CN109276241B - Pressure identification method and equipment - Google Patents
Pressure identification method and equipment Download PDFInfo
- Publication number
- CN109276241B CN109276241B CN201811436841.1A CN201811436841A CN109276241B CN 109276241 B CN109276241 B CN 109276241B CN 201811436841 A CN201811436841 A CN 201811436841A CN 109276241 B CN109276241 B CN 109276241B
- Authority
- CN
- China
- Prior art keywords
- pressure
- hrv
- features
- preset
- pressure identification
- 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
- 238000000034 method Methods 0.000 title claims abstract description 91
- 238000000605 extraction Methods 0.000 claims abstract description 49
- 238000012360 testing method Methods 0.000 claims abstract description 42
- 238000010276 construction Methods 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 25
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013186 photoplethysmography Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 abstract description 12
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 37
- 238000004364 calculation method Methods 0.000 description 11
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000017531 blood circulation Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 210000003403 autonomic nervous system Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 230000010247 heart contraction Effects 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 230000004089 microcirculation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000005622 photoelectricity Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 210000001013 sinoatrial node Anatomy 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02405—Determining heart rate variability
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The application discloses a pressure identification method, which comprises the steps of carrying out feature extraction on a test signal when the test signal is received, and obtaining HRV (high resolution video) features of correlation to be tested; calculating a pressure value of the HRV characteristic to be detected through a preset pressure identification model to obtain a target pressure value; comparing the target pressure value with a pressure degree grading rule, and determining a pressure grade corresponding to the target pressure value; the pressure identification method realizes pressure identification based on the HRV characteristics with certain correlation with pressure change, and greatly improves the pressure identification efficiency. The application also discloses a pressure identification device, a pressure identification device and a computer readable storage medium, all having the above beneficial effects.
Description
Technical Field
The application relates to the technical field of intelligent equipment, in particular to a pressure identification method, a pressure identification device, pressure identification equipment and a computer readable storage medium.
Background
Psychological stress is an important factor influencing human health, and when the psychological stress exceeds the psychological stress bearing capacity of an individual, diseases are caused to be high, and the human health is influenced. In real life, psychological stress is becoming a major factor affecting physical and mental health and high-quality life of people. The psychological stress needs to be quantitatively measured for effective diagnosis and intervention, but the degree of psychological stress of one person cannot be accurately evaluated by subjective emotion and experience of other people, and auxiliary judgment needs to be carried out through physical sign signals of the human body. On the other hand, with the development of wearable technology in recent years, a series of wearable devices such as smartwatches and smartbands are widely popularized, and it is becoming possible to collect personal physiological information by means of the wearable devices, and it is feasible and widely paid attention to the automatic detection of psychological stress by means of technical means. In the fields of education, medical treatment and special fields, doctors and patients can be objectively and conveniently helped to evaluate psychological pressure, and the purposes of effectively assisting diagnosis of the doctors and recovery of the patients are achieved.
The basis for assessing the psychological stress is to accurately measure the psychological stress, and the current common method for testing the psychological stress is mainly a physiological measurement method, which is mainly used for assessing the health condition of people by applying a bioelectricity related technology and is a hot spot of current domestic and foreign research. The existing research shows that human sign signals contain rich emotional information, and have the characteristics of objectivity, authenticity and real-time monitoring, and correlation exists between the sign signals and psychological reactions, so that the feasibility and the effectiveness are realized by selecting the sign signals with good characteristics to comprehensively measure the psychological pressure.
HRV (Heart Rate Variability) refers to the small difference in the beat-to-beat interval, which results from the modulation of the sinoatrial node of the Heart by the autonomic nervous system, and varies in time with the change in the in vivo and in vitro environment, so that the beat interval typically varies and fluctuates by several tens of milliseconds. At present, the HRV-based pressure recognition method mainly calculates a large number of HRV features by acquiring physiological data in different degree environments, for example, acquiring electrocardiographic signals in relaxed, mild, moderate, and severe pressure environments, then establishes and trains a pressure recognition model by some machine learning methods, such as a support vector machine, and then recognizes pressure by the model. However, since the HRV features are various in types and large in number, the construction of the pressure identification model based on a large number of HRV features not only consumes a large amount of time in the model construction process, but also greatly reduces the efficiency of pressure identification based on the pressure identification model.
Therefore, how to provide a pressure identification method to effectively improve the pressure identification efficiency is an urgent problem to be solved by those skilled in the art.
Disclosure of Invention
The pressure identification method realizes pressure identification based on HRV characteristics having certain correlation with pressure change, and greatly improves pressure identification efficiency; another object of the present application is to provide a pressure identification device, a pressure identification apparatus, and a computer-readable storage medium, which also have the above-mentioned advantages.
In order to solve the above technical problem, the present application provides a pressure identification method, where the pressure identification method includes:
when a test signal is received, carrying out feature extraction on the test signal to obtain HRV (relevance-variable) features to be tested;
calculating a pressure value of the HRV characteristic to be detected through a preset pressure identification model to obtain a target pressure value;
and comparing the target pressure value with a pressure degree grading rule, and determining the pressure grade corresponding to the target pressure value.
Preferably, the process of constructing the preset pressure identification model includes:
carrying out feature extraction on sample signals under different pressure levels to obtain a plurality of HRV features;
extracting relevant HRV characteristics from all the HRV characteristics through a characteristic extraction algorithm;
constructing a model according to the correlation HRV characteristics to obtain the preset pressure identification model;
and calculating according to the preset pressure identification model to obtain the pressure degree grading rule.
Preferably, the performing feature extraction on the sample signals at different pressure levels to obtain a plurality of HRV features includes:
and performing feature extraction on the sample signals under different pressure levels by a photoplethysmography to obtain the multiple HRV features.
Preferably, after the performing feature extraction on the sample signals at different pressure levels to obtain a plurality of HRV features, the method further includes:
and preprocessing each HRV characteristic to obtain a processed HRV characteristic.
Preferably, the extracting, by a feature extraction algorithm, relevant HRV features from all the HRV features specifically includes:
standardizing each HRV characteristic to obtain a standard HRV characteristic;
extracting the relevant HRV features in all the standard HRV features by the feature extraction algorithm.
Preferably, the extracting, by the feature extraction algorithm, the relevant HRV features in all the standard HRV features includes:
processing the standard HRV characteristics of the same type under each adjacent pressure grade through the T-test analysis algorithm to obtain a plurality of significance factors;
and selecting the standard HRV characteristics with the significance factor lower than a preset significance factor as the related HRV characteristics.
Preferably, the constructing a model according to the correlation HRV feature to obtain the preset pressure identification model includes:
calculating and obtaining a weight coefficient of each correlation HRV characteristic according to the significance factor;
and carrying out model construction on the related HRV characteristics according to the weight coefficient to obtain the preset pressure identification model.
Preferably, the step of obtaining the pressure degree classification rule according to the preset pressure identification model includes:
calculating pressure values of the HRV characteristics of the correlations through the preset pressure identification model to obtain the pressure values of the HRV characteristics of the correlations;
sequencing the pressure values in a descending order;
carrying out equipartition processing on all the sorted pressure values to obtain a preset number of pressure grading threshold values;
and constructing the pressure degree grading rule according to each pressure grading threshold value.
Preferably, the pressure identification method further includes:
and correcting the pressure degree grading rule according to the target pressure value and the pressure grade corresponding to the target pressure value to obtain the corrected pressure degree grading rule.
In order to solve the above technical problem, the present application provides a pressure identification device, which includes:
the test feature extraction module is used for extracting the test signal features when a test signal is received to obtain the HRV (heart rate variability) features of the correlation to be tested;
the pressure value calculation module is used for calculating the pressure value of the HRV characteristic to be detected through a preset pressure identification model to obtain a target pressure value;
and the pressure grade determining module is used for comparing the target pressure value with a pressure degree grading rule and determining the pressure grade corresponding to the target pressure value.
In order to solve the above technical problem, the present application provides a pressure identification apparatus, which includes:
a memory for storing a computer program;
a processor for implementing the steps of any of the above-described pressure identification methods when executing the computer program.
In order to solve the above technical problem, the present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of any one of the above pressure identification methods.
The pressure identification method comprises the steps of extracting test signal characteristics when a test signal is received, and obtaining correlation HRV characteristics to be tested; calculating a pressure value of the HRV characteristic to be detected through a preset pressure identification model to obtain a target pressure value; and comparing the target pressure value with a pressure degree grading rule, and determining the pressure grade corresponding to the target pressure value.
Therefore, when the pressure identification method provided by the application is used for carrying out pressure identification on the obtained test signal, firstly, the test signal is subjected to feature extraction to obtain the HRV feature which has larger correlation with the pressure change of the human body, namely the HRV feature to be detected, and further, the HRV feature to be detected is input into a preset pressure identification model for carrying out pressure identification. In addition, because the preset pressure identification model is used for realizing pressure identification by calculating the extracted HRV characteristics of the correlation to be detected, it is conceivable that the construction process of the preset pressure identification model is also obtained by constructing based on the HRV characteristics of the sample correlation, rather than realizing model construction through all the HRV characteristics, and therefore, the model construction time is greatly shortened.
The pressure identification device, the equipment and the computer readable storage medium provided by the application all have the beneficial effects, and are not described again.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of a pressure identification method provided in the present application;
fig. 2 is a schematic flow chart of a preset pressure identification model construction method provided in the present application;
fig. 3 is a schematic flow chart of a pressure level classification rule obtaining method provided in the present application;
FIG. 4 is a flow chart of a pressure identification model construction provided herein;
FIG. 5 is a flow chart illustrating a test of a pressure identification model provided herein;
FIG. 6 is a flow chart illustrating a modification of a pressure identification model provided herein;
fig. 7 is a schematic structural diagram of a pressure identification device provided in the present application;
fig. 8 is a schematic structural diagram of a pressure identification device provided in the present application.
Detailed Description
The core of the application is to provide a pressure identification method, the pressure identification method realizes pressure identification based on HRV characteristics having certain correlation with pressure change, and the pressure identification efficiency is greatly improved; another core of the present application is to provide a pressure identification device, a pressure identification apparatus, and a computer-readable storage medium, which also have the above-mentioned advantages.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the existing pressure identification method based on the HRV, as the HRV features are various in types and large in quantity, the pressure identification model is constructed based on a large number of HRV features, so that a large amount of time is consumed in the model construction process, and the efficiency of pressure identification based on the pressure identification model is greatly reduced. Therefore, in order to solve the above problems, the present application provides a pressure identification method, which implements pressure identification based on an HRV feature having a certain correlation with a pressure change, and greatly improves pressure identification efficiency.
Referring to fig. 1, fig. 1 is a schematic flow chart of a pressure identification method provided in the present application, where the pressure identification method may include:
s101: when a test signal is received, carrying out feature extraction on the test signal to obtain HRV (relevance-variable-V) features to be tested;
the method aims to extract and obtain the HRV characteristics of the correlation to be tested in the test signal. Specifically, after the test signal is received, all HRV features do not need to be extracted from the test signal, and only the to-be-tested correlation HRV features need to be extracted. The HRV characteristic to be measured is an HRV characteristic most related to pressure change, that is, an HRV characteristic having a strong pressure correlation. Therefore, subsequent pressure identification can be realized based on the HRV characteristics of the correlation to be detected.
In addition, any one of the prior art can be adopted for the feature extraction method, and the extraction of the HRV feature to be measured can be realized, which is not limited in the present application.
S102: calculating a pressure value of the HRV characteristic to be measured through a preset pressure identification model to obtain a target pressure value;
specifically, in this step, a pressure value of the to-be-measured correlation HRV feature is calculated by using a pre-constructed pressure identification model, that is, the preset pressure identification model, to obtain a corresponding pressure value, that is, the target pressure value.
The preset pressure identification model can be constructed based on a large amount of sample data, and the specific construction method can adopt any one of the prior art, which is not limited in the application. However, it should be noted that, because the preset pressure identification model in this step is to perform pressure identification on the to-be-detected correlation HRV feature extracted and obtained in S101, sample data for implementing model construction is also the correlation HRV feature, and thus, model construction is implemented only based on the correlation HRV feature, and the model construction efficiency is greatly improved.
S103: and comparing the target pressure value with the pressure degree grading rule, and determining the pressure grade corresponding to the target pressure value.
Specifically, the step aims to compare the obtained target pressure value with the pressure degree grading rule, so as to determine the pressure grade of the tested person. The pressure degree grading rule defines the classification of pressure grades, wherein the pressure grades corresponding to different pressure value stages are defined.
According to the pressure identification method, when the obtained test signal is subjected to pressure identification, the test signal is subjected to feature extraction firstly to obtain the HRV feature with large correlation with human body pressure change, namely the HRV feature to be detected, and further the HRV feature to be detected is input into a preset pressure identification model to be subjected to pressure identification. In addition, because the preset pressure identification model is used for realizing pressure identification by calculating the extracted HRV characteristics of the correlation to be detected, it is conceivable that the construction process of the preset pressure identification model is also obtained by constructing based on the HRV characteristics of the sample correlation, rather than realizing model construction through all the HRV characteristics, and therefore, the model construction time is greatly shortened.
On the basis of the above embodiments, please refer to fig. 2, and fig. 2 is a schematic flow chart of a preset pressure identification model construction method provided in the present application. As a preferred embodiment, the process of constructing the preset pressure identification model may include:
s201: carrying out feature extraction on sample signals under different pressure levels to obtain a plurality of HRV features;
firstly, a sample signal is required to be collected for model training, wherein the sample signal is a sample signal under different pressure environments, such as sample signals under various environments of relaxation, mild pressure, moderate pressure, severe pressure and the like, namely the sample signals under different pressure levels; further, feature extraction can be performed on each sample signal, so that a large number of HRV features can be obtained.
In the present application, the number of HRV features is not specifically limited, but the higher the number of HRV features, the higher the recognition accuracy of the pressure recognition model.
In addition, as for the type selection of the sample signal and the extraction mode of the HRV feature, any mode in the prior art can be adopted, and the specific implementation mode does not affect the implementation of the technical scheme, and the obtained sample signal can be used to extract the HRV feature, and further, the corresponding acquisition mode and the extraction mode of the HRV feature can be selected according to the type of the sample signal.
Preferably, the extracting the features of the sample signals at different pressure levels to obtain the plurality of HRV features may include extracting the features of the sample signals at different pressure levels by photoplethysmography to obtain the plurality of HRV features.
Specifically, the present application provides a more specific method for extracting a sample signal, which is implemented by the above-mentioned photoplethysmography (PPG). PPG is a non-invasive method for detecting blood volume changes in living tissues by means of photoelectricity, and volume pulse blood flow contains important physiological information of many cardiovascular systems such as blood flow and also contains abundant microcirculation physiological and pathological information, so that the volume pulse blood flow can be acquired based on a corresponding PPG sensor, and further, the volume pulse blood flow can be used as a sample signal from which the HRV features are extracted.
Of course, the above-mentioned acquisition of the sample signal is only one embodiment provided in the present application, and the extraction of the HRV feature may also be implemented based on an Electrocardiograph (ECG). Specifically, the cardiac electrical signals may be acquired by the corresponding ECG sensors and used as sample signals to extract HRV features therefrom. The electrocardiosignals are important physical sign signals of a human body, have the characteristics of convenient acquisition and rich physiological information, have long use history and rich diagnosis experience, can effectively reflect a plurality of physiological information of the heart contraction, the blood vessel expansion pressure, the blood vessel elasticity and the like of the individual, and mean that the relevant condition of the individual psychological pressure can be reflected. The HRV characteristics are obtained and calculated from the electrocardiosignals, and the psychological pressure state can be quickly and clearly known through the analysis of the HRV characteristics, so that the method has higher application value in testing and researching the psychological pressure through the electrocardiosignal processing.
As a preferred embodiment, after the feature extraction is performed on the sample signals at different pressure levels to obtain a plurality of HRV features, the method may further include preprocessing each HRV feature to obtain a processed HRV feature.
Specifically, because the directly acquired sample signals may be interfered in different degrees, and thus, the later-stage data calculation is affected, in order to further ensure the accuracy of the constructed pressure identification model, after extracting and obtaining each HRV feature, the HRV feature may be preprocessed, the preprocessing process is an interference filtering process, the interference types may include baseline drift, power frequency interference, motion interference, and the like, and the commonly used interference filtering method may include filter filtering, empirical mode decomposition, wavelet transformation, and the like. And the specific implementation process of the method is set according to the actual situation. Further, subsequent data analysis and calculation can be performed based on the processed HRV features.
S202: extracting relevant HRV characteristics from all HRV characteristics through a characteristic extraction algorithm;
specifically, the step aims to extract the correlation HRV features based on a feature extraction algorithm, so that a subsequent pressure identification model can be constructed according to the correlation HRV features. For the above feature extraction algorithm, any algorithm capable of realizing data feature extraction in the prior art can be adopted, and the specific implementation manner does not affect the implementation of the technical scheme.
As a preferred embodiment, the extracting of the correlated HRV features from all HRV features by the feature extraction algorithm may specifically include performing normalization processing on each HRV feature to obtain a standard HRV feature; and extracting related HRV characteristics from all the standard HRV characteristics through a characteristic extraction algorithm.
Specifically, in order to eliminate the influence of individual differences on the classification result, each HRV feature may be normalized first during feature extraction, and any one of the prior art may be used for the normalization process. For example, a baseline signal characteristic elimination method can be adopted, firstly, a sample to be tested in a no-task and relaxed state is collected as a baseline signal, and further, in the subsequent signal processing and characteristic processing stage, HRV characteristics under different pressure levels are respectively divided by the baseline characteristics, so that the change of the HRV characteristic value in the sample signal caused by pressure can be obtained, and the accuracy of a pressure identification model and the accuracy of later-stage pressure identification can be further ensured.
Further, since the HRV features are normalized before feature extraction, the relevant HRV features can be extracted and obtained from all the standard HRV features in the feature extraction process.
Preferably, the extracting of the correlated HRV features from all the standard HRV features by the feature extraction algorithm may include processing the same type of standard HRV features at each adjacent pressure level by a T-test analysis algorithm to obtain a plurality of significance factors; and selecting the standard HRV characteristics with the significance factor lower than the preset significance factor as the related HRV characteristics.
The application provides a specific feature extraction mode, namely the feature extraction mode is realized based on a T-test analysis algorithm, and the T-test analysis algorithm can realize statistics of significance difference between two different groups. Specifically, after obtaining a large number of HRV features, the feature types of all the HRV features may be counted, and the HRV features may be classified into time-domain features, frequency-domain features, and nonlinear features. The time domain analysis mainly comprises two modes, namely a statistical analysis method and a geometric figure analysis method, wherein the statistical analysis method is mainly used for evaluating HRV characteristics by calculating related mathematical statistical indexes of RR intervals (among wave crests), including mean values, standard deviations, variances and the like of the RR intervals; the geometry analysis is to calculate the change of HRV characteristics by geometry analysis of the distribution of RR intervals. The frequency domain features are mainly 0-0.4Hz and may include three spectral components, namely high frequency components (HF, spectral peak around 0.25 Hz), low frequency components (LF, spectral peak around 0.1 Hz), and very low frequencies (VLF, spectral peak around 0.003-0.04 Hz). The nonlinear features may include Poincare scattergram extracted features (such as vector angle index and vector length index) and Lyaponov index, among others. Further, after the feature type statistics is completed, the T-test analysis can be performed on the HRV features of the same type under each adjacent pressure level.
For example, when a sample signal is collected, sample signals under four pressure environments of relaxed, mild, moderate and severe pressures are collected, ten types of HRV features including a mean value, a standard deviation, a variance, a geometric figure, a high-frequency component, a low-frequency component, a very low-frequency component, a vector angle index, a vector length index and a Lyaponov index are extracted from the sample signals, and when T-test analysis is performed, T-test analysis can be performed on the mean value under the relaxed state and the mild pressure state, the mean value under the mild pressure state and the moderate pressure state, and the mean value under the moderate pressure state and the severe pressure state, so that three corresponding significance factors can be obtained. Furthermore, T test analysis of other types of HRV characteristics can be realized according to the method, and corresponding significance factors are obtained.
The significance factor represents the significance difference between two different populations, and the smaller the value of the significance factor is, the more relevant the HRV characteristic corresponding to the significance factor is to the change of the pressure. Therefore, the HRV features with the significance factor lower than the preset criterion, that is, lower than the preset significance factor, may be selected as the correlation HRV features, and the subsequent pressure identification model is constructed based on the correlation HRV features.
Based on the above example, when the acquired sample signal is divided into four pressure levels, there are 3 corresponding significance factors obtained, at this time, the average value of the three may be taken to compare with the preset significance factor, the minimum value may also be taken to compare with the preset significance factor, 3 preset significance factors for different adjacent pressure levels may also be set to compare respectively, when two or more of the significance factors are lower than the corresponding preset significance factors, the corresponding HRV characteristic may be taken as the correlated HRV characteristic, or any other implementation manner may also be adopted, which does not affect the implementation of the present technical solution regardless of the manner adopted.
It should be noted that, for the specific value of the preset significance factor, the application is not limited, and the user may autonomously set the value based on the number of the HRV features and the requirement on the accuracy of the pressure recognition model, for example, the value may be 0.05 or 0.01.
S203: constructing a model according to the correlation HRV characteristics to obtain a preset pressure identification model;
specifically, after obtaining the correlation HRV features, the pressure identification model may be constructed, and for the specific construction process, reference may be made to the construction method of the pressure identification model for all the HRV features in the prior art. In the application, the construction of the preset pressure identification model is realized only through the part of HRV characteristics with stronger pressure correlation, and the model construction efficiency and the later pressure identification efficiency are effectively improved. Therefore, the construction of the preset pressure identification model is completed, and the pressure identification can be realized based on the preset pressure identification model in the later stage.
Preferably, the model construction according to the correlation HRV features, and the obtaining of the preset pressure identification model may include obtaining a weight coefficient of each correlation HRV feature by calculation according to a significance factor; and carrying out model construction on the correlation HRV characteristics according to the weight coefficient to obtain a preset pressure identification model.
Specifically, since the preset pressure identification model is constructed and obtained based on various kinds of correlation HRV features, the weight coefficients of various kinds of HRV features need to be calculated, the weight coefficients represent the importance degree of a plurality of quantities in the total quantity, and the calculation mode can be realized based on the significance factor obtained in S202. Also for the example in S202, the inverse of the mean of the three significance factors of the HRV-related feature may be taken as the weighting factor of the HRV-related feature, and the greater the variation between different pressure levels, the smaller the significance factor, the greater the corresponding weighting factor. Further, after the weight coefficients of various kinds of correlation HRV features are obtained, all the correlation HRV features may be linearly combined to a certain extent based on the weight coefficients to obtain corresponding preset pressure identification models.
S204: calculating according to a preset pressure identification model to obtain a pressure degree grading rule;
specifically, after the preset pressure identification model is obtained, the corresponding pressure degree grading rule can be calculated and obtained according to the preset pressure identification model, so that the pressure degree grading rule is obtained, and when pressure identification is performed at a later stage, the pressure grade of the tested person can be determined based on the pressure degree grading rule.
Referring to fig. 3, fig. 3 is a schematic flow chart of a pressure degree classification rule obtaining method provided in the present application, and preferably, the obtaining of the pressure degree classification rule by calculation according to a preset pressure identification model may include:
s301: calculating the pressure value of each correlation HRV characteristic through a preset pressure identification model to obtain the pressure value of each correlation HRV characteristic;
s302: sequencing the pressure values in a descending order;
s303: carrying out equipartition processing on each sorted pressure value to obtain a predetermined number of pressure grading threshold values;
s304: and constructing a pressure degree grading rule according to each pressure grading threshold value.
Specifically, when the pressure degree classification rule is calculated based on the preset pressure identification model, pressure values of all correlation HRV characteristics can be calculated through the preset pressure identification model, and corresponding pressure values are obtained; further, the pressure values are sorted in the order from small to large, and the sorted pressure values are equally divided, where the results of the equally divided processing correspond to different pressure levels in S201, for example, when sample signals are collected, the collected sample signals are sample signals under four pressure environments of relaxed pressure, mild pressure, moderate pressure and severe pressure, and when the pressure values are equally divided, all the sorted pressure values can be equally divided by four to obtain 3 pressure classification threshold values, so that a pressure degree classification rule can be constructed and obtained according to the three pressure classification threshold values.
It should be noted that, the above example of the pressure level division is only a preferred embodiment provided in the present application, and is not unique, that is, the present application does not specifically limit the specific values of the predetermined number, and may also perform more detailed division on the pressure level. In addition, the arrangement order of the pressure values can also be arranged in the descending order, and the implementation of the technical scheme is not influenced.
It should be further noted that the steps from S201 to S204 implement the construction of the pressure identification model and the acquisition of the corresponding pressure degree classification rule, the above process is only executed once, and only needs to be directly invoked when performing pressure identification based on the pressure identification model and the pressure degree classification rule in the following.
In practical application, based on the above pressure identification method, the higher the consistency of the test signal and the sample signal during modeling, the higher the accuracy. However, in general, the real stress situation is not the same as the stress degree grading in the experiment, and there are some problems that the real stress data is not acquired at all or is inaccurate, or even the data amount is not enough, so the sample signal in the model construction is limited or even incomplete, for example, the sample signal in the severe stress state acquired in the experiment environment is not basically the maximum stress of the individual, because it is not known at all what the upper stress limit of the individual is, and the acquired sample signal is only the severe stress data in other states; similarly, the sample signal collected in the relaxed state is not the sample signal of the most relaxed state of the individual, but is also the relaxation data relative to the rest of the state. Therefore, the preset pressure recognition model obtained above does not sufficiently reflect the pressure level in the real situation. In addition, because the pressure level of each person is different, all individual pressure levels are detected by using the same preset pressure identification model, the difference of the pressure levels among individuals is ignored, and the accuracy is not high.
Therefore, in order to solve the above problem, on the basis of the above embodiments, as a preferred embodiment, the pressure identification method may further include correcting the pressure degree classification rule according to the target pressure value and the corresponding pressure level thereof, so as to obtain a corrected pressure degree classification rule.
Specifically, in order to further ensure the accuracy of the recognition result obtained by performing pressure recognition based on the pressure recognition model, the pressure recognition model may be continuously updated and corrected, that is, the pressure classification threshold is updated, that is, the pressure degree classification rule is updated. Specifically, after the target pressure value and the corresponding pressure level are obtained, the pressure level classification rule may be modified based on the target pressure value and the corresponding pressure level, so as to obtain a modified pressure level classification rule. The self-updating of the pressure identification model further ensures the accuracy of the pressure identification result, and meanwhile, the pressure identification mode can reflect the personal pressure level more truly and has more individuation.
Further, a more specific model self-correction method is provided below.
In this embodiment, taking dividing four different pressure classes as an example, that is, the number of the pressure classification threshold values is 3, that is, the predetermined number is 3, and the pressure degree classification rule is modified according to the target pressure value, and a specific implementation process of obtaining the modified pressure degree classification rule is as follows:
according to research, the HRV characteristics related to pressure significance have a linear or approximately linear relationship with pressure, namely, the HRV characteristics change more when the pressure is higher, and the pressure identification model has a linear relationship with the HRV characteristics, so that the pressure grading threshold has a linear relationship. Therefore, when the number of the pressure classification threshold values is 3, only two pressure classification threshold values of the minimum and the maximum need to be calculated, and then the second pressure classification threshold value is calculated by averaging the minimum pressure classification threshold value and the maximum pressure classification threshold value, so that the correction of the pressure degree classification rule is completed.
In general, for the above four examples of the classification of different pressure levels, the above model modification process is not entered during mild pressure and moderate pressure, and only when the individual state is detected to be a relaxed state or a severe pressure state, the pressure classification threshold value is updated and modified based on the corresponding target pressure value.
According to the pressure identification method, after pressure identification is carried out based on the preset pressure identification model, self-correction of the preset pressure identification model can be further carried out, the accuracy of the pressure identification model is effectively improved, and meanwhile the accuracy of a pressure identification result is also improved.
On the basis of the above embodiments, the present application provides a more specific pressure identification method.
1. The construction process of the pressure identification model comprises the following steps:
referring to fig. 4, fig. 4 is a flow chart illustrating a construction process of a preset pressure recognition model according to the present application.
Firstly, four physiological signals with different pressure degrees, namely sample signals (such as electrocardio or pulse wave data and the like) can be acquired through a relevant experimental method, wherein the pressure degrees can comprise a relaxed state, mild pressure, moderate pressure and severe pressure; after physiological signals of a plurality of individuals are obtained, the HRV characteristics can be extracted through an ECG sensor or a PPG sensor, in the extraction process, the extracted HRV characteristics can be subjected to distortion-free amplification through an amplifying circuit, and an analog signal is converted into a digital signal which can be calculated by a processor through an A/D conversion circuit. When the sensor is not integrated with an A/D conversion circuit, an additional A/D converter can be added to realize the conversion process of the digital signal.
Further, the extracted HRV features are preprocessed to filter interference signals.
Further, performing classification calculation and standardization processing on the preprocessed HRV characteristics, performing statistical analysis on the standardized HRV characteristics to obtain significance factors and weight coefficients corresponding to various HRV characteristics, and selecting the HRV characteristics with the significance factors lower than preset significance factors as related HRV characteristics f 1 ，f 2 ，…，f m And the pressure recognition model is used as an input characteristic of the pressure recognition model.
Further, linear combination is performed on the correlation HRV characteristics to a certain degree, and then a corresponding pressure identification model can be obtained:
wherein, w total ＝w coef1 +w coef2 +…+w coefm ；w coef1 For the HRV feature f of correlation 1 Corresponding weight coefficient, w coef2 For the HRV feature f of correlation 2 Corresponding weight coefficient, w coefm For the HRV feature f of correlation m The corresponding weight coefficient, SV, represents the pressure value.
Wherein if the HRV correlation and the pressure exhibit positive correlation (i.e., the greater the pressure, the greater the signature), the sign of the coefficient is positive; if the HRV signature of the correlation exhibits a negative correlation with pressure (i.e., the greater the pressure, the smaller the signature), the sign of the coefficient is negative.
Further, based on the pressure recognition model, pressure value calculation is performed on all selected correlation HRV characteristics to obtain corresponding pressure values, all the pressure values are ranked, and three quartiles are calculated to serve as pressure classification threshold values, namely a first pressure classification threshold value th1, a second pressure classification threshold value th2 and a third pressure classification threshold value th3, so that corresponding pressure degree classification rules can be obtained:
the light state: SV < th 1;
mild stress: th1 is less than or equal to SV < th 2;
moderate pressure: th2 is less than or equal to SV < th 3;
severe stress: th3 is less than or equal to SV;
therefore, the construction of the pressure identification model and the acquisition of the pressure degree grading rule are completed.
It should be noted that, the above pressure identification model is constructed only once, so that the sample data thereof needs to be as accurate as possible, and the data size needs to be as large as possible, so as to ensure the accuracy of the pressure identification model.
2. The testing process based on the pressure identification model comprises the following steps:
referring to fig. 5, fig. 5 is a flowchart illustrating a testing process of a pressure identification model according to the present application.
Specifically, the testing process of the pressure identification model is partially similar to the building process, such as the signal acquisition and preprocessing process, and meanwhile, the pressure identification model is established, and the functional descriptions of the pressure identification model corresponding to different modules are as follows:
firstly, because the HRV characteristics with the strongest pressure correlation are counted in the construction stage of the pressure identification model, the test process only needs to calculate the HRV characteristics with the strongest pressure correlation, and other characteristics do not need to be calculated. Further, after preprocessing of the correlation HRV characteristics is completed, pressure value calculation can be performed on the correlation HRV characteristics through a pressure identification model, a corresponding target pressure value is obtained, and the target pressure value is compared with a pressure degree grading rule so as to identify and determine the current pressure state of the corresponding individual.
In addition, the testing process of the pressure identification model can not only include pressure identification in practical application, but also include a verification process of the pressure identification model in a development stage, and the difference is that the data verified in the development stage is labeled data, namely data with known data types, and the pressure identification model can be verified and optimized through feedback of results.
3. And (3) a correction process of the pressure identification model:
referring to fig. 6, fig. 6 is a flowchart illustrating a modification of a pressure identification model according to the present application.
In the pressure identification practical application, when the target pressure value SV > th3 is obtained through calculation, the target pressure value is added to the severe pressure database DB2, and when the newly added data amount reaches a predetermined number, for example, the predetermined number is set to 100, the lower quartile of the severe pressure database DB2 is recalculated, that is, all the data in the DB2 are arranged from small to large and divided into four equal parts, and the data at the 25% position is used as a new third pressure classification threshold value th 3. When the data in the DB2 exceeds the maximum capacity, the newly added data is replaced with the oldest data, or one of the data is randomly replaced.
Similarly, when SV < th1, the target pressure value is added to the relaxation state database DB1, and when the newly added data amount reaches a predetermined number, also taking the predetermined number as an example of 100, the upper quartile of the relaxation state database DB1 is recalculated, that is, all the data in DB1 are arranged from small to large and divided into four equal parts, the data at the 75% position is used as the new first pressure classification threshold th 1. When the data in DB1 exceeds the maximum capacity, the newly added data is replaced with the oldest data, or one of the data is randomly replaced.
It should be noted that, in the above updating process of the pressure classification threshold, the upper quartile instead of the maximum value in DB1 is used as the first pressure classification threshold th1, and the lower quartile instead of the minimum value in DB2 is used as the third pressure classification threshold th3, mainly considering that the maximum value is easily affected and easily changed, but the pressure classification threshold needs to be updated stably and the updating can be performed only if there is a certain changed data amount, so that the accuracy and stability of the pressure identification model can be ensured. Of course, the implementation is not limited to the use of quartiles, and may be replaced with octants or the like.
Further, the updated second pressure classification threshold value th2 can be obtained by averaging the updated first pressure classification threshold value th1 and the updated third pressure classification threshold value th3, and thus, the pressure degree classification rule is corrected.
To solve the above problem, please refer to fig. 7, fig. 7 is a schematic structural diagram of a pressure identification device provided in the present application, where the pressure identification device may include:
the test feature extraction module 1 is used for extracting the test signal features when a test signal is received, and obtaining the HRV (heart rate variability) features of the correlation to be tested;
the pressure value calculation module 2 is used for calculating a pressure value of the HRV characteristic to be measured through a preset pressure identification model to obtain a target pressure value;
and the pressure grade determining module 3 is used for comparing the target pressure value with a pressure degree grading rule and determining the pressure grade corresponding to the target pressure value.
As a preferred embodiment, the pressure identification apparatus may further include a model construction module, and the model construction module may include:
the sample characteristic extraction unit is used for extracting characteristics of sample signals under different pressure levels to obtain a plurality of HRV characteristics;
the sample feature selection unit is used for extracting related HRV features from all the HRV features through a feature extraction algorithm;
the identification model construction unit is used for constructing a model according to the correlation HRV characteristics to obtain the preset pressure identification model;
and the pressure degree grading rule obtaining unit is used for calculating and obtaining the pressure degree grading rule according to the preset pressure identification model.
As a preferred embodiment, the sample feature extraction unit may be specifically configured to perform feature extraction on sample signals at different pressure levels by a photoplethysmography method to obtain a plurality of HRV features.
As a preferred embodiment, the model building module may further include:
and the characteristic preprocessing unit is used for preprocessing each HRV characteristic to obtain the processed HRV characteristic.
As a preferred embodiment, the sample feature selecting unit may specifically include:
the characteristic standardization subunit is used for carrying out standardization processing on each HRV characteristic to obtain a standard HRV characteristic;
a sample feature selection subunit, configured to extract, by the feature extraction algorithm, the relevant HRV features from all the standard HRV features.
As a preferred embodiment, the sample feature selection subunit may be specifically configured to process, through a T-test analysis algorithm, the same type of standard HRV features under each adjacent pressure level to obtain a plurality of significance factors; and the characteristic selection submodule is used for selecting the standard HRV characteristic with the significance factor lower than the preset significance factor as the related HRV characteristic.
As a preferred embodiment, the identification model building unit may be specifically configured to obtain a weight coefficient of each correlation HRV feature according to the significance factor; and carrying out model construction on the correlation HRV characteristics according to the weight coefficient to obtain a preset pressure identification model.
As a preferred embodiment, the pressure degree classification rule obtaining unit may be specifically configured to calculate a pressure value of each correlation HRV feature through a preset pressure identification model, so as to obtain the pressure value of each correlation HRV feature; sequencing the pressure values in a descending order; carrying out equipartition processing on each sorted pressure value to obtain a predetermined number of pressure grading threshold values; and constructing a pressure degree grading rule according to each pressure grading threshold value.
As a preferred embodiment, the pressure identification means may further include:
and the pressure degree grading rule correcting module is used for correcting the pressure degree grading rule according to the target pressure value and the pressure grade corresponding to the target pressure value to obtain the corrected pressure degree grading rule.
For the introduction of the apparatus provided in the present application, please refer to the above method embodiments, which are not described herein again.
To solve the above problem, please refer to fig. 8, fig. 8 is a schematic structural diagram of a pressure identification device provided in the present application, where the pressure identification device may include:
a memory 11 for storing a computer program;
the processor 12, when executing the computer program, may implement the steps of any of the above-described pressure identification methods.
For the introduction of the device provided in the present application, please refer to the above method embodiment, which is not described herein again.
To solve the above problem, the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program can implement the steps of any one of the above pressure identification methods when executed by a processor.
The computer-readable storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
For the introduction of the computer-readable storage medium provided in the present application, please refer to the above method embodiments, which are not described herein again.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The pressure identification method, apparatus, device and computer readable storage medium provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and these improvements and modifications also fall into the elements of the protection scope of the claims of the present application.
Claims (7)
1. A method of pressure identification, comprising:
when a test signal is received, carrying out feature extraction on the test signal to obtain a correlation Heart Rate Variability (HRV) feature to be tested;
calculating a pressure value of the HRV characteristic to be measured through a preset pressure identification model to obtain a target pressure value;
comparing the target pressure value with a pressure degree grading rule, and determining a pressure grade corresponding to the target pressure value;
the construction process of the preset pressure identification model comprises the following steps:
carrying out feature extraction on sample signals under different pressure levels to obtain a plurality of HRV features;
extracting relevant HRV characteristics from all the HRV characteristics through a characteristic extraction algorithm;
carrying out model construction according to the correlation HRV characteristics to obtain the preset pressure identification model;
calculating according to the preset pressure identification model to obtain the pressure degree grading rule;
wherein, the step of obtaining the pressure degree grading rule according to the preset pressure identification model comprises the following steps:
calculating pressure values of the HRV characteristics of the correlations through the preset pressure identification model to obtain the pressure values of the HRV characteristics of the correlations;
sequencing the pressure values in a descending order;
carrying out equipartition processing on all the sorted pressure values to obtain a preset number of pressure grading threshold values;
constructing the pressure degree grading rule according to each pressure grading threshold value;
wherein, still include:
and correcting the pressure degree grading rule according to the target pressure value and the pressure grade corresponding to the target pressure value to obtain the corrected pressure degree grading rule.
2. The pressure identification method of claim 1, wherein the performing feature extraction on the sample signals at different pressure levels to obtain a plurality of HRV features comprises:
and performing feature extraction on the sample signals under different pressure levels by a photoplethysmography to obtain the multiple HRV features.
3. The pressure identification method of claim 1, wherein after the extracting the features of the sample signals at different pressure levels to obtain a plurality of HRV features, the method further comprises:
and preprocessing each HRV characteristic to obtain a processed HRV characteristic.
4. The pressure identification method as claimed in claim 1, wherein the extracting relevant HRV features in all the HRV features by a feature extraction algorithm specifically comprises:
standardizing each HRV characteristic to obtain a standard HRV characteristic;
extracting the relevant HRV features in all the standard HRV features by the feature extraction algorithm.
5. The pressure identification method of claim 4, wherein said extracting the relevant HRV features in all of the standard HRV features by the feature extraction algorithm comprises:
processing the standard HRV characteristics of the same type under each adjacent pressure grade through a T test analysis algorithm to obtain a plurality of significance factors;
and selecting the standard HRV characteristics with the significance factor lower than a preset significance factor as the related HRV characteristics.
6. The pressure identification method of claim 5, wherein the model building according to the HRV correlation features to obtain the preset pressure identification model comprises:
calculating and obtaining a weight coefficient of each correlation HRV characteristic according to the significance factor;
and carrying out model construction on the related HRV characteristics according to the weight coefficient to obtain the preset pressure identification model.
7. A pressure identification device, comprising:
a memory for storing a computer program;
processor for implementing the steps of the pressure identification method according to any of claims 1 to 6 when executing said computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811436841.1A CN109276241B (en) | 2018-11-28 | 2018-11-28 | Pressure identification method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811436841.1A CN109276241B (en) | 2018-11-28 | 2018-11-28 | Pressure identification method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109276241A CN109276241A (en) | 2019-01-29 |
| CN109276241B true CN109276241B (en) | 2022-08-09 |
Family
ID=65173559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811436841.1A Active CN109276241B (en) | 2018-11-28 | 2018-11-28 | Pressure identification method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109276241B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109924960A (en) * | 2019-01-31 | 2019-06-25 | 深圳市爱都科技有限公司 | A kind of blood oxygen saturation, the calculation method and wearable device of heart rate value and pressure rating |
| CN111493886A (en) * | 2019-01-31 | 2020-08-07 | 深圳市爱都科技有限公司 | Calculation method of blood oxygen saturation and pressure level and wearable device |
| CN110192872B (en) * | 2019-04-16 | 2020-09-11 | 华为技术有限公司 | Pressure evaluation calibration method and device and storage medium |
| CN110477932B (en) * | 2019-07-31 | 2022-04-15 | 商丘师范学院 | Student psychological stress assessment method and system based on Internet and cloud computing |
| CN110916635B (en) * | 2019-11-15 | 2022-06-07 | 北京点滴灵犀科技有限公司 | Psychological pressure grading and training method and device |
| CN111248928A (en) * | 2020-01-20 | 2020-06-09 | 北京津发科技股份有限公司 | Pressure identification method and device |
| CN111184521B (en) * | 2020-01-20 | 2023-01-06 | 北京津发科技股份有限公司 | Pressure identification bracelet |
| CN111407243B (en) * | 2020-03-23 | 2021-05-14 | 华南理工大学 | Pulse signal pressure identification method based on deep learning |
| CN112545501A (en) * | 2020-12-10 | 2021-03-26 | 徐岩 | Blood component concentration detection method and device |
| CN112545526A (en) * | 2020-12-10 | 2021-03-26 | 青岛大爱慈康智能医疗科技有限公司 | Electrocardiosignal detection method and device |
| CN113704201A (en) * | 2021-09-02 | 2021-11-26 | 国家电网有限公司信息通信分公司 | Log anomaly detection method and device and server |
| CN116327188B (en) * | 2023-05-29 | 2023-09-08 | 深圳市亿米生命科技有限公司 | Blood oxygen analysis method based on finger-clip type oximeter |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104983434A (en) * | 2015-06-17 | 2015-10-21 | 重庆邮电大学 | Multi-parameter mental stress assessment method based on analytical hierarchy method and device |
| CN106934199A (en) * | 2015-12-31 | 2017-07-07 | 深圳先进技术研究院 | A kind of psychological pressure appraisal procedure and device |
| CN106923846A (en) * | 2015-12-31 | 2017-07-07 | 深圳先进技术研究院 | A kind of psychological pressure assessment and reponse system |
| CN107595274A (en) * | 2017-09-27 | 2018-01-19 | 广州中科新知科技有限公司 | Back cushion based on HRV non-contact detection emotional stress |
| CN108577865A (en) * | 2018-03-14 | 2018-09-28 | 天使智心（北京）科技有限公司 | A kind of psychological condition determines method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9301695B2 (en) * | 2013-01-18 | 2016-04-05 | Fujitsu Limited | Stress model based on RR integral average |
-
2018
- 2018-11-28 CN CN201811436841.1A patent/CN109276241B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104983434A (en) * | 2015-06-17 | 2015-10-21 | 重庆邮电大学 | Multi-parameter mental stress assessment method based on analytical hierarchy method and device |
| CN106934199A (en) * | 2015-12-31 | 2017-07-07 | 深圳先进技术研究院 | A kind of psychological pressure appraisal procedure and device |
| CN106923846A (en) * | 2015-12-31 | 2017-07-07 | 深圳先进技术研究院 | A kind of psychological pressure assessment and reponse system |
| CN107595274A (en) * | 2017-09-27 | 2018-01-19 | 广州中科新知科技有限公司 | Back cushion based on HRV non-contact detection emotional stress |
| CN108577865A (en) * | 2018-03-14 | 2018-09-28 | 天使智心（北京）科技有限公司 | A kind of psychological condition determines method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109276241A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109276241B (en) | Pressure identification method and equipment | |
| Gierałtowski et al. | Multiscale multifractal analysis of heart rate variability recordings with a large number of occurrences of arrhythmia | |
| US9042973B2 (en) | Apparatus and method for measuring physiological signal quality | |
| KR100954817B1 (en) | System and method for testing blood vessel's health and stress through signal analysis of pluse wave | |
| KR102008196B1 (en) | Apparatus for generating of Potassium level determination model using ECG and method thereof | |
| US8280501B2 (en) | Systems and methods for quantitatively characterizing slow wave activities and states in sleep | |
| US20180233227A1 (en) | Systems and methods of analyte measurement analysis | |
| US20110201951A1 (en) | System for cardiac arrhythmia detection and characterization | |
| US11406304B2 (en) | Systems and methods for physiological sign analysis | |
| Zhang et al. | A novel encoding Lempel–Ziv complexity algorithm for quantifying the irregularity of physiological time series | |
| CN111248928A (en) | Pressure identification method and device | |
| CN112294272A (en) | Monitor and irregular pulse rate identification method thereof | |
| RU2016146176A (en) | METHOD AND SYSTEM OF NON-INVASIVE SCREENING ASSESSMENT OF PHYSIOLOGICAL PARAMETERS AND PATHOLOGIES | |
| Song et al. | Extracting features for cardiovascular disease classification based on ballistocardiography | |
| Poddar et al. | Heart rate variability based classification of normal and hypertension cases by linear-nonlinear method | |
| Alves et al. | Linear and complex measures of heart rate variability during exposure to traffic noise in healthy women | |
| CN113069091A (en) | Pulse condition classification device and method for PPG (photoplethysmography) signals | |
| Chou et al. | Modelling arterial blood pressure waveforms for extreme bradycardia and tachycardia by curve fitting with Gaussian functions | |
| JP2017042562A (en) | Music hearing experience presence/absence estimation method, music hearing experience presence/absence estimation device and music hearing experience presence/absence estimation program | |
| Lucena et al. | The performance of short-term heart rate variability in the detection of congestive heart failure | |
| Sujan et al. | Performance analysis for the Feature Extraction algorithm of an ECG signal | |
| Raab et al. | Large-scale dimension densities for heart rate variability analysis | |
| CN113679369B (en) | Evaluation method of heart rate variability, intelligent wearable device and storage medium | |
| Savostin et al. | DEVISING A METHOD FOR PREDICTING A BLOOD PRESSURE LEVEL BASED ON ELECTROCARDIOGRAM AND PHOTOPLETHYSMOGRAM SIGNALS. | |
| RU165751U1 (en) | ANALYZER OF FUNCTIONAL STATE OF THE ORGANISM |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190628 Address after: 518057 Yuanzheng Industrial Park, 4012 North Fifth Avenue, Bantian Street, Longgang District, Shenzhen City, Guangdong Province Applicant after: LAUNCH TECH Co.,Ltd. Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: HESVIT HEALTH TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |