addition, the device for predicting a female physiological cycle provided in the above embodiments and the method for predicting a female physiological cycle belong to the same concept, wherein the specific manner in which each module performs operations has been described in detail in the method embodiments, and is not described herein again.
In an exemplary embodiment, a user equipment includes a processor and a memory.
Wherein the memory has stored thereon computer readable instructions which, when executed by the processor, implement the method for predicting a female physiological cycle as in the above embodiments.
In an exemplary embodiment, a computer readable storage medium has stored thereon a computer program which, when being executed by a processor, implements the method for predicting a female physiological cycle as in the above embodiments.
The above description is only a preferred exemplary embodiment of the present disclosure, and not intended to limit the embodiments of the present disclosure, and one of ordinary skill in the art can easily make various changes and modifications according to the main concept and spirit of the present disclosure, so that the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (25)
1. A method for predicting a female physiological cycle, comprising:
monitoring the trigger operation of a user for predicting a physiological cycle to generate a physiological cycle prediction instruction;
acquiring body temperature data triggered according to the physiological cycle prediction instruction;
sample classification is carried out on the body temperature data according to preset classification conditions, and a sample type identifier corresponding to the body temperature data is determined;
finding out a corresponding physiological cycle prediction model according to the sample type identification association;
performing feature extraction on the acquired body temperature data to obtain a physiological feature sequence;
and in a pre-constructed physiological cycle prediction model, the physiological characteristic sequence is used as the input of the physiological cycle prediction model to predict the physiological cycle, and the physiological cycle is obtained through output.
2. The method of claim 1, wherein said obtaining body temperature data comprises:
drawing a body temperature curve according to a prestored body temperature record;
carrying out smooth denoising processing on the body temperature curve;
and extracting the body temperature data which meets the preset extraction conditions from the body temperature curve obtained by the smooth denoising treatment.
3. The method of claim 2, wherein prior to said drawing a body temperature curve from a pre-stored body temperature record, the method further comprises:
responding to a body temperature recording operation triggered by a user aiming at the measured body temperature, and generating a body temperature record, wherein the body temperature record comprises the measured body temperature and the measuring time corresponding to the body temperature;
and storing the generated body temperature record to a user log file.
4. The method of claim 1, wherein the preset classification condition comprises at least one of a type of body temperature curve and a measurement time period.
5. The method of claim 1, wherein before the sample classification is performed on the body temperature data according to a preset classification condition and the sample type identifier corresponding to the body temperature data is determined, the method further comprises:
carrying out data cleaning on the body temperature data according to a data format of a preset feature extraction algorithm to obtain body temperature data conforming to the data format;
correspondingly, the obtaining of the physiological characteristic sequence by performing characteristic extraction on the obtained body temperature data includes:
and calling the preset feature extraction algorithm to extract features of the body temperature data conforming to the data format to obtain the physiological feature sequence.
6. The method of claim 1, wherein after the feature extraction of the acquired body temperature data to obtain the physiological feature sequence, the method further comprises:
collecting influence factors and carrying out characteristic transformation on the influence factors;
and adding the influence factor characteristics obtained by characteristic conversion to the physiological characteristic sequence, wherein the influence factor characteristics are used for characterizing the influence factors which can influence the physiological cycle.
7. The method of claim 6, wherein the influential characteristic comprises at least one of a female age characteristic, a regional characteristic, and a historical physiological cycle characteristic.
8. The method of any of claims 1 to 7, further comprising:
acquiring training data;
performing feature extraction on the obtained training data to obtain a feature sequence corresponding to the training data;
and establishing and training a model according to the characteristic sequence corresponding to the training data to obtain the physiological cycle prediction model.
9. The method of claim 8, wherein the obtaining training data comprises:
and extracting the body temperature according to the body temperature record contained in the user log file, and generating training data according to the extracted body temperature.
10. The method of claim 8, wherein before the feature extraction is performed on the obtained training data to obtain the feature sequence corresponding to the training data, the method further comprises:
carrying out sample classification on the training data according to preset classification conditions, and determining a sample type identifier corresponding to the training data;
correspondingly, after the model is established and trained according to the feature sequence corresponding to the training data to obtain the physiological cycle prediction model, the method further comprises:
and storing the sample type identification in association with a physiological cycle prediction model.
11. The method of claim 10, wherein the preset classification condition comprises at least one of a type of body temperature curve and a measurement time period.
12. The method of claim 10, wherein before the sample classification is performed on the training data according to a preset classification condition and the sample type identifier corresponding to the training data is determined, the method further comprises:
performing data cleaning on the training data according to a data format of a preset feature extraction algorithm to obtain training data conforming to the data format;
correspondingly, the performing feature extraction on the obtained training data to obtain a feature sequence corresponding to the training data includes:
and calling the preset feature extraction algorithm to extract features of the training data conforming to the data format to obtain a feature sequence corresponding to the training data.
13. The method of claim 8, wherein the model building and training according to the feature sequence corresponding to the training data to obtain the physiological cycle prediction model comprises:
modeling a characteristic sequence corresponding to the training data by adopting a preset mathematical model to obtain a model to be trained;
performing random initialization on the parameters of the model to be trained, and performing iterative optimization on the parameters obtained by the random initialization by using a maximum expectation algorithm;
and when the optimized parameters enable the model to be trained to be converged, judging that the converged model to be trained is the physiological cycle prediction model.
14. An apparatus for predicting a female physiological cycle, comprising:
the instruction generation module is used for monitoring the trigger operation of the user for predicting the physiological cycle and generating a physiological cycle prediction instruction;
the body temperature data acquisition module is used for acquiring body temperature data according to the physiological cycle prediction instruction;
the first feature extraction module is used for performing feature extraction on the acquired body temperature data to obtain a physiological feature sequence;
the physiological cycle prediction module is used for predicting a physiological cycle by taking the physiological characteristic sequence as the input of the physiological cycle prediction model in a pre-constructed physiological cycle prediction model and outputting the physiological cycle;
the first sample classification module is used for carrying out sample classification on the body temperature data according to preset classification conditions and determining a sample type identifier corresponding to the body temperature data;
correspondingly, the device further comprises:
and the correlation searching module is used for searching the corresponding physiological cycle prediction model according to the sample type identification correlation.
15. The apparatus of claim 14, wherein the body temperature data acquisition module comprises:
the body temperature curve drawing unit is used for drawing a body temperature curve according to a prestored body temperature record;
the body temperature curve processing unit is used for carrying out smooth denoising processing on the body temperature curve;
and the body temperature data extraction unit is used for extracting the body temperature data which meet preset extraction conditions from the body temperature curve obtained through the smooth denoising processing.
16. The apparatus of claim 15, wherein the apparatus further comprises:
the body temperature record generating module is used for responding to body temperature record operation triggered by a user aiming at the measured body temperature and generating a body temperature record, wherein the body temperature record comprises the measured body temperature and the measuring time corresponding to the body temperature;
and the body temperature record storage module is used for storing the generated body temperature record to a user log file.
17. The apparatus of claim 16, wherein the apparatus further comprises:
the first data cleaning module is used for cleaning the body temperature data according to a data format of a preset feature extraction algorithm to obtain the body temperature data conforming to the data format;
accordingly, the first feature extraction module comprises:
and the first feature extraction unit is used for calling the preset feature extraction algorithm to perform feature extraction on the body temperature data conforming to the data format to obtain the physiological feature sequence.
18. The apparatus of claim 15, wherein the apparatus further comprises:
the characteristic transformation module is used for collecting influence factors and carrying out characteristic transformation on the influence factors;
and the influence factor characteristic adding module is used for adding the influence factor characteristics obtained by characteristic conversion to the physiological characteristic sequence, and the influence factor characteristics are used for representing the influence factors which can influence the physiological cycle.
19. The apparatus of any of claims 14 to 18, further comprising:
the training data acquisition module is used for acquiring training data;
the second feature extraction module is used for extracting features of the obtained training data to obtain a feature sequence corresponding to the training data;
and the model construction module is used for carrying out model construction and training according to the characteristic sequence corresponding to the training data to obtain the physiological cycle prediction model.
20. The apparatus of claim 19, wherein the training data acquisition module comprises:
and the log file reading module is used for extracting the body temperature according to the body temperature records contained in the user log file and generating training data according to the extracted body temperature.
21. The apparatus of claim 19, wherein the apparatus further comprises:
the second sample classification module is used for carrying out sample classification on the training data according to preset classification conditions and determining a sample type identifier corresponding to the training data;
correspondingly, the device further comprises:
and the association storage module is used for associating and storing the sample type identifier and the physiological cycle prediction model.
22. The apparatus of claim 21, wherein the apparatus further comprises:
the second data cleaning module is used for cleaning the training data according to the data format of a preset feature extraction algorithm to obtain the training data conforming to the data format;
accordingly, the second feature extraction module comprises:
and the second feature extraction unit is used for calling the preset feature extraction algorithm to extract features of the training data conforming to the data format to obtain a feature sequence corresponding to the training data.
23. The apparatus of claim 19, wherein the model building module comprises:
the modeling unit is used for modeling the characteristic sequence corresponding to the training data by adopting a preset mathematical model to obtain a model to be trained;
the training unit is used for carrying out random initialization on the parameters of the model to be trained and carrying out iterative optimization on the parameters obtained by the random initialization by utilizing a maximum expectation algorithm;
and the model generation unit is used for judging that the converged model to be trained is the physiological cycle prediction model when the optimized parameters enable the model to be trained to be converged.
24. A user device, comprising:
a processor; and
memory having stored thereon computer readable instructions which, when executed by the processor, implement a method of predicting a female physiological cycle as defined in any one of claims 1 to 13.
25. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of predicting a female physiological cycle as set forth in any one of claims 1 to 13.
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 CN107252323A (en) | 2017-10-17 |
| CN107252323B true 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) |
Families Citing this family (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 |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1126508C (en) * | 1998-11-30 | 2003-11-05 | 光磊科技股份有限公司 | Physiological period indicator for women |
| JP5099751B2 (en) * | 2007-04-24 | 2012-12-19 | 公立大学法人会津大学 | Menstrual cycle estimation device and menstrual cycle estimation method |
| KR101043261B1 (en) * | 2009-01-23 | 2011-06-21 | 서강대학교산학협력단 | Prediction system for personally adjusted menstrual period or child-bearing period, and thereof calculation method |
| CN102929454A (en) * | 2011-08-12 | 2013-02-13 | 宸鸿科技(厦门)有限公司 | Capacitive touch panel and method for reducing visibility of metal conductors thereof |
| WO2015079526A1 (en) * | 2013-11-28 | 2015-06-04 | 楽天株式会社 | Information processing device, information processing method, and information processing program |
| CN104714669A (en) * | 2013-12-14 | 2015-06-17 | 宋齐 | Mouse capable of detecting female physiological cycle |
| CN104224239B (en) * | 2014-10-17 | 2016-09-28 | 肖南 | Determining female physiological periodicity monitoring method and system |
| WO2016132528A1 (en) * | 2015-02-20 | 2016-08-25 | 楽天株式会社 | Information processing device, 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 |
| CN105249937B (en) * | 2015-11-09 | 2019-02-05 | 上海温尔信息科技有限公司 | A kind of women natural contraception time monitoring method and device |
-
2017
- 2017-06-05 CN CN201710413820.7A patent/CN107252323B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107252323A (en) | 2017-10-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107252323B (en) | Method and device for predicting female physiological cycle and user equipment | |
| US20220129825A1 (en) | Method for estimating amount of task objects required to reach target completed tasks | |
| CN103488691A (en) | Task scheduling device and task scheduling method | |
| CN105488539B (en) | The predictor method and device of the generation method and device of disaggregated model, power system capacity | |
| US11425012B2 (en) | Dynamically generating visualizations of data based on correlation measures and search history | |
| CN112633573B (en) | Prediction method of active state and determination method of activity threshold | |
| JP2019534487A (en) | System and method for determining optimal strategy | |
| CN105892304B (en) | Curve data automatic interpretation method | |
| TW202022726A (en) | User admission risk determination method and device | |
| CN113641994B (en) | Data processing method and system based on graph data | |
| CN110766236A (en) | Power equipment state trend prediction method based on statistical analysis and deep learning | |
| CN110519263A (en) | Anti- brush amount method, apparatus, equipment and computer readable storage medium | |
| CN111694714A (en) | Many-core chip power consumption estimation method, device, equipment and readable storage medium | |
| CN112907064A (en) | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal | |
| US20230075453A1 (en) | Generating machine learning based models for time series forecasting | |
| CN113408210A (en) | Deep learning based non-intrusive load splitting method, system, medium, and apparatus | |
| Zhang et al. | On the cost of interactions in interactive visual machine learning | |
| CN112783949A (en) | Human body data prediction method and device, electronic equipment and storage medium | |
| CN111598296A (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
| CN112036504A (en) | Temperature measurement model training method, device, equipment and storage medium | |
| CN114969543B (en) | Popularization method, popularization system, electronic equipment and storage medium | |
| CN113408730B (en) | Causal relationship generation method and device and electronic equipment | |
| CN112579657B (en) | Machine learning-based data tag identification and marking method and system | |
| CN111428742B (en) | Human health measurement method, device, computer equipment and storage medium | |
| CN116450667A (en) | Data query method, device, computer equipment and storage medium |
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 | ||
| 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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |