CN114305345B - Pulse condition identification method, system, device and storage medium - Google Patents
Pulse condition identification method, system, device and storage medium Download PDFInfo
- Publication number
- CN114305345B CN114305345B CN202210142968.2A CN202210142968A CN114305345B CN 114305345 B CN114305345 B CN 114305345B CN 202210142968 A CN202210142968 A CN 202210142968A CN 114305345 B CN114305345 B CN 114305345B
- Authority
- CN
- China
- Prior art keywords
- pulse
- condition
- preset
- rate value
- pulse condition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a pulse condition identification method, a system, a device and a storage medium, wherein the method comprises the following steps: acquiring pulse wave signals, wherein the pulse wave signals comprise a single pulse wave and a plurality of continuous pulse waves; acquiring a first characteristic according to a plurality of continuous pulse waves, and acquiring a second characteristic according to a single pulse wave; carrying out first pulse condition identification according to the first characteristic to obtain a first identification result, wherein the first identification result is a first type pulse condition or a second type pulse condition; and carrying out second pulse condition identification according to the second characteristic to obtain a second identification result, wherein the second identification result is a third type pulse condition or a fourth type pulse condition. The invention extracts the first characteristic from a single pulse wave, extracts the second characteristic from a plurality of continuous pulse waves, characterizes the pulse beat rate and the second characteristic by the first characteristic to characterize the pulse beat amplitude, and enhances the characterization capability; by carrying out refined identification or classification on the pulse condition, the accuracy of pulse condition identification is improved. The method can be widely applied to the technical field of data classification.
Description
Technical Field
The present invention relates to the field of data classification technologies, and in particular, to a pulse condition identification method, system, device, and storage medium.
Background
In TCM, pulse condition identification mainly depends on finger feeling and is very dependent on personal experience of TCM. The modern Chinese medicine researches a pulse diagnosis instrument, the basic principle of which is that a sensor is used for collecting pulse wave signals and drawing pulse waveforms, and the pulse condition of the pulse wave is judged according to the pulse waveforms.
In the current automatic pulse condition identification method, a plurality of characteristics are mainly collected in a single pulse wave, and pulse condition identification is carried out based on the plurality of characteristics, wherein the pulse condition identification result comprises a plurality of different types of pulse conditions (such as false pulses and rapid pulses), and the characteristic characterization capability is not strong, so that the identification accuracy is influenced.
Disclosure of Invention
In order to solve at least one of the technical problems existing in the prior art to a certain extent, the invention aims to provide a pulse condition identification method, a pulse condition identification system, a pulse condition identification device and a pulse condition storage medium so as to improve identification accuracy.
In order to achieve the above object, an embodiment of the present invention provides a pulse condition recognition method, including the following steps:
acquiring pulse wave signals, wherein the pulse wave signals comprise a single pulse wave and a plurality of continuous pulse waves;
acquiring a first characteristic according to the plurality of continuous pulse waves, and acquiring a second characteristic according to the single pulse wave;
Performing first pulse condition identification according to the first characteristic to obtain a first identification result, wherein the first identification result is a first type pulse condition or a second type pulse condition;
performing second pulse condition identification according to the second characteristic to obtain a second identification result, wherein the second identification result is a third type pulse condition or a fourth type pulse condition;
wherein the first characteristic is a characteristic characterizing pulse beat rate and the second characteristic is a characteristic characterizing pulse beat amplitude.
In order to achieve the above object, an embodiment of the present invention further provides a pulse condition recognition system, including:
a signal acquisition module for acquiring pulse wave signals, the pulse wave signals comprising a single pulse wave and a plurality of continuous pulse waves;
the feature extraction module is used for acquiring first features according to the plurality of continuous pulse waves and acquiring second features according to the single pulse wave;
the first recognition module is used for carrying out first pulse condition recognition according to the first characteristics to obtain a first recognition result, wherein the first recognition result is a first type pulse condition or a second type pulse condition;
the second recognition module is used for carrying out second pulse condition recognition according to the second characteristics to obtain a second recognition result, wherein the second recognition result is a third type pulse condition or a fourth type pulse condition;
Wherein the first characteristic is a characteristic characterizing pulse beat rate and the second characteristic is a characteristic characterizing pulse beat amplitude.
In order to achieve the above object, an embodiment of the present invention further provides a pulse condition recognition device, including:
at least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to carry out the steps of the aforementioned method.
To achieve the above object, an embodiment of the present invention also proposes a storage medium for computer-readable storage, the storage medium storing one or more programs executable by one or more processors to implement the steps of the foregoing method.
The pulse condition identification method, the system, the device and the storage medium provided by the invention have the advantages that the first characteristic is extracted from a single pulse wave, the second characteristic is extracted from a plurality of continuous pulse waves, the pulse beat rate and the second characteristic are represented by the first characteristic, the pulse beat amplitude is represented by the first characteristic, and the representation capability is enhanced; the first pulse condition identification is carried out according to the first characteristic, the second pulse condition identification is carried out according to the second characteristic, and the refined identification or classification is carried out on the pulse condition through the first pulse condition identification and the second pulse condition identification, so that the accuracy of pulse condition identification is improved.
Drawings
FIG. 1 is a flow chart of steps of a pulse condition recognition method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps for performing a first pulse condition recognition according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a single pulse wave provided by an embodiment of the present invention;
FIG. 4 is a flowchart illustrating steps for performing a second pulse condition recognition according to an embodiment of the present invention;
FIG. 5 is a block diagram of a pulse condition recognition system according to an embodiment of the present invention;
fig. 6 is a block diagram of a pulse condition recognition device according to an embodiment of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the following description, suffixes such as "module", "part" or "unit" for representing elements are used only for facilitating the description of the present invention, and have no particular meaning in themselves. Thus, "module," "component," or "unit" may be used in combination.
As shown in fig. 1, the present embodiment provides a pulse condition identification method, which includes the following steps:
step S110: a pulse wave signal is acquired, the pulse wave signal comprising a single pulse wave and a plurality of successive pulse waves.
The waveform of pulse wave has close relation with the pulse feeling of traditional Chinese medicine, and the diagnosis of pulse feeling, i.e. pulse condition, of traditional Chinese medicine generally adopts a more classical pulse feeling finger method of 'single cunkou'. From a physiological and medical point of view, the pulse is driven by the heart and the blood follows a tortuous and lengthy path along the artery in the body before reaching the radial artery remote from the heart. Therefore, the pulse signals are affected by not only the heart condition but also the arterial vessel characteristics, blood flow parameters, muscles, skin and other factors. In traditional Chinese medicine, pulse condition identification mainly depends on finger feeling, but the traditional Chinese medicine relies on pulse information provided by fingers when a patient feels radial artery pulsation, and the pulse attribute identification only stays in the original visual concept, and more is based on years of clinical experience of doctors, and the subjective feeling of doctor's identification experience and pulse diagnosis is doped. Along with the development of science and technology, modern traditional Chinese medicine researches a pulse diagnosis instrument, which can collect and draw pulse signals into pulse waveforms and judge pulse conditions of the pulse waves according to the pulse waveforms.
In this embodiment, the pulse wave signal may be obtained by an existing pulse diagnosis apparatus, and the pulse wave signal may be an optoelectronic pulse wave signal, an ultrasonic pulse wave signal or a pressure pulse wave signal. The acquired pulse wave signals comprise a single pulse wave and a plurality of continuous pulse waves, wherein the single pulse wave refers to the waveform of the single pulse wave, and the plurality of continuous pulse waves refer to the waveforms of the plurality of continuous pulse waves.
Step S120: the first feature is acquired from a plurality of successive pulse waves and the second feature is acquired from a single pulse wave. Wherein the first characteristic is a characteristic characterizing pulse beat rate and the second characteristic is a characteristic characterizing pulse beat amplitude.
In this embodiment, the feature extraction is performed on a plurality of continuous pulses to obtain a first feature, where the first feature reflects the condition of the pulse beat rate, such as whether the pulse beat is rapid, whether the pulse beat is uniform, or whether the pulse beat is regular. By extracting features of the single pulse wave, a second feature is obtained, where the second feature reflects the condition of the pulse beat amplitude, such as the period of the pulse wave, the heights of the main wave, the tide wave and the counterpulsation wave in the pulse wave, the width of the main wave of the pulse wave, the width of the systolic period of the pulse wave, and the like.
Step S130: and carrying out first pulse condition identification according to the first characteristic to obtain a first identification result, wherein the first identification result is the first type pulse condition or the second type pulse condition.
In the prior art, a plurality of features are acquired and identified once based on the plurality of features, for example, feature vectors are formed by the acquired features, the feature vectors are input into an identification model for identification and classification, so that corresponding pulse types are identified, the identification results may include identification results with different dimensions, for example, the pulse of a patient is rapid and weak, the output result may be a false pulse or a number pulse, and thus the identification results are not accurate enough. For this reason, the present embodiment acquires the first feature and the second feature in different manners, and performs corresponding feature recognition for different features.
In some alternative embodiments, the first characteristic includes a pulse rate value and a continuous pulse period rate of change of adjacent two periods of the plurality of continuous pulse waves. Step S130 may further include:
s131, acquiring a plurality of continuous pulse period change rates in a preset time period.
S132, performing first pulse condition identification according to the pulse rate value and the continuous pulse period change rate to obtain a first identification result.
Pulse rate values are obtained by obtaining the number of pulse beats within a preset time (e.g., 1 minute). In pulse beating, there is a possibility that beat imbalance between adjacent pulse waves, that is, the periods of adjacent pulse waves are different, even a large difference, may reflect some problems of body functions, and thus a continuous pulse period change rate is introduced. In some alternative embodiments, the continuous pulse cycle rate is calculated as follows:
σ＝(t 1 -t 2 )/t 1
wherein t is 1 And t 2 For the period of any two adjacent pulse waves, t 1 At t 2 Is the next pulse wave period.
In some alternative embodiments, the first type of pulse condition includes a disease pulse, a promotion pulse, and a rapid pulse, and the second type of pulse condition includes a knot pulse, a slow pulse, and a slow pulse, as shown in fig. 2, step S132 may further include:
S1321, counting a first quantity, wherein the first quantity is the number that the absolute value of the continuous pulse period change rate is larger than a first preset value;
s1322, if the pulse rate value is larger than a first preset pulse rate value and the first quantity is smaller than a second preset value, judging that the pulse condition is a disease pulse;
s1323, if the pulse rate value is greater than or equal to the second preset pulse rate value and the first number is greater than or equal to the second preset value, judging that the pulse condition is pulse promotion;
s1324, if the pulse rate value is greater than the second preset pulse rate value and less than or equal to the first preset pulse rate value, and the first number is less than the second preset value, determining that the pulse condition is a pulse number;
s1325, if the pulse rate value is smaller than the second preset pulse rate value and the first quantity is larger than or equal to the second preset value, judging that the pulse condition is a knot pulse;
s1326, if the pulse rate value is greater than or equal to the third preset pulse rate value and less than the second preset pulse rate value, and the first quantity is less than the second preset value, determining that the pulse condition is a slow pulse;
s1327, if the pulse rate value is smaller than the third preset pulse rate value and the first quantity is smaller than the second preset value, judging that the pulse condition is a delayed pulse;
wherein the first preset pulse rate value is greater than the second preset pulse rate value and greater than the third preset pulse rate value.
In this embodiment, the first number n is counted first, where n is the number that the absolute value of the period change rate of the continuous pulse is greater than the first preset value, and when the absolute value of the period change rate is greater than 20%, the first number n is added by 1. Illustratively, the first preset pulse rate value is 110 times/min, the second preset pulse rate value is 90 times/min, and the third preset pulse rate value is 65 times/min.
When the pulse rate value is more than 110 times/min and n is less than 3, the pulse rate is regular, the continuous pulse period is basically equal, and the pulse condition is judged to be a disease pulse.
When the pulse rate value is greater than 90 times/min and n is greater than or equal to 3, the pulse period is unequal, and irregular intermittent or stopping pulse exists; the descending time is different, and the time is slow; the pulse condition is judged as promoting pulse.
When the pulse rate value is greater than 90 times/min and less than 110 times/min, and n is less than 3, the pulse rate is regular, and the continuous pulse periods are basically equal, the pulse condition is judged to be a number pulse.
When the pulse rate value is smaller than 90 times/min and n is larger than or equal to 3, indicating that the pulse period is unequal and the pulse wave has irregular stopping pulse, judging that the pulse condition is a knot pulse.
When the pulse rate value is greater than 65 times/min and less than 90 times/min, and n is less than 3, it indicates that the main peak included angle in the pulse is slightly wider and the descending slope is reduced, and then the pulse condition is determined to be slow.
When the pulse rate value is smaller than 65 times/min and n is smaller than 3, the pulse rate is regular but slow, and the continuous pulse period is basically the same, the pulse condition is judged to be the slow pulse.
Step S140: and carrying out second pulse condition identification according to the second characteristic to obtain a second identification result, wherein the second identification result is a third type pulse condition or a fourth type pulse condition.
The second characteristic is obtained through single pulse wave extraction, wherein the waveform of the single pulse wave is characterized by a waveform curve, the waveform curve comprises a first curve corresponding to a first period, and the first period belongs to the systolic period of the waveform curve. The second characteristic includes a total integrated area of the waveform curve, a shape characteristic of the waveform curve, and an integrated area of the first curve. The third category of pulse conditions includes large pulse and real pulse, and the fourth category of pulse conditions includes thin pulse and deficient pulse.
In some alternative embodiments, referring to fig. 3, the total integrated area E is the integrated area corresponding to the entire pulse wave. The section from the highest point of the main wave to the end point of the pulse wave is the systolic phase, and the last 1/3 line segment in the systolic phase is selected as a first curve, and the integral area corresponding to the first curve is delta. The shape characteristics of the waveform curve include tide wave, microblog wave, main wave height, main wave width, main wave rising time and the like. As shown in fig. 4, step S140 may further include steps S141-S143:
s141, determining that the pulse condition is a third type pulse condition or a fourth type pulse condition according to the total integral area, the shape characteristic and the integral area of the first curve.
In this embodiment, multiple features are used to comprehensively identify the condition of the pulse condition, for example, a multidimensional vector is constructed through multiple features, and classification and identification are performed based on the vector. Step S141 may further include steps S1411-S1413:
S1411, calculating a real pulse cumulative score and a virtual pulse cumulative score according to the total integral area, the shape characteristic and the integral area of the first curve.
In some alternative embodiments, the shape characteristics of the waveform profile include the width of the main preset height and the peak rise time, and step S1411 may further include steps A1-A2:
a1, dividing each second characteristic into a plurality of numerical value areas, determining the numerical value areas corresponding to the third type of pulse condition and the numerical value areas corresponding to the fourth type of pulse condition, and determining the scores corresponding to the numerical value areas.
A2, calculating the real pulse cumulative score and the imaginary pulse cumulative score according to the total integral area, the integral area of the first curve, the width of the main wave preset height, the peak rising time, the numerical region and the score corresponding to the numerical region.
The width of the main wave preset height is the corresponding width at the main wave preset height of the pulse wave; the peak rise time is the time from the initial point of the pulse wave to the highest point of the main wave.
In this embodiment, referring to FIG. 3, the width of the main preset height includes a w3/t width and a w5/t width. The highest point of the main wave is h, the w3/t width refers to the width corresponding to the main wave at the 2/3h height, and the w5/t width refers to the width corresponding to the main wave at the 4/5h height. The peak rise time ts is the time from the initial point of the pulse wave (e.g., origin 0 in fig. 3) to the highest point of the main wave.
S1412, if the real pulse cumulative score is greater than or equal to the imaginary pulse cumulative score, determining that the pulse condition is the third type pulse condition.
S1413, if the accumulated score of the real pulse is smaller than the accumulated score of the imaginary pulse, determining that the pulse condition is the fourth type pulse condition.
The above-described identification means will be explained in detail with reference to specific embodiments.
The third type of pulse condition includes big pulse and real pulse, the fourth type of pulse condition includes thin pulse and deficient pulse, the variable of the accumulated score of the real pulse of the third type of pulse condition is shi, and the variable of the accumulated score of the deficient pulse of the fourth type of pulse condition is xu. The numerical region division is carried out on the characteristics of the total integral area, the integral area of the first curve, the width of the main wave preset height, the rising time of the wave crest and the like as follows:
(1) Total integral area E
If the total integrated area E >2.1, the variable shi=shi+2;
if the total integrated area E >1.4, the variable shi=shi+1;
if the total integrated area E <0.7, the variable xu=xu+1;
if the total integration area E <0.3, the variable xu=xu+2.
(2) Integral area delta of the first curve
The variable xu=xu+1 if the integrated area δ of the first curve is > 0.15;
the variable xu=xu+2 if the integrated area δ of the first curve is > 0.3;
if the integrated area δ of the first curve is <0.15, the variable shi=shi+1;
If the integral area δ of the first curve is <0.07, the variable shi=shi+2.
(3) Width w3/t and width w5/t
If the width w3/t <0.2 or the width w5/t <0.1, the variable shi=shi+2;
if the width w3/t <0.25 or the width w5/t <0.12, the variable shi=shi+1;
if the width w3/t >0.3or the width w5/t >0.18, the variable xu=xu+1;
if the width w3/t >0.35or the width w5/t >0.2, the variable xu=xu+2.
(4) Peak rise time ts
If the peak rise time ts <200, the variable shi=shi+2;
if peak rise time ts <260, variable shi=shi+1;
if peak rise time ts >260, then the variable xu=xu+1;
if peak rise time ts >300, then the variable xu=xu+2.
Calculating the score of each feature, counting the real pulse accumulated score shi and the imaginary pulse accumulated score xu according to the divided numerical value areas, and judging as a third type of pulse condition when the shi is more than or equal to xu; when shi < xu, the fourth pulse condition is determined.
As an alternative embodiment, the step A2 may further include:
and carrying out weighted summation on the total integral area, the integral area of the first curve, the width of the main wave preset height, the rising time of the wave crest, the numerical value area and the numerical value area to obtain a real pulse accumulated score and a virtual pulse accumulated score.
Because the contribution degree of each feature to pulse condition identification is different, for example, the contribution of the total integral area is relatively large, and the contribution of other features is relatively small, the weight distribution is performed on each feature, for example, the total integral area is 40%, the integral area of the first curve is 20%, the width of the main wave preset height is 20%, and the rising time of the wave crest is 20%. When the accumulated score is calculated, the calculation is performed in combination with the assigned weight, so as to obtain a more accurate recognition effect.
S142, if the third pulse condition is the third pulse condition, the pulse condition is judged to be the big pulse or the real pulse according to the total integrated area. Step S142 may further include steps S1421-S1422:
s1421, if the total integral area is larger than the first preset area, judging that the pulse condition is a large pulse;
s1422, if the total integrated area is smaller than or equal to the first preset area, determining that the pulse condition is a real pulse.
Because the total integral area can represent the 'force' of the pulse condition, after the pulse condition is judged to be the third type of pulse condition, the large pulse and the real pulse are further distinguished according to the total integral area. Illustratively, if the total integrated area E >3, the pulse condition is determined to be a large pulse; if the total integration area E is less than or equal to 3, the pulse condition is judged to be real pulse.
S143, if the fourth pulse condition is the fourth pulse condition, the pulse condition is determined to be a thready pulse or a deficient pulse according to the total integrated area. Step S142 may further include step S1431-step S1432:
S1431, if the total integral area is smaller than the second preset area, judging that the pulse condition is a fine pulse;
s1432, if the total integral area is larger than or equal to the second preset area, determining that the pulse condition is a deficient pulse.
Based on the total integral area, the condition of 'dynamics' of the pulse condition can be reflected, so that after the pulse condition is judged to be the fourth type of pulse condition, the thin pulse and the deficient pulse are further distinguished according to the total integral area. Illustratively, if the total integrated area E is less than 0.7, the pulse condition is determined to be a fine pulse; if the total integral area E is more than or equal to 0.7, the pulse condition is judged to be a deficient pulse. In some alternative embodiments, upon determining a stringer, a shape feature is added, such as: when the total integral area E is less than 0.7, judging whether a microblog wave or a tide wave appears in the waveform, and if so, judging that the pulse condition is a fine pulse; if not, the pulse condition is judged as a deficient pulse.
As shown in fig. 5, an embodiment of the present invention provides a pulse condition recognition system, including:
the pulse wave signal acquisition module is used for acquiring pulse wave signals, wherein the pulse wave signals comprise a single pulse wave and a plurality of continuous pulse waves.
The waveform of pulse wave has close relation with the pulse feeling of traditional Chinese medicine, and the diagnosis of pulse feeling, i.e. pulse condition, of traditional Chinese medicine generally adopts a more classical pulse feeling finger method of 'single cunkou'. From a physiological and medical point of view, the pulse is driven by the heart and the blood follows a tortuous and lengthy path along the artery in the body before reaching the radial artery remote from the heart. Therefore, the pulse signals are affected by not only the heart condition but also the arterial vessel characteristics, blood flow parameters, muscles, skin and other factors. In traditional Chinese medicine, pulse condition identification mainly depends on finger feeling, but the traditional Chinese medicine relies on pulse information provided by fingers when a patient feels radial artery pulsation, and the pulse attribute identification only stays in the original visual concept, and more is based on years of clinical experience of doctors, and the subjective feeling of doctor's identification experience and pulse diagnosis is doped. Along with the development of science and technology, modern traditional Chinese medicine researches a pulse diagnosis instrument, which can collect and draw pulse signals into pulse waveforms and judge pulse conditions of the pulse waves according to the pulse waveforms.
In this embodiment, the pulse wave signal may be obtained by an existing pulse diagnosis apparatus, and the pulse wave signal may be an optoelectronic pulse wave signal, an ultrasonic pulse wave signal or a pressure pulse wave signal. The acquired pulse wave signals comprise a single pulse wave and a plurality of continuous pulse waves, wherein the single pulse wave refers to the waveform of the single pulse wave, and the plurality of continuous pulse waves refer to the waveforms of the plurality of continuous pulse waves.
The feature extraction module is used for acquiring first features according to the plurality of continuous pulse waves and acquiring second features according to the single pulse wave. Wherein the first characteristic is a characteristic characterizing pulse beat rate and the second characteristic is a characteristic characterizing pulse beat amplitude.
In this embodiment, the feature extraction is performed on a plurality of continuous pulses to obtain a first feature, where the first feature reflects the condition of the pulse beat rate, such as whether the pulse beat is rapid, whether the pulse beat is uniform, or whether the pulse beat is regular. By extracting features of the single pulse wave, a second feature is obtained, where the second feature reflects the condition of the pulse beat amplitude, such as the period of the pulse wave, the heights of the main wave, the tide wave and the counterpulsation wave in the pulse wave, the width of the main wave of the pulse wave, the width of the systolic period of the pulse wave, and the like.
The first recognition module is used for carrying out first pulse condition recognition according to the first characteristic to obtain a first recognition result, wherein the first recognition result is a first type pulse condition or a second type pulse condition.
In the prior art, a plurality of features are acquired and identified once based on the plurality of features, for example, feature vectors are formed by the acquired features, the feature vectors are input into an identification model for identification and classification, so that corresponding pulse types are identified, the identification results may include identification results with different dimensions, for example, the pulse of a patient is rapid and weak, the output result may be a false pulse or a number pulse, and thus the identification results are not accurate enough. For this reason, the present embodiment acquires the first feature and the second feature in different manners, and performs corresponding feature recognition for different features.
In some alternative embodiments, the first characteristic includes a pulse rate value and a continuous pulse period rate of change of adjacent two periods of the plurality of continuous pulse waves. The first recognition module may further include:
and the period calculation unit is used for acquiring a plurality of continuous pulse period change rates in a preset time period.
The first recognition unit is used for carrying out first pulse condition recognition according to the pulse rate value and the continuous pulse period change rate to obtain a first recognition result.
Pulse rate values are obtained by obtaining the number of pulse beats within a preset time (e.g., 1 minute). In pulse beating, there is a possibility that beat imbalance between adjacent pulse waves, that is, the periods of adjacent pulse waves are different, even a large difference, may reflect some problems of body functions, and thus a continuous pulse period change rate is introduced. In some alternative embodiments, the continuous pulse cycle rate is calculated as follows:
σ＝(t 1 -t 2 )/t 1
wherein t is 1 And t 2 For the period of any two adjacent pulse waves, t 1 At t 2 Is the next pulse wave period.
In some alternative embodiments, the first type of pulse condition includes a disease pulse, a promotion pulse, and a rapid pulse, the second type of pulse condition includes a knot pulse, a slow pulse, and a delayed pulse, and the first identifying unit may further include:
the quantity counting subunit is used for counting a first quantity, wherein the first quantity is a quantity that the absolute value of the continuous pulse period change rate is larger than a first preset value;
the pulse disease judging subunit is used for judging that the pulse condition is a pulse disease if the pulse rate value is larger than a first preset pulse rate value and the first quantity is smaller than a second preset value;
The pulse promoting judging subunit is used for judging that the pulse condition is pulse promoting if the pulse rate value is greater than or equal to a second preset pulse rate value and the first quantity is greater than or equal to the second preset value;
the pulse counting judging subunit is used for judging that the pulse condition is pulse counting if the pulse rate value is larger than a second preset pulse rate value and smaller than or equal to a first preset pulse rate value and the first quantity is smaller than the second preset value;
the pulse junction judging subunit is used for judging that the pulse condition is pulse junction if the pulse rate value is smaller than the second preset pulse rate value and the first quantity is larger than or equal to the second preset value;
the pulse-slowing judging subunit is used for judging that the pulse condition is pulse slowing if the pulse rate value is greater than or equal to a third preset pulse rate value and smaller than a second preset pulse rate value and the first quantity is smaller than the second preset value;
the pulse delay judging subunit is used for judging that the pulse condition is a pulse delay if the pulse rate value is smaller than a third preset pulse rate value and the first quantity is smaller than a second preset value;
wherein the first preset pulse rate value is greater than the second preset pulse rate value and greater than the third preset pulse rate value.
In this embodiment, the first number n is counted first, where n is the number that the absolute value of the period change rate of the continuous pulse is greater than the first preset value, and when the absolute value of the period change rate is greater than 20%, the first number n is added by 1. Illustratively, the first preset pulse rate value is 110 times/min, the second preset pulse rate value is 90 times/min, and the third preset pulse rate value is 65 times/min.
When the pulse rate value is more than 110 times/min and n is less than 3, the pulse rate is regular, the continuous pulse period is basically equal, and the pulse condition is judged to be a disease pulse.
When the pulse rate value is greater than 90 times/min and n is greater than or equal to 3, the pulse period is unequal, and irregular intermittent or stopping pulse exists; the descending time is different, and the time is slow; the pulse condition is judged as promoting pulse.
When the pulse rate value is greater than 90 times/min and less than 110 times/min, and n is less than 3, the pulse rate is regular, and the continuous pulse periods are basically equal, the pulse condition is judged to be a number pulse.
When the pulse rate value is smaller than 90 times/min and n is larger than or equal to 3, indicating that the pulse period is unequal and the pulse wave has irregular stopping pulse, judging that the pulse condition is a knot pulse.
When the pulse rate value is greater than 65 times/min and less than 90 times/min, and n is less than 3, it indicates that the main peak included angle in the pulse is slightly wider and the descending slope is reduced, and then the pulse condition is determined to be slow.
When the pulse rate value is smaller than 65 times/min and n is smaller than 3, the pulse rate is regular but slow, and the continuous pulse period is basically the same, the pulse condition is judged to be the slow pulse.
And the second recognition module is used for carrying out second pulse condition recognition according to the second characteristics to obtain a second recognition result, wherein the second recognition result is a third type pulse condition or a fourth type pulse condition.
The second characteristic is obtained through single pulse wave extraction, wherein the waveform of the single pulse wave is characterized by a waveform curve, the waveform curve comprises a first curve corresponding to a first period, and the first period belongs to the systolic period of the waveform curve. The second characteristic includes a total integrated area of the waveform curve, a shape characteristic of the waveform curve, and an integrated area of the first curve. The third category of pulse conditions includes large pulse and real pulse, and the fourth category of pulse conditions includes thin pulse and deficient pulse.
In some alternative embodiments, referring to fig. 3, the total integrated area E is the integrated area corresponding to the entire pulse wave. The section from the highest point of the main wave to the end point of the pulse wave is the systolic phase, and the last 1/3 line segment in the systolic phase is selected as a first curve, and the integral area corresponding to the first curve is delta. The shape characteristics of the waveform curve include tide wave, microblog wave, main wave height, main wave width, main wave rising time and the like. The second recognition module may further include a real-virtual classification sub-module, a real-vein classification sub-module, and a virtual-vein classification sub-module:
the real-deficiency classification sub-module is used for determining that the pulse condition is a third type pulse condition or a fourth type pulse condition according to the total integral area, the shape characteristic and the integral area of the first curve.
In this embodiment, multiple features are used to comprehensively identify the condition of the pulse condition, for example, a multidimensional vector is constructed through multiple features, and classification and identification are performed based on the vector. The real-virtual classification sub-module may further include:
and the score accumulating unit is used for calculating the real pulse accumulated score and the imaginary pulse accumulated score according to the total integral area, the shape characteristic and the integral area of the first curve.
In some alternative embodiments, the shape characteristic of the waveform curve includes a width of a main preset height and a peak rise time, and the score accumulating unit may further include:
the region dividing subunit is configured to divide each second feature into a plurality of value regions, determine a value region corresponding to the third type of pulse condition and a value region corresponding to the fourth type of pulse condition, and determine a score corresponding to each value region.
The score accumulation subunit is configured to calculate an actual pulse accumulation score and a virtual pulse accumulation score according to the total integration area, the integration area of the first curve, the width of the preset main wave height, the peak rising time, the numerical region and the score corresponding to the numerical region.
The width of the main wave preset height is the corresponding width at the main wave preset height of the pulse wave; the peak rise time is the time from the initial point of the pulse wave to the highest point of the main wave.
In this embodiment, referring to FIG. 3, the width of the main preset height includes a w3/t width and a w5/t width. The highest point of the main wave is h, the w3/t width refers to the width corresponding to the main wave at the 2/3h height, and the w5/t width refers to the width corresponding to the main wave at the 4/5h height. The peak rise time ts is the time from the initial point of the pulse wave to the highest point of the main wave.
The real pulse type judging unit is used for judging that the pulse condition is the third type pulse condition if the real pulse cumulative score is larger than or equal to the virtual pulse cumulative score.
The deficient pulse type judging unit is used for judging that the pulse condition is the fourth type pulse condition if the accumulated score of the real pulse is smaller than the accumulated score of the deficient pulse.
The above-described identification means will be explained in detail with reference to specific embodiments.
The third type of pulse condition includes big pulse and real pulse, the fourth type of pulse condition includes thin pulse and deficient pulse, the variable of the accumulated score of the real pulse of the third type of pulse condition is shi, and the variable of the accumulated score of the deficient pulse of the fourth type of pulse condition is xu. The numerical region division is carried out on the characteristics of the total integral area, the integral area of the first curve, the width of the main wave preset height, the rising time of the wave crest and the like as follows:
(1) Total integral area E
If the total integrated area E >2.1, the variable shi=shi+2;
If the total integrated area E >1.4, the variable shi=shi+1;
if the total integrated area E <0.7, the variable xu=xu+1;
if the total integration area E <0.3, the variable xu=xu+2.
(2) Integral area delta of the first curve
The variable xu=xu+1 if the integrated area δ of the first curve is > 0.15;
the variable xu=xu+2 if the integrated area δ of the first curve is > 0.3;
if the integrated area δ of the first curve is <0.15, the variable shi=shi+1;
if the integral area δ of the first curve is <0.07, the variable shi=shi+2.
(3) Width w3/t and width w5/t
If the width w3/t <0.2 or the width w5/t <0.1, the variable shi=shi+2;
if the width w3/t <0.25 or the width w5/t <0.12, the variable shi=shi+1;
if the width w3/t >0.3or the width w5/t >0.18, the variable xu=xu+1;
if the width w3/t >0.35or the width w5/t >0.2, the variable xu=xu+2.
(4) Peak rise time ts
If the peak rise time ts <200, the variable shi=shi+2;
if peak rise time ts <260, variable shi=shi+1;
if peak rise time ts >260, then the variable xu=xu+1;
if peak rise time ts >300, then the variable xu=xu+2.
Calculating the score of each feature, counting the real pulse accumulated score shi and the imaginary pulse accumulated score xu according to the divided numerical value areas, and judging as a third type of pulse condition when the shi is more than or equal to xu; when shi < xu, the fourth pulse condition is determined.
As an optional embodiment, the score accumulating subunit is specifically configured to:
and carrying out weighted summation on the total integral area, the integral area of the first curve, the width of the main wave preset height, the rising time of the wave crest, the numerical value area and the numerical value area to obtain a real pulse accumulated score and a virtual pulse accumulated score.
Because the contribution degree of each feature to pulse condition identification is different, for example, the contribution of the total integral area is relatively large, and the contribution of other features is relatively small, the weight distribution is performed on each feature, for example, the total integral area is 40%, the integral area of the first curve is 20%, the width of the main wave preset height is 20%, and the rising time of the wave crest is 20%. When the accumulated score is calculated, the calculation is performed in combination with the assigned weight, so as to obtain a more accurate recognition effect.
The real pulse classification sub-module is used for judging whether the pulse condition is the big pulse or the real pulse according to the total integrated area if the pulse condition is the third pulse condition. The real vein classification sub-module may further include:
the large pulse judging unit is used for judging that the pulse condition is a large pulse if the total integral area is larger than a first preset area;
the real pulse judging unit is used for judging that the pulse condition is real pulse if the total integral area is smaller than or equal to the first preset area.
Because the total integral area can represent the 'force' of the pulse condition, after the pulse condition is judged to be the third type of pulse condition, the large pulse and the real pulse are further distinguished according to the total integral area. Illustratively, if the total integrated area E >3, the pulse condition is determined to be a large pulse; if the total integration area E is less than or equal to 3, the pulse condition is judged to be real pulse.
And the deficient pulse classification submodule is used for judging whether the pulse condition is a thin pulse or a deficient pulse according to the total integral area if the pulse condition is a fourth pulse condition. The imaginary pulse class classification sub-module may further include:
the thin pulse judging unit is used for judging that the pulse condition is a thin pulse if the total integral area is smaller than a second preset area;
and the deficient pulse judging unit is used for judging that the pulse condition is deficient pulse if the total integral area is larger than or equal to the second preset area.
Based on the total integral area, the condition of 'dynamics' of the pulse condition can be reflected, so that after the pulse condition is judged to be the fourth type of pulse condition, the thin pulse and the deficient pulse are further distinguished according to the total integral area. Illustratively, if the total integrated area E is less than 0.7, the pulse condition is determined to be a fine pulse; if the total integral area E is more than or equal to 0.7, the pulse condition is judged to be a deficient pulse. In some alternative embodiments, upon determining a stringer, a shape feature is added, such as: when the total integral area E is less than 0.7, judging whether a microblog wave or a tide wave appears in the waveform, and if so, judging that the pulse condition is a fine pulse; if not, the pulse condition is judged as a deficient pulse.
As shown in fig. 6, an embodiment of the present invention proposes a pulse condition recognition device 30, the device 30 comprising a memory 31, a processor 32, a program stored on the memory and executable on the processor, and a data bus 33 for enabling connection communication between the processor 32 and the memory 31, the program being executed by the processor to implement the following specific steps as shown in fig. 1.
The content in the method embodiment is applicable to the embodiment of the device, and the functions specifically realized by the embodiment of the device are the same as those of the method embodiment, and the obtained beneficial effects are the same as those of the method embodiment.
Embodiments of the present invention provide a computer-readable storage medium storing one or more programs executable by one or more processors to implement the following specific steps as shown in fig. 1.
The content in the method embodiment is applicable to the embodiment of the storage medium, and the specific functions of the embodiment of the storage medium are the same as those of the embodiment of the method, and the achieved beneficial effects are the same as those of the embodiment of the method.
Those of ordinary skill in the art will appreciate that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof.
In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and thus do not limit the scope of the claims of the present invention. Any modifications, equivalent substitutions and improvements made by those skilled in the art without departing from the scope and spirit of the present invention shall fall within the scope of the appended claims.
Claims (8)
1. The pulse condition identification method is characterized by comprising the following steps of:
acquiring pulse wave signals, wherein the pulse wave signals comprise a single pulse wave and a plurality of continuous pulse waves; acquiring a first characteristic according to the plurality of continuous pulse waves, and acquiring a second characteristic according to the single pulse wave;
performing first pulse condition identification according to the first characteristic to obtain a first identification result, wherein the first identification result is a first type pulse condition or a second type pulse condition;
performing second pulse condition identification according to the second characteristic to obtain a second identification result, wherein the second identification result is a third type pulse condition or a fourth type pulse condition;
wherein the first characteristic is a characteristic characterizing pulse beat rate and the second characteristic is a characteristic characterizing pulse beat amplitude;
the first characteristic comprises a pulse rate value and a continuous pulse period change rate, wherein the continuous pulse period change rate is the change rate of two adjacent periods in the plurality of continuous pulse waves;
The step of performing first pulse condition identification according to the first characteristic to obtain a first identification result comprises the following steps:
acquiring a plurality of continuous pulse period change rates in a preset time period;
performing first pulse condition identification according to the pulse rate value and the continuous pulse period change rate to obtain a first identification result;
the first type of pulse condition comprises a disease pulse, a promotion pulse and a rapid pulse, the second type of pulse condition comprises a knot pulse, a slow pulse and a delayed pulse, the first pulse condition identification is carried out according to the pulse rate value and the continuous pulse period change rate, and a first identification result is obtained, and the method comprises the following steps:
counting a first quantity, wherein the first quantity is the number that the absolute value of the continuous pulse period change rate is larger than a first preset value;
if the pulse rate value is larger than a first preset pulse rate value and the first quantity is smaller than a second preset value, judging that the pulse condition is a disease pulse;
if the pulse rate value is greater than or equal to a second preset pulse rate value, and the first quantity is greater than or equal to the second preset value, judging that the pulse condition is pulse promotion;
if the pulse rate value is larger than the second preset pulse rate value and smaller than or equal to the first preset pulse rate value, and the first quantity is smaller than the second preset value, judging that the pulse condition is a pulse number;
If the pulse rate value is smaller than a second preset pulse rate value, and the first quantity is larger than or equal to the second preset value, judging that the pulse condition is a knot pulse;
if the pulse rate value is larger than or equal to a third preset pulse rate value and smaller than a second preset pulse rate value, and the first quantity is smaller than the second preset value, judging that the pulse condition is a slow pulse;
if the pulse rate value is smaller than a third preset pulse rate value and the first quantity is smaller than the second preset value, judging that the pulse condition is a delayed pulse;
wherein the first preset pulse rate value is greater than the second preset pulse rate value and greater than the third preset pulse rate value.
2. The pulse condition identification method according to claim 1, wherein the waveform of the single pulse wave is characterized by a waveform curve, the waveform curve comprises a first curve corresponding to a first period, and the first period belongs to a systolic period of the waveform curve; the second feature comprises a total integrated area of the waveform curve, a shape feature of the waveform curve, and an integrated area of the first curve; the third type of pulse condition comprises a large pulse and a real pulse, and the fourth type of pulse condition comprises a thin pulse and a deficient pulse;
and carrying out second pulse condition identification according to the second characteristic to obtain a second identification result, wherein the second identification result comprises the following steps:
Determining that the pulse condition is a third type pulse condition or a fourth type pulse condition according to the total integral area, the shape characteristic and the integral area of the first curve;
if the third pulse condition is the third pulse condition, judging whether the pulse condition is a large pulse or a real pulse according to the total integral area;
if the fourth pulse condition is the fourth pulse condition, the pulse condition is judged to be a thin pulse or a deficient pulse according to the total integral area.
3. The method of claim 2, wherein determining whether the pulse condition is a third type pulse condition or a fourth type pulse condition based on the total integrated area, the shape feature, and the integrated area of the first curve comprises:
calculating a real pulse cumulative score and a virtual pulse cumulative score according to the total integral area, the shape feature and the integral area of the first curve;
if the real pulse cumulative score is greater than or equal to the imaginary pulse cumulative score, judging that the pulse condition is a third type pulse condition;
if the real pulse cumulative score is smaller than the imaginary pulse cumulative score, judging that the pulse condition is a fourth type pulse condition;
the determining whether the pulse condition is a large pulse or a real pulse according to the total integral area comprises:
if the total integral area is larger than the first preset area, judging that the pulse condition is a large pulse;
If the total integral area is smaller than or equal to the first preset area, judging that the pulse condition is real pulse;
the determining that the pulse condition is a thin pulse or a deficient pulse according to the total integral area includes:
if the total integral area is smaller than the second preset area, judging that the pulse condition is a fine pulse;
and if the total integral area is larger than or equal to a second preset area, judging that the pulse condition is a deficient pulse.
4. A pulse condition recognition method according to claim 3, wherein the shape characteristics of the waveform curve include a width of a main preset height and a peak rise time;
said integrating area according to said total integrating area, said shape feature and said first curve,
calculating a real pulse cumulative score and a imaginary pulse cumulative score, comprising:
dividing each second characteristic into a plurality of numerical value areas, determining the numerical value areas corresponding to the third type of pulse condition and the numerical value areas corresponding to the fourth type of pulse condition, and determining the scores corresponding to the numerical value areas;
calculating a real pulse cumulative score and a virtual pulse cumulative score according to the total integral area, the integral area of the first curve, the width of the main wave preset height, the peak rising time, the numerical value region and the scores corresponding to the numerical value region;
The width of the main wave preset height is the corresponding width at the main wave preset height of the pulse wave; the peak rise time is the time from the initial point of the pulse wave to the highest point of the main wave.
5. The pulse condition recognition method according to claim 4, wherein the calculating the real pulse cumulative score and the imaginary pulse cumulative score according to the total integrated area, the integrated area of the first curve, the width of the main preset height, the peak rise time, the numerical region, and the scores corresponding to the numerical region includes:
and carrying out weighted summation on the total integral area, the integral area of the first curve, the width of the main wave preset height, the rising time of the wave crest, the numerical value area and the numerical value area to obtain a real pulse accumulated score and a virtual pulse accumulated score.
6. A pulse condition recognition system, comprising:
a signal acquisition module for acquiring pulse wave signals, the pulse wave signals comprising a single pulse wave and a plurality of continuous pulse waves;
the feature extraction module is used for acquiring first features according to the plurality of continuous pulse waves and acquiring second features according to the single pulse wave;
The first recognition module is used for carrying out first pulse condition recognition according to the first characteristics to obtain a first recognition result, wherein the first recognition result is a first type pulse condition or a second type pulse condition;
the second recognition module is used for carrying out second pulse condition recognition according to the second characteristics to obtain a second recognition result, wherein the second recognition result is a third type pulse condition or a fourth type pulse condition;
wherein the first characteristic is a characteristic characterizing pulse beat rate and the second characteristic is a characteristic characterizing pulse beat amplitude;
the first characteristic comprises a pulse rate value and a continuous pulse period change rate, wherein the continuous pulse period change rate is the change rate of two adjacent periods in the plurality of continuous pulse waves;
the step of performing first pulse condition identification according to the first characteristic to obtain a first identification result comprises the following steps:
acquiring a plurality of continuous pulse period change rates in a preset time period;
performing first pulse condition identification according to the pulse rate value and the continuous pulse period change rate to obtain a first identification result;
the first type of pulse condition comprises a disease pulse, a promotion pulse and a rapid pulse, the second type of pulse condition comprises a knot pulse, a slow pulse and a delayed pulse, the first pulse condition identification is carried out according to the pulse rate value and the continuous pulse period change rate, and a first identification result is obtained, and the method comprises the following steps:
Counting a first quantity, wherein the first quantity is the number that the absolute value of the continuous pulse period change rate is larger than a first preset value;
if the pulse rate value is larger than a first preset pulse rate value and the first quantity is smaller than a second preset value, judging that the pulse condition is a disease pulse;
if the pulse rate value is greater than or equal to a second preset pulse rate value, and the first quantity is greater than or equal to the second preset value, judging that the pulse condition is pulse promotion;
if the pulse rate value is larger than the second preset pulse rate value and smaller than or equal to the first preset pulse rate value, and the first quantity is smaller than the second preset value, judging that the pulse condition is a pulse number;
if the pulse rate value is smaller than a second preset pulse rate value, and the first quantity is larger than or equal to the second preset value, judging that the pulse condition is a knot pulse;
if the pulse rate value is larger than or equal to a third preset pulse rate value and smaller than a second preset pulse rate value, and the first quantity is smaller than the second preset value, judging that the pulse condition is a slow pulse;
if the pulse rate value is smaller than a third preset pulse rate value and the first quantity is smaller than the second preset value, judging that the pulse condition is a delayed pulse;
wherein the first preset pulse rate value is greater than the second preset pulse rate value and greater than the third preset pulse rate value.
7. A pulse condition recognition device, comprising:
At least one processor;
at least one memory for storing at least one program;
the at least one program, when executed by the at least one processor, causes the at least one processor to implement the method of any one of claims 1-5.
8. A computer readable storage medium, in which a processor executable program is stored, characterized in that the processor executable program is for performing the method according to any of claims 1-5 when being executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210142968.2A CN114305345B (en) | 2022-02-16 | 2022-02-16 | Pulse condition identification method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210142968.2A CN114305345B (en) | 2022-02-16 | 2022-02-16 | Pulse condition identification method, system, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114305345A CN114305345A (en) | 2022-04-12 |
| CN114305345B true CN114305345B (en) | 2023-07-25 |
Family
ID=81030924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210142968.2A Active CN114305345B (en) | 2022-02-16 | 2022-02-16 | Pulse condition identification method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114305345B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114916910B (en) * | 2022-04-29 | 2024-04-09 | 无锡市华焯光电科技有限公司 | Pulse classification method, classification model training method, classification device, and storage medium |
| CN115868944B (en) * | 2022-09-23 | 2023-09-08 | 广东省新黄埔中医药联合创新研究院 | Method for measuring pulse envelope and identifying pulse buffering characteristics by three pressure sensing arrays of cunguan ruler |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104083157B (en) * | 2014-07-07 | 2016-04-20 | 北京印刷学院 | A kind of pulse signal recognition methods |
| CN107736880B (en) * | 2017-10-24 | 2024-01-30 | 新绎健康科技有限公司 | Pulse analysis method and system |
| CN108670209A (en) * | 2018-03-29 | 2018-10-19 | 中国科学院微电子研究所 | A kind of method and system of automatic identification Chinese medicine pulse |
| CN109009004A (en) * | 2018-07-19 | 2018-12-18 | 上海泰怡健康科技有限公司 | A kind of physical examinations method based on Chinese medicine pulse analysis |
| CN111801047B (en) * | 2018-12-25 | 2022-07-12 | 深圳市大富智慧健康科技有限公司 | Blood pressure pulse condition detection system and detection method and detection device thereof |
-
2022
- 2022-02-16 CN CN202210142968.2A patent/CN114305345B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114305345A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114305345B (en) | Pulse condition identification method, system, device and storage medium | |
| CN108289615B (en) | Method for quantifying photoplethysmography (PPG) signal quality | |
| US9801609B2 (en) | Device and method for enhancing accuracy of recognizing fetus heart rate acceleration data | |
| CN107822608A (en) | Pulse wave feature extracting method based on gauss hybrid models | |
| CN109480783B (en) | Apnea detection method and device and computing equipment | |
| CN109117730A (en) | Electrocardiogram auricular fibrillation real-time judge method, apparatus, system and storage medium | |
| CN109864736A (en) | Processing method, device, terminal device and the medium of electrocardiosignal | |
| CN104905785B (en) | ECG signal detection method and system | |
| CN108324271B (en) | Electrocardiosignal identification method and system and electrocardiosignal monitoring equipment | |
| CN112184656B (en) | Method and device for determining fetal section based on ultrasonic dynamic image | |
| CN110853605A (en) | Music generation method and device and electronic equipment | |
| KR20200123335A (en) | Method for estimating continuous blood pressure using recurrent neural network and apparatus thereof | |
| US10702210B2 (en) | Meal intake detection device, meal intake detection method and computer-readable non-transitory medium | |
| CN114224297B (en) | Pulse condition identification method, device, equipment and storage medium based on pulse characteristics | |
| CN110151156B (en) | Fetal heart rate extraction method and system based on in-window automatic weighted average algorithm | |
| CN101866423A (en) | Method for dividing arterial pressure signal beat by beat | |
| Elixmann et al. | Single pulse analysis of intracranial pressure for a hydrocephalus implant | |
| WO2020220403A1 (en) | Fatigue state detection method, apparatus and device, and storage medium | |
| CN111671409A (en) | Pulse waveform analysis method and device | |
| CN110368019A (en) | A kind of cardiechema signals feature extraction, detection model building and detection device | |
| CN111227814A (en) | Method and device for analyzing arterial state | |
| CN101879058B (en) | Method for segmenting intracranial pressure signal beat by beat | |
| CN112370013A (en) | Method and system for determining sleep stage | |
| Pietrzak et al. | New indices for sleep apnea detection from long-time ECG recordings | |
| KR102418339B1 (en) | Apparatus for extracting blood sugar lever using continuous blood glucose data and method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |