CN113223700A - Traditional Chinese medicine pulse condition identification method and device based on pulse condition data - Google Patents
Traditional Chinese medicine pulse condition identification method and device based on pulse condition data Download PDFInfo
- Publication number
- CN113223700A CN113223700A CN202110401491.0A CN202110401491A CN113223700A CN 113223700 A CN113223700 A CN 113223700A CN 202110401491 A CN202110401491 A CN 202110401491A CN 113223700 A CN113223700 A CN 113223700A
- Authority
- CN
- China
- Prior art keywords
- pulse
- condition
- determining
- pulse condition
- array
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Alternative & Traditional Medicine (AREA)
- Cardiology (AREA)
- Manipulation Of Pulses (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the technical field of traditional Chinese medicine pulse conditions, in particular to a traditional Chinese medicine pulse condition identification method and a device based on pulse condition data, wherein the method comprises the following steps: acquiring initial pulse condition data to be identified; determining pulse condition data to be identified according to the initial pulse condition data, wherein the pulse condition data to be identified comprises pulse times, pulse amplitude, pulse width, left pulse width, right pulse width, pulse potential, left pulse potential and right pulse potential; forming a one-dimensional array by the pulse condition data to be identified according to a preset sequence to obtain a pulse condition array to be identified; acquiring a pulse condition sample array of pre-stored pulse condition sample data; and comparing the pulse condition array to be identified with the pulse condition sample array to determine the pulse condition corresponding to the pulse condition array to be identified. By the method and the device, the pulse condition corresponding to the initial pulse condition data can be determined more accurately.
Description
Technical Field
The invention relates to the technical field of traditional Chinese medicine pulse conditions, in particular to a traditional Chinese medicine pulse condition identification method and device based on pulse condition data.
Background
The pulse condition of traditional Chinese medicine plays an important role in clinical diagnosis, and is one of the important expression forms of the traditional Chinese medicine theory applied to the clinic. In order to solve the disease of the patient, doctors need to organically combine the theory of traditional Chinese medicine with years of clinical experience, make identification according to the pulse condition characteristics of the patient and then determine a treatment scheme (treatment) by combining other symptoms. In clinical practice, there are the saying that the herbs do not leave the prescription, the recipe does not leave the syndrome, and the syndrome does not leave the symptoms (including pulse conditions), and it seems that the syndrome plays a bridge role between the recipe and the symptoms. For the study of syndrome differentiation, there is much ingenuity behind syndrome differentiation, and it is necessary to trace back to the source to know the nature and the shortcut of the syndrome differentiation. The pulse of TCM is composed of 92 standardized names, such as deep pulse, slow pulse, superficial pulse, rapid pulse, deficient pulse, … ….
In the past, the pulse condition of a patient is described by words known by sensibility, such as deep pulse, slow pulse, floating pulse, rapid pulse, weak pulse and the like, and doctors often judge the corresponding pulse condition of the patient through more practical clinical experiences of the doctors, which may cause the problem of misjudgment due to insufficient experience of the doctors.
Disclosure of Invention
The embodiment of the invention provides a traditional Chinese medicine pulse condition identification method and device based on pulse condition data. The technical scheme is as follows:
in one aspect, a method for traditional Chinese medicine pulse condition identification based on pulse condition data is provided, and the method is applied to electronic equipment, and comprises the following steps:
acquiring initial pulse condition data to be identified;
determining pulse condition data to be identified according to the initial pulse condition data, wherein the pulse condition data to be identified comprises pulse times, pulse amplitude, pulse width, left pulse width, right pulse width, pulse potential, left pulse potential and right pulse potential;
forming a one-dimensional array by the pulse condition data to be identified according to a preset sequence to obtain a pulse condition array to be identified;
acquiring a pulse condition sample array of pre-stored pulse condition sample data, wherein the pulse condition sample data comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse conditions, left pulse conditions and right pulse conditions, the arrangement sequence of data in the pulse condition sample array is the same as that of data in the pulse condition array to be identified, and the number of data in the pulse condition sample array is the same as that of data in the sample array to be identified;
and comparing the pulse condition array to be identified with the pulse condition sample array to determine the pulse condition corresponding to the pulse condition array to be identified.
Optionally, the determining pulse condition data to be identified according to the initial pulse condition data includes:
determining a pulse amplitude value according to the initial pulse condition data;
determining the peak and the valley of the pulse according to the pulse amplitude;
determining pulse times based on the pulse peaks and the position value of a time axis;
determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and a time axis and the height of the pulse peak;
determining a pulse condition, a left pulse condition and a right pulse condition based on the pulse peak, the pulse valley and the pulse amplitude of the initial pulse condition data.
Optionally, the determining a pulse amplitude value according to the initial pulse condition data includes:
determining a pulse amplitude value according to an initial pulse amplitude value in the initial pulse condition data and the following formula (1):
Am＝An+Ve×n……(1)
wherein A isnIs the initial pulse amplitude; n is 1, 2, 3, … …; m is 1, 2, 3, … …; veFor adjusting the coefficient of pulse amplitude, Ve＝0.00001。
Optionally, the determining the pulse peak and the pulse valley according to the pulse amplitude includes:
determining a first intermediate value according to the following formula (2) based on a preset pulse amplitude threshold coefficient, a maximum pulse amplitude value and a minimum pulse amplitude value:
L＝Ammax-(Ammax-Ammin)×Fm……(2)
wherein L is a first intermediate value, FmIs the pulse amplitude threshold coefficient, Fm＝0.4；AmmaxMaximum value of pulse amplitude, AmminIs the minimum value of pulse amplitude;
determining the pulse amplitude value according to the first intermediate value and the following formula (3):
wherein D ismTaking the pulse amplitude as two values;
determining a binary pulse amplitude difference value according to the binary pulse amplitude and the following formula (4):
wherein E ismThe pulse amplitude binary differential value is obtained;
determining a pulse amplitude difference value according to the initial pulse amplitude value and the following formula (5):
wherein, CmThe pulse amplitude difference value is obtained;
when C is presentm＝1，En>0，Em<At 0, the peak and valley of the pulse are determined according to the following formula (6)
Where h is the cumulative value of the sampling interval time, i is 1, 2, 3, … …, f (h), and g (h) is a function of the loop calculation process performed to calculate the pulse peaks and pulse troughs.
Optionally, the determining the pulse frequency based on the position value of the pulse peak and the time axis includes:
determining the pulse frequency according to the position value of the intersection of the curve of the pulse peak and the time axis and the following formula (7):
Fi＝WAmf(i+1)-WAmfi……(7)
wherein, FiFor a pulse, AmfiDenotes the ith pulse peak, WAmfiAnd WAmf(i+1)Two of the curve of the ith pulse peak intersecting the time axisA position value.
Optionally, the determining a pulse width, a left pulse width and a right pulse width based on a position value of the pulse peak where the curve intersects with the time axis and the height of the pulse peak includes:
determining two left and right pulse valleys of a pulse peak, determining a minimum value of the pulse valley among the two pulse valleys, determining a difference value between the pulse peak and the minimum value of the pulse valley, determining a half value of the difference value, determining two position values at which a time axis corresponding to the half value intersects with a curve of the pulse peak, determining the difference value between the two position values as a pulse width, determining a difference value between a smaller position value of the two position values and a position value corresponding to the pulse peak as a left pulse width, and determining a difference value between a larger position value of the two position values and a position value corresponding to the pulse peak as a right pulse width.
Optionally, the determining the pulse condition, the left pulse condition, and the right pulse condition based on the pulse peak, the pulse trough, and the pulse amplitude of the initial pulse condition data includes:
determining two adjacent pulse valleys, wherein the pulse valley with a smaller position value corresponding to the two pulse valleys on the time axis is a left pulse valley, and the pulse valley with a larger position value corresponding to the two pulse valleys on the time axis is a right pulse valley;
determining a corresponding position value of the left pulse valley on a time axis and a corresponding position value of the right pulse valley on the time axis;
the pulse condition is determined according to the following equation (8):
wherein S isiFor pulse condition, GpIndicating the position value, G, corresponding to the left pulse valleyqIndicates the position value corresponding to the right pulse valley, AiA pulse amplitude value representing the initial pulse condition data;
the left pulse potential is determined according to the following equation (9):
wherein S isliIndicating the left pulse, GoRepresenting the position value corresponding to the pulse peak;
the right pulse potential is determined according to the following equation (10):
wherein S isriIndicating the right pulse.
8. The method of claim 1, wherein the comparing the array of pulse conditions to be identified with the array of pulse condition samples to determine the pulse conditions corresponding to the array of pulse conditions to be identified comprises:
according to the pulse condition array to be identified, a plurality of groups of pulse condition sample arrays and the following formula (11), determining the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays:
wherein, TxRepresenting the degree of similarity between said array of pulse conditions to be discriminated and said array of pulse condition samples, EltData representing said array of pulse conditions to be discriminated, EytRepresenting data of a group of pulse condition sample arrays, and u represents the number of the data in the pulse condition array to be identified;
comparing the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays to determine the maximum similarity, determining the pulse condition sample array corresponding to the maximum similarity as a target pulse condition sample array, and determining the pulse condition corresponding to the target pulse condition sample array as the pulse condition corresponding to the pulse condition array to be identified.
In one aspect, an apparatus for traditional Chinese medicine pulse condition discrimination based on pulse condition data is provided, the apparatus being applied to an electronic device, the apparatus comprising:
the first acquisition unit is used for acquiring initial pulse condition data to be identified;
the determining unit is used for determining pulse condition data to be identified according to the initial pulse condition data, wherein the pulse condition data to be identified comprises pulse frequency, pulse amplitude, pulse width, left pulse width, right pulse width, pulse position, left pulse position and right pulse position;
the sorting unit is used for forming the pulse condition data to be identified into a one-dimensional array according to a preset sequence to obtain a pulse condition array to be identified;
the second obtaining unit is used for obtaining a pulse condition sample array of pre-stored pulse condition sample data, wherein the pulse condition sample data comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the arrangement sequence of data in the pulse condition sample array is the same as the arrangement sequence of data in the pulse condition array to be identified, and the number of data in the pulse condition sample array is the same as the number of data in the pulse condition sample array to be identified;
and the comparison unit is used for comparing the pulse condition array to be identified with the pulse condition sample array and determining the pulse condition corresponding to the pulse condition array to be identified.
Optionally, the determining unit is configured to:
determining a pulse amplitude value according to the initial pulse condition data;
determining the peak and the valley of the pulse according to the pulse amplitude;
determining pulse times based on the pulse peaks and the position value of a time axis;
determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and a time axis and the height of the pulse peak;
determining a pulse condition, a left pulse condition and a right pulse condition based on the pulse peak, the pulse valley and the pulse amplitude of the initial pulse condition data.
Optionally, the determining unit is configured to:
determining a pulse amplitude value according to an initial pulse amplitude value in the initial pulse condition data and the following formula (1):
Am＝An+Ve×n……(1)
wherein A isnIs a firstThe amplitude of the onset pulse; n is 1, 2, 3, … …; m is 1, 2, 3, … …; veFor adjusting the coefficient of pulse amplitude, Ve＝0.00001。
Optionally, the determining unit is configured to:
determining a first intermediate value according to the following formula (2) based on a preset pulse amplitude threshold coefficient, a maximum pulse amplitude value and a minimum pulse amplitude value:
L＝Ammax-(Ammax-Ammin)×Fm……(2)
determining the pulse amplitude value according to the first intermediate value and the following formula (3):
wherein D ismTaking the pulse amplitude as two values;
determining a binary pulse amplitude difference value according to the binary pulse amplitude and the following formula (4):
wherein E ismThe pulse amplitude binary differential value is obtained;
determining a pulse amplitude difference value according to the initial pulse amplitude value and the following formula (5):
wherein, CmThe pulse amplitude difference value is obtained;
when C is presentm＝1，En>0，Em<At 0, the peak and valley of the pulse are determined according to the following formula (6)
Where h is the cumulative value of the sampling interval time, i is 1, 2, 3, … …, f (h), and g (h) is a function of the loop calculation process performed to calculate the pulse peaks and pulse troughs.
Optionally, the determining unit is configured to:
determining the pulse frequency according to the position value of the intersection of the curve of the pulse peak and the time axis and the following formula (7):
Fi＝WAmf(i+1)-WAmfi……(7)
wherein, FiFor a pulse, AmfiDenotes the ith pulse peak, WAmfiAnd WAmf(i+1)The curve of the ith pulse peak is two position values intersected with the time axis.
Optionally, the determining unit is configured to:
determining two left and right pulse valleys of a pulse peak, determining a minimum value of the pulse valley among the two pulse valleys, determining a difference value between the pulse peak and the minimum value of the pulse valley, determining a half value of the difference value, determining two position values at which a time axis corresponding to the half value intersects with a curve of the pulse peak, determining the difference value between the two position values as a pulse width, determining a difference value between a smaller position value of the two position values and a position value corresponding to the pulse peak as a left pulse width, and determining a difference value between a larger position value of the two position values and a position value corresponding to the pulse peak as a right pulse width.
Optionally, the determining unit is configured to:
determining two adjacent pulse valleys, wherein the pulse valley with a smaller position value corresponding to the two pulse valleys on the time axis is a left pulse valley, and the pulse valley with a larger position value corresponding to the two pulse valleys on the time axis is a right pulse valley;
determining a corresponding position value of the left pulse valley on a time axis and a corresponding position value of the right pulse valley on the time axis;
the pulse condition is determined according to the following equation (8):
wherein S isiFor pulse condition, GpIndicating the position value, G, corresponding to the left pulse valleyqIndicates the position value corresponding to the right pulse valley, AiA pulse amplitude value representing the initial pulse condition data;
the left pulse potential is determined according to the following equation (9):
wherein S isliIndicating the left pulse, GoRepresenting the position value corresponding to the pulse peak;
the right pulse potential is determined according to the following equation (10):
wherein S isriIndicating the right pulse.
Optionally, the alignment unit is configured to:
according to the pulse condition array to be identified, a plurality of groups of pulse condition sample arrays and the following formula (11), determining the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays:
wherein, TxRepresenting the degree of similarity between said array of pulse conditions to be discriminated and said array of pulse condition samples, EltData representing said array of pulse conditions to be discriminated, EytRepresenting data of a group of pulse condition sample arrays, and u represents the number of the data in the pulse condition array to be identified;
comparing the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays to determine the maximum similarity, determining the pulse condition sample array corresponding to the maximum similarity as a target pulse condition sample array, and determining the pulse condition corresponding to the target pulse condition sample array as the pulse condition corresponding to the pulse condition array to be identified.
In one aspect, an electronic device is provided, which includes a processor and a memory, where at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the above method for traditional Chinese medicine pulse condition identification based on pulse condition data.
In one aspect, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the above method for traditional Chinese medicine pulse condition identification based on pulse condition data.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
in the scheme, initial pulse condition data to be identified is obtained, the pulse condition data to be identified is determined according to the initial pulse condition data, the pulse condition data to be identified comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse conditions, left pulse conditions and right pulse conditions, the pulse condition data to be identified are formed into a one-dimensional array according to a preset sequence, a pulse condition array to be identified is obtained, a pre-stored pulse condition sample array of pulse condition sample data is obtained, the pulse condition array to be identified is compared with the pulse condition sample array, and the pulse condition corresponding to the pulse condition array to be identified is determined. Therefore, the pulse condition is identified in a quantitative mode, a lot of external interference is eliminated, and the comparison result is more accurate, so that the traditional Chinese medicine pulse condition is developed from perceptual character description to rational digital description, the traditional Chinese medicine pulse condition can be intuitively told to a doctor after being digitalized, and a brand new means is provided for the doctor to better diagnose and treat the pulse condition.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a diagram of an implementation environment provided by an embodiment of the invention;
FIG. 2 is a flow chart of a method for traditional Chinese medicine pulse condition identification based on pulse condition data according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for Chinese medical pulse condition identification based on pulse condition data according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating initial pulse condition data according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating initial pulse condition data according to an embodiment of the present invention;
FIG. 6 is a block diagram of an apparatus for traditional Chinese medicine pulse condition identification based on pulse condition data according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
The embodiment of the invention provides a traditional Chinese medicine pulse condition identification method based on pulse condition data, and the implementation environment can comprise at least one terminal 101 and a server 102 for providing services for the plurality of terminals 101. At least one terminal 101 is connected to the server 102 through a wireless or wired network, and the plurality of terminals 101 may be computer devices or intelligent terminals, etc. capable of accessing the server 102. For the process of pulse condition identification, the terminal 101 may be provided with an initial pulse condition data acquisition program and a pulse condition data processing program, the server 102 stores a plurality of pulse condition sample arrays, after the terminal 101 obtains the pulse condition array to be identified, the terminal 101 obtains the pulse condition sample array from the server 102, and then the terminal 101 compares the pulse condition array to be identified with the pulse condition sample array.
The embodiment of the invention provides a traditional Chinese medicine pulse condition identification method based on pulse condition data, which can be realized by electronic equipment, wherein the electronic equipment can be a terminal or a server. As shown in fig. 2, the processing flow of the method for traditional Chinese medicine pulse condition identification based on pulse condition data may include the following steps:
And 204, obtaining a pulse condition sample array of pre-stored pulse condition sample data, wherein the pulse condition sample data comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the arrangement sequence of the data in the pulse condition sample array is the same as the arrangement sequence of the data in the pulse condition array to be identified, and the number of the data in the pulse condition sample array is the same as the number of the data in the sample array to be identified.
Optionally, determining the pulse condition data to be identified according to the initial pulse condition data includes:
determining the pulse amplitude according to the initial pulse condition data;
determining the peak and the valley of the pulse according to the pulse amplitude;
determining pulse times based on the position values of the pulse peaks and the time axis;
determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and the time axis and the height of the pulse peak;
determining the pulse condition, the left pulse condition and the right pulse condition based on the pulse peak, the pulse valley and the pulse amplitude of the initial pulse condition data.
Optionally, determining the pulse amplitude from the initial pulse profile data comprises:
determining a pulse amplitude value according to an initial pulse amplitude value in the initial pulse condition data and the following formula (1):
Am＝An+Ve×n……(1)
wherein A isnIs a firstThe amplitude of the onset pulse; n is 1, 2, 3, … …; m is 1, 2, 3, … …; veFor adjusting the coefficient of pulse amplitude, Ve＝0.00001。
Optionally, determining the pulse peak and the pulse valley according to the pulse amplitude comprises:
determining a first intermediate value according to the following formula (2) based on a preset pulse amplitude threshold coefficient, a maximum pulse amplitude value and a minimum pulse amplitude value:
L＝Ammax-(Ammax-Ammin)×Fm……(2)
wherein L is a first intermediate value, FmIs the pulse amplitude threshold coefficient, Fm＝0.4；AmmaxMaximum value of pulse amplitude, AmminIs the minimum value of pulse amplitude;
determining a pulse amplitude value according to the first intermediate value and the following formula (3):
wherein D ismTaking the pulse amplitude as two values;
determining a binary pulse amplitude difference value according to the binary pulse amplitude and the following formula (4):
wherein E ismThe pulse amplitude binary differential value is obtained;
determining a pulse amplitude difference value according to the initial pulse amplitude value and the following formula (5):
wherein, CmThe pulse amplitude difference value is obtained;
when C is presentm＝1，En>0，Em<At 0, determining the pulse peak and the pulse valley according to the following formula (6):
where h is the cumulative value of the sampling interval time, i is 1, 2, 3, … …, f (h), and g (h) is a function of the loop calculation process performed to calculate the pulse peaks and pulse troughs.
Optionally, determining the pulse frequency based on the position values of the pulse peak and the time axis includes:
determining the pulse frequency according to the position value of the intersection of the curve of the pulse peak and the time axis and the following formula (7):
Fi＝WAmf(i+1)-WAmfi……(7)
wherein, FiFor a pulse, AmfiDenotes the ith pulse peak, WAmfiAnd WAmf(i+1)The curve of the ith pulse peak is two position values intersected with the time axis.
Optionally, determining the pulse width, the left pulse width and the right pulse width based on a position value of the curve of the pulse peak intersecting the time axis and the height of the pulse peak, includes:
determining two left and right pulse valleys of a pulse peak, determining a minimum value of the pulse valley in the two pulse valleys, determining a difference value between the pulse peak and the minimum value of the pulse valley, determining a half value of the difference value, determining two position values at which a time axis corresponding to the half value intersects with a curve of the pulse peak, determining the difference value between the two position values as a pulse width, determining the difference value between a smaller position value of the two position values and a position value corresponding to the pulse peak as a left pulse width, and determining the difference value between a larger position value of the two position values and a position value corresponding to the pulse peak as a right pulse width.
Optionally, determining the pulse condition, the left pulse condition, and the right pulse condition based on the pulse peak, the pulse trough, and the pulse amplitude of the initial pulse condition data comprises:
determining two adjacent pulse valleys, wherein the pulse valley with the smaller position value corresponding to the two pulse valleys on the time axis is a left pulse valley, and the pulse valley with the larger position value corresponding to the two pulse valleys on the time axis is a right pulse valley;
determining a position value corresponding to the left pulse valley on the time axis and a position value corresponding to the right pulse valley on the time axis;
the pulse condition is determined according to the following equation (8):
wherein S isiFor pulse condition, GpIndicating the position value, G, corresponding to the left pulse valleyqIndicates the position value corresponding to the right pulse valley, AiA pulse amplitude value representing the initial pulse condition data;
the left pulse potential is determined according to the following equation (9):
wherein S isliIndicating the left pulse, GoRepresenting the position value corresponding to the pulse peak;
the right pulse potential is determined according to the following equation (10):
wherein S isriIndicating the right pulse.
Optionally, comparing the pulse condition array to be identified with the pulse condition sample array to determine the pulse condition corresponding to the pulse condition array to be identified, including:
according to the pulse condition array to be identified, the multiple groups of pulse condition sample arrays and the following formula (11), determining the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays:
wherein, TxRepresenting the similarity between the array of pulse conditions to be discriminated and the array of pulse condition samples, EltData representing an array of pulse conditions to be discriminated, EytData representing an array of pulse condition samples, u representingThe number of data in the pulse condition array to be identified;
comparing the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays to determine the maximum similarity, determining the pulse condition sample array corresponding to the maximum similarity as a target pulse condition sample array, and determining the pulse condition corresponding to the target pulse condition sample array as the pulse condition corresponding to the pulse condition array to be identified.
In the embodiment of the invention, initial pulse condition data to be identified is obtained, the pulse condition data to be identified is determined according to the initial pulse condition data, the pulse condition data to be identified comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the pulse condition data to be identified is formed into a one-dimensional array according to a preset sequence to obtain a pulse condition array to be identified, a pre-stored pulse condition sample array of pulse condition sample data is obtained, the pulse condition array to be identified is compared with the pulse condition sample array, and the pulse condition corresponding to the pulse condition array to be identified is determined. Therefore, the pulse condition is identified in a quantitative mode, a lot of external interference is eliminated, and the comparison result is more accurate, so that the traditional Chinese medicine pulse condition is developed from perceptual character description to rational digital description, the traditional Chinese medicine pulse condition can be intuitively told to a doctor after being digitalized, and a brand new means is provided for the doctor to better diagnose and treat the pulse condition.
The embodiment of the invention provides a traditional Chinese medicine pulse condition identification method based on pulse condition data, which can be realized by electronic equipment, wherein the electronic equipment can be a terminal or a server. As shown in fig. 3, the processing flow of the method for traditional Chinese medicine pulse condition identification based on pulse condition data may include the following steps:
In a possible embodiment, the initial pulse condition data to be identified is pulse condition data directly collected from the wrist of the patient by the collecting device, which may be a pulse collecting device in the prior art, but is not limited thereto.
After the electronic device obtains the initial pulse condition data to be identified, a graph can be drawn according to the beating rhythm of the initial pulse condition data, as shown in fig. 4.
In one possible embodiment, the pulse amplitude is determined based on the initial pulse amplitude in the initial pulse profile data and the following equation (1):
Am＝An+Ve×n……(1)
wherein A isnIs the initial pulse amplitude; n is 1, 2, 3, … …; m is 1, 2, 3, … …; veFor adjusting the coefficient of pulse amplitude, Ve＝0.00001。
Optionally, a pulse amplitude A is obtainedmThereafter, the average value A thereof can be calculated according to the following formula (1a)pThe variance A is calculated according to the following formula (1b)cThe value:
where s is the number of pulse peaks, and m is (1, 2, 3, … …, s).
In one possible embodiment, based on the preset pulse amplitude threshold coefficient, the maximum pulse amplitude value, and the minimum pulse amplitude value, the first intermediate value is determined according to the following formula (2):
L＝Ammax-(Ammax-Ammin)×Fm……(2)
wherein L is a first intermediate value, FmIs the pulse amplitude threshold coefficient, Fm＝0.4；AmmaxMaximum value of pulse amplitude, AmminIs the minimum value of pulse amplitude;
determining a pulse amplitude value according to the first intermediate value and the following formula (3):
wherein D ismTaking the pulse amplitude as two values;
determining a binary pulse amplitude difference value according to the binary pulse amplitude and the following formula (4):
wherein E ismThe pulse amplitude binary differential value is obtained;
determining a pulse amplitude difference value according to the initial pulse amplitude value and the following formula (5):
wherein, CmThe pulse amplitude difference value is obtained;
when C is presentm＝1，En>0，Em<At 0, determining the pulse peak and the pulse valley according to the following formula (6):
where h is the cumulative value of the sampling interval time, i is 1, 2, 3, … …, f (h), and g (h) is a function of the loop calculation process performed to calculate the pulse peaks and pulse troughs.
In one possible embodiment, as shown in the graph of fig. 4, the curve of each pulse peak and the time axis generate two intersection points, the value on the time axis corresponding to the two intersection points is the position value, and the pulse number is determined according to the position value of the intersection of the curve of the pulse peak and the time axis and the following formula (7):
Fi＝WAmf(i+1)-WAmfi……(7)
wherein, FiFor a pulse, AmfiDenotes the ith pulse peak, WAmfiAnd WAmf(i+1)The curve of the ith pulse peak is two position values intersected with the time axis.
Alternatively, after determining the number of pulses, the number of pulses F is calculated according to the following formula (7a)mAverage value of FpThe variance F of the pulse number is calculated according to the following formula (7b)cThe value:
wherein s is the number of pulses, and m is 1, 2, 3, … …, s.
Alternatively, the pulse amplitude threshold may be adjusted based on the pulse number value, specifically, the maximum variable Mcmax of the pulse number (set 60 second measured pulse number) is set to 160, and the minimum variable Mcmin of the pulse number (set 60 second measured pulse number) is set to 40.
If the pulse number is less than Mcmin:
h<＝Mcmin
Fm<1
Fm＝Fm+Fmu
pulse number greater than Mcmax:
h>＝Mcmax
Fm>0
Fm＝Fm+Fml
L′＝Ammax-(Ammax-Ammin)×Fm
where L' is the pulse amplitude to be adjusted.
And step 305, determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and the time axis and the height of the pulse peak.
In one possible embodiment, as shown in fig. 5, two left and right pulse troughs of a pulse peak are determined, then a minimum value of the pulse trough is determined from the two pulse troughs, a difference value between the pulse peak and the minimum value of the pulse trough is determined, a half value of the difference value is determined, two position values where a time axis corresponding to the half value intersects with a curve of the pulse peak are determined, a difference value between the two position values is determined as a pulse width, a difference value between a smaller position value of the two position values and a position value corresponding to the pulse peak is determined as a left pulse width, and a difference value between a larger position value of the two position values and a position value corresponding to the pulse peak is determined as a right pulse width.
In a possible implementation manner, two pulse valleys adjacent to the pulse peak are determined, wherein the corresponding pulse valley with the smaller position value on the time axis of the two pulse valleys is the left pulse valley, and the corresponding pulse valley with the larger position value on the time axis is the right pulse valley;
determining a position value corresponding to the left pulse valley on the time axis and a position value corresponding to the right pulse valley on the time axis;
the pulse condition is determined according to the following equation (8):
wherein S isiFor pulse condition, GpIndicating the position value, G, corresponding to the left pulse valleyqIndicates the position value corresponding to the right pulse valley, AiA pulse amplitude value representing the initial pulse condition data;
the left pulse potential is determined according to the following equation (9):
wherein S isliIndicating the left pulse, GoRepresenting the position value corresponding to the pulse peak;
the right pulse potential is determined according to the following equation (10):
wherein S isriIndicating the right pulse.
Alternatively, after determining the pulse condition, the average value G of the pulse condition is determined according to the following formula (8a)pThe variance G of the pulse condition is calculated according to the following formula (8b)c：
Wherein s is the number of pulse conditions, and m is 1, 2, 3, … …, s.
And 307, forming the pulse condition data to be identified into a one-dimensional array according to a preset sequence to obtain the pulse condition array to be identified.
It should be noted that, each time the pulse condition arrays to be identified are formed, the order and the number of data of each pulse condition array to be identified are the same.
And 308, acquiring a pulse condition sample array of the pre-stored pulse condition sample data.
The pulse condition sample data includes a pulse frequency, a pulse amplitude, a pulse width, a left pulse width, a right pulse width, a pulse condition, a left pulse condition, and a right pulse condition, and the obtaining method of the pulse condition sample data is the same as the obtaining method of the pulse condition array to be identified, and reference may be made to step 301 and step 307, so the arrangement order of the data in the pulse condition sample array is the same as the arrangement order of the data in the pulse condition array to be identified, and the number of the data in the pulse condition sample array is the same as the number of the data in the sample array to be identified, and the specific obtaining method is not described herein.
It should be noted that the pulse condition can be divided into 92 pulse conditions, and the 92 pulse conditions are subjected to sample learning, and the more the number of the learned samples is, the more accurate the pulse clinical syndrome comparison is.
In one possible embodiment, the similarity between the pulse condition array to be identified and each pulse condition sample array is determined according to the pulse condition array to be identified, the multiple pulse condition sample arrays and the following formula (11):
wherein, TxRepresenting the similarity between the array of pulse conditions to be discriminated and the array of pulse condition samples, EltData representing an array of pulse conditions to be discriminated, EytAnd u represents the number of data in the pulse condition array to be identified.
And (3) carrying out similarity calculation on the pulse condition array to be identified and each pulse condition sample array according to the formula (11) to obtain a plurality of similarities, comparing the similarities to determine the maximum similarity, determining the pulse condition sample array corresponding to the maximum similarity as a target pulse condition sample array, and determining the pulse condition corresponding to the target pulse condition sample array as the pulse condition corresponding to the pulse condition array to be identified.
In the embodiment of the invention, initial pulse condition data to be identified is obtained, the pulse condition data to be identified is determined according to the initial pulse condition data, the pulse condition data to be identified comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the pulse condition data to be identified is formed into a one-dimensional array according to a preset sequence to obtain a pulse condition array to be identified, a pre-stored pulse condition sample array of pulse condition sample data is obtained, the pulse condition array to be identified is compared with the pulse condition sample array, and the pulse condition corresponding to the pulse condition array to be identified is determined. Therefore, the pulse condition is identified in a quantitative mode, a lot of external interference is eliminated, and the comparison result is more accurate, so that the traditional Chinese medicine pulse condition is developed from perceptual character description to rational digital description, the traditional Chinese medicine pulse condition can be intuitively told to a doctor after being digitalized, and a brand new means is provided for the doctor to better diagnose and treat the pulse condition.
Fig. 6 is a block diagram of an apparatus for traditional chinese medical pulse condition discrimination based on pulse condition data according to an exemplary embodiment. Referring to fig. 6, the apparatus includes a first obtaining unit 610, a determining unit 620, a sorting unit 630, a second obtaining unit 640, and a comparing unit 650.
A first obtaining unit 610, configured to obtain initial pulse condition data to be identified;
a determining unit 620, configured to determine pulse condition data to be identified according to the initial pulse condition data, where the pulse condition data to be identified includes a pulse frequency, a pulse amplitude, a pulse width, a left pulse width, a right pulse width, a pulse condition, a left pulse condition, and a right pulse condition;
the sorting unit 630 is configured to combine the pulse condition data to be identified into a one-dimensional array according to a preset order, so as to obtain a pulse condition array to be identified;
a second obtaining unit 640, configured to obtain a pulse condition sample array of pre-stored pulse condition sample data, where the pulse condition sample data includes a pulse order, a pulse amplitude, a pulse width, a left pulse width, a right pulse width, a pulse condition, a left pulse condition, and a right pulse condition, an arrangement order of data in the pulse condition sample array is the same as an arrangement order of data in the pulse condition array to be identified, and a number of data in the pulse condition sample array is the same as a number of data in the sample array to be identified;
the comparison unit 650 is configured to compare the pulse condition array to be identified with the pulse condition sample array, and determine a pulse condition corresponding to the pulse condition array to be identified.
Optionally, the determining unit 620 is configured to:
determining a pulse amplitude value according to the initial pulse condition data;
determining the peak and the valley of the pulse according to the pulse amplitude;
determining pulse times based on the pulse peaks and the position value of a time axis;
determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and a time axis and the height of the pulse peak;
determining a pulse condition, a left pulse condition and a right pulse condition based on the pulse peak, the pulse valley and the pulse amplitude of the initial pulse condition data.
Optionally, the determining unit 620 is configured to:
determining a pulse amplitude value according to an initial pulse amplitude value in the initial pulse condition data and the following formula (1):
Am＝An+Ve×n……(1)
wherein A isnIs the initial pulse amplitude; n is 1, 2, 3, … …; m is 1, 2, 3, … …; veFor adjusting the coefficient of pulse amplitude, Ve＝0.00001。
Optionally, the determining unit 620 is configured to:
determining a first intermediate value according to the following formula (2) based on a preset pulse amplitude threshold coefficient, a maximum pulse amplitude value and a minimum pulse amplitude value:
L＝Ammax-(Ammax-Ammin)×Fm……(2)
wherein L is a first intermediate value, FmIs the pulse amplitude threshold coefficient, Fm＝0.4；AmmaxMaximum value of pulse amplitude, AmminIs the minimum value of pulse amplitude;
determining the pulse amplitude value according to the first intermediate value and the following formula (3):
wherein D ismTaking the pulse amplitude as two values;
determining a binary pulse amplitude difference value according to the binary pulse amplitude and the following formula (4):
wherein E ismThe pulse amplitude binary differential value is obtained;
determining a pulse amplitude difference value according to the initial pulse amplitude value and the following formula (5):
wherein, CmThe pulse amplitude difference value is obtained;
when C is presentm＝1，En>0，Em<At 0, the peak and valley of the pulse are determined according to the following formula (6)
Where h is the cumulative value of the sampling interval time, i is 1, 2, 3, … …, f (h), and g (h) is a function of the loop calculation process performed to calculate the pulse peaks and pulse troughs.
Optionally, the determining unit 620 is configured to:
determining the pulse frequency according to the position value of the intersection of the curve of the pulse peak and the time axis and the following formula (7):
Fi＝WAmf(i+1)-WAmfi……(7)
wherein, FiFor a pulse, AmfiDenotes the ith pulse peak, WAmfiAnd WAmf(i+1)The curve of the ith pulse peak is two position values intersected with the time axis.
Optionally, the determining unit 620 is configured to:
determining two left and right pulse valleys of a pulse peak, determining a minimum value of the pulse valley among the two pulse valleys, determining a difference value between the pulse peak and the minimum value of the pulse valley, determining a half value of the difference value, determining two position values at which a time axis corresponding to the half value intersects with a curve of the pulse peak, determining the difference value between the two position values as a pulse width, determining a difference value between a smaller position value of the two position values and a position value corresponding to the pulse peak as a left pulse width, and determining a difference value between a larger position value of the two position values and a position value corresponding to the pulse peak as a right pulse width.
Optionally, the determining unit 620 is configured to:
determining two adjacent pulse valleys, wherein the pulse valley with a smaller position value corresponding to the two pulse valleys on the time axis is a left pulse valley, and the pulse valley with a larger position value corresponding to the two pulse valleys on the time axis is a right pulse valley;
determining a corresponding position value of the left pulse valley on a time axis and a corresponding position value of the right pulse valley on the time axis;
the pulse condition is determined according to the following equation (8):
wherein S isiFor pulse condition, GpIndicating the position value, G, corresponding to the left pulse valleyqIndicates the position value corresponding to the right pulse valley, AiA pulse amplitude value representing the initial pulse condition data;
the left pulse potential is determined according to the following equation (9):
wherein S isliIndicating the left pulse, GoRepresenting the position value corresponding to the pulse peak;
the right pulse potential is determined according to the following equation (10):
wherein S isriIndicating the right pulse.
Optionally, the alignment unit 650 is configured to:
according to the pulse condition array to be identified, a plurality of groups of pulse condition sample arrays and the following formula (11), determining the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays:
wherein, TxRepresenting the degree of similarity between said array of pulse conditions to be discriminated and said array of pulse condition samples, EltRepresenting the array of pulse conditions to be identifiedData of (E), EytRepresenting data of a group of pulse condition sample arrays, and u represents the number of the data in the pulse condition array to be identified;
comparing the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays to determine the maximum similarity, determining the pulse condition sample array corresponding to the maximum similarity as a target pulse condition sample array, and determining the pulse condition corresponding to the target pulse condition sample array as the pulse condition corresponding to the pulse condition array to be identified.
In the embodiment of the invention, initial pulse condition data to be identified is obtained, the pulse condition data to be identified is determined according to the initial pulse condition data, the pulse condition data to be identified comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the pulse condition data to be identified is formed into a one-dimensional array according to a preset sequence to obtain a pulse condition array to be identified, a pre-stored pulse condition sample array of pulse condition sample data is obtained, the pulse condition array to be identified is compared with the pulse condition sample array, and the pulse condition corresponding to the pulse condition array to be identified is determined. Therefore, the pulse condition is identified in a quantitative mode, a lot of external interference is eliminated, and the comparison result is more accurate, so that the traditional Chinese medicine pulse condition is developed from perceptual character description to rational digital description, the traditional Chinese medicine pulse condition can be intuitively told to a doctor after being digitalized, and a brand new means is provided for the doctor to better diagnose and treat the pulse condition.
Fig. 7 is a schematic structural diagram of an electronic device 700 according to an embodiment of the present invention, where the electronic device 700 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 701 and one or more memories 702, where at least one instruction is stored in the memory 702, and the at least one instruction is loaded and executed by the processor 701 to implement the following steps of the method for traditional Chinese medicine pulse condition identification based on pulse condition data:
acquiring initial pulse condition data to be identified;
determining pulse condition data to be identified according to the initial pulse condition data, wherein the pulse condition data to be identified comprises pulse times, pulse amplitude, pulse width, left pulse width, right pulse width, pulse condition, left pulse condition and right pulse condition;
forming a one-dimensional array by the pulse condition data to be identified according to a preset sequence to obtain a pulse condition array to be identified;
acquiring a pulse condition sample array of pre-stored pulse condition sample data, wherein the pulse condition sample data comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse conditions, left pulse conditions and right pulse conditions, the arrangement sequence of data in the pulse condition sample array is the same as that of data in the pulse condition array to be identified, and the number of the data in the pulse condition sample array is the same as that of the data in the sample array to be identified;
and comparing the pulse condition array to be identified with the pulse condition sample array to determine the pulse condition corresponding to the pulse condition array to be identified.
In the embodiment of the invention, initial pulse condition data to be identified is obtained, the pulse condition data to be identified is determined according to the initial pulse condition data, the pulse condition data to be identified comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the pulse condition data to be identified is formed into a one-dimensional array according to a preset sequence to obtain a pulse condition array to be identified, a pre-stored pulse condition sample array of pulse condition sample data is obtained, the pulse condition array to be identified is compared with the pulse condition sample array, and the pulse condition corresponding to the pulse condition array to be identified is determined. Therefore, the pulse condition is identified in a quantitative mode, a lot of external interference is eliminated, and the comparison result is more accurate, so that the traditional Chinese medicine pulse condition is developed from perceptual character description to rational digital description, the traditional Chinese medicine pulse condition can be intuitively told to a doctor after being digitalized, and a brand new means is provided for the doctor to better diagnose and treat the pulse condition.
In an exemplary embodiment, a computer-readable storage medium, such as a memory, including instructions executable by a processor in a terminal, is also provided for performing the above method for tongue state discrimination in traditional Chinese medicine based on a tongue picture clinical picture. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A traditional Chinese medicine pulse condition identification method based on pulse condition data is characterized by comprising the following steps:
acquiring initial pulse condition data to be identified;
determining pulse condition data to be identified according to the initial pulse condition data, wherein the pulse condition data to be identified comprises pulse times, pulse amplitude, pulse width, left pulse width, right pulse width, pulse potential, left pulse potential and right pulse potential;
forming a one-dimensional array by the pulse condition data to be identified according to a preset sequence to obtain a pulse condition array to be identified;
acquiring a pulse condition sample array of pre-stored pulse condition sample data, wherein the pulse condition sample data comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse conditions, left pulse conditions and right pulse conditions, the arrangement sequence of data in the pulse condition sample array is the same as that of data in the pulse condition array to be identified, and the number of data in the pulse condition sample array is the same as that of data in the sample array to be identified;
and comparing the pulse condition array to be identified with the pulse condition sample array to determine the pulse condition corresponding to the pulse condition array to be identified.
2. The method of claim 1, wherein determining pulse profile data to be identified based on the initial pulse profile data comprises:
determining a pulse amplitude value according to the initial pulse condition data;
determining the peak and the valley of the pulse according to the pulse amplitude;
determining pulse times based on the pulse peaks and the position value of a time axis;
determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and a time axis and the height of the pulse peak;
determining a pulse condition, a left pulse condition and a right pulse condition based on the pulse peak, the pulse valley and the pulse amplitude of the initial pulse condition data.
3. The method of claim 2, wherein determining a pulse amplitude value from the initial pulse profile data comprises:
determining a pulse amplitude value according to an initial pulse amplitude value in the initial pulse condition data and the following formula (1):
Am＝An+Ve×n……(1)
wherein A isnIs the initial pulse amplitude; n is 1, 2, 3, … …; m is 1, 2, 3, … …; veFor adjusting the coefficient of pulse amplitude, Ve＝0.00001。
4. The method of claim 3, wherein determining pulse peaks and pulse troughs from the pulse amplitude comprises:
determining a first intermediate value according to the following formula (2) based on a preset pulse amplitude threshold coefficient, a maximum pulse amplitude value and a minimum pulse amplitude value:
L＝Ammax-(Ammax-Ammin)×Fm……(2)
wherein L is a first intermediate value, FmIs the pulse amplitude threshold coefficient, Fm＝0.4；AmmaxMaximum value of pulse amplitude, AmminIs the minimum value of pulse amplitude;
determining the pulse amplitude value according to the first intermediate value and the following formula (3):
wherein D ismTaking the pulse amplitude as two values;
determining a binary pulse amplitude difference value according to the binary pulse amplitude and the following formula (4):
wherein E ismThe pulse amplitude binary differential value is obtained;
determining a pulse amplitude difference value according to the initial pulse amplitude value and the following formula (5):
wherein, CmThe pulse amplitude difference value is obtained;
when C is presentm＝1，En>0，Em<At 0, the peak and valley of the pulse are determined according to the following formula (6)
Where h is the cumulative value of the sampling interval time, i is 1, 2, 3, … …, f (h), and g (h) is a function of the loop calculation process performed to calculate the pulse peaks and pulse troughs.
5. The method of claim 4, wherein determining the pulse frequency based on the position values of the pulse peak and the time axis comprises:
determining the pulse frequency according to the position value of the intersection of the curve of the pulse peak and the time axis and the following formula (7):
Fi＝WAmf(i+1)-WAmfi……(7)
wherein, FiFor a pulse, AmfiThe peak of the ith pulse is shown,WAmfiand WAmf(i+1)The curve of the ith pulse peak is two position values intersected with the time axis.
6. The method of claim 5, wherein determining the pulse width, the left pulse width and the right pulse width based on the position value of the curve of the pulse peak intersecting the time axis and the height of the pulse peak comprises:
determining two left and right pulse valleys of a pulse peak, determining a minimum value of the pulse valley among the two pulse valleys, determining a difference value between the pulse peak and the minimum value of the pulse valley, determining a half value of the difference value, determining two position values at which a time axis corresponding to the half value intersects with a curve of the pulse peak, determining the difference value between the two position values as a pulse width, determining a difference value between a smaller position value of the two position values and a position value corresponding to the pulse peak as a left pulse width, and determining a difference value between a larger position value of the two position values and a position value corresponding to the pulse peak as a right pulse width.
7. The method of claim 6, wherein determining the pulse potential, the left pulse potential, and the right pulse potential based on the pulse peak, the pulse trough, and the pulse amplitude of the initial pulse condition data comprises:
determining two adjacent pulse valleys, wherein the pulse valley with a smaller position value corresponding to the two pulse valleys on the time axis is a left pulse valley, and the pulse valley with a larger position value corresponding to the two pulse valleys on the time axis is a right pulse valley;
determining a corresponding position value of the left pulse valley on a time axis and a corresponding position value of the right pulse valley on the time axis;
the pulse condition is determined according to the following equation (8):
wherein S isiFor pulse condition, GpIndicating the position value, G, corresponding to the left pulse valleyqIndicating correspondence of right pulse and valleyPosition value, AiA pulse amplitude value representing the initial pulse condition data;
the left pulse potential is determined according to the following equation (9):
wherein S isliIndicating the left pulse, GoRepresenting the position value corresponding to the pulse peak;
the right pulse potential is determined according to the following equation (10):
wherein S isriIndicating the right pulse.
8. The method of claim 1, wherein the comparing the array of pulse conditions to be identified with the array of pulse condition samples to determine the pulse conditions corresponding to the array of pulse conditions to be identified comprises:
according to the pulse condition array to be identified, a plurality of groups of pulse condition sample arrays and the following formula (11), determining the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays:
wherein, TxRepresenting the degree of similarity between said array of pulse conditions to be discriminated and said array of pulse condition samples, EltData representing said array of pulse conditions to be discriminated, EytRepresenting data of a group of pulse condition sample arrays, and u represents the number of the data in the pulse condition array to be identified;
comparing the similarity between the pulse condition array to be identified and each group of pulse condition sample arrays to determine the maximum similarity, determining the pulse condition sample array corresponding to the maximum similarity as a target pulse condition sample array, and determining the pulse condition corresponding to the target pulse condition sample array as the pulse condition corresponding to the pulse condition array to be identified.
9. A device for traditional chinese medical pulse condition discrimination based on pulse condition data, said device comprising:
the first acquisition unit is used for acquiring initial pulse condition data to be identified;
the determining unit is used for determining pulse condition data to be identified according to the initial pulse condition data, wherein the pulse condition data to be identified comprises pulse frequency, pulse amplitude, pulse width, left pulse width, right pulse width, pulse position, left pulse position and right pulse position;
the sorting unit is used for forming the pulse condition data to be identified into a one-dimensional array according to a preset sequence to obtain a pulse condition array to be identified;
the second obtaining unit is used for obtaining a pulse condition sample array of pre-stored pulse condition sample data, wherein the pulse condition sample data comprises pulse times, pulse amplitudes, pulse widths, left pulse widths, right pulse widths, pulse potentials, left pulse potentials and right pulse potentials, the arrangement sequence of data in the pulse condition sample array is the same as the arrangement sequence of data in the pulse condition array to be identified, and the number of data in the pulse condition sample array is the same as the number of data in the pulse condition sample array to be identified;
and the comparison unit is used for comparing the pulse condition array to be identified with the pulse condition sample array and determining the pulse condition corresponding to the pulse condition array to be identified.
10. The apparatus of claim 9, wherein the determining unit is configured to:
determining a pulse amplitude value according to the initial pulse condition data;
determining the peak and the valley of the pulse according to the pulse amplitude;
determining pulse times based on the pulse peaks and the position value of a time axis;
determining a pulse width, a left pulse width and a right pulse width based on the position values of the pulse peak and a time axis and the height of the pulse peak;
determining a pulse condition, a left pulse condition and a right pulse condition based on the pulse peak, the pulse valley and the pulse amplitude of the initial pulse condition data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110401491.0A CN113223700B (en) | 2021-04-14 | 2021-04-14 | Traditional Chinese medicine pulse condition identification method and device based on pulse condition data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110401491.0A CN113223700B (en) | 2021-04-14 | 2021-04-14 | Traditional Chinese medicine pulse condition identification method and device based on pulse condition data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113223700A true CN113223700A (en) | 2021-08-06 |
| CN113223700B CN113223700B (en) | 2022-02-08 |
Family
ID=77087219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110401491.0A Active CN113223700B (en) | 2021-04-14 | 2021-04-14 | Traditional Chinese medicine pulse condition identification method and device based on pulse condition data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113223700B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114224297A (en) * | 2022-01-14 | 2022-03-25 | 平安科技（深圳）有限公司 | Pulse condition identification method, device, equipment and storage medium based on pulse characteristics |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1337208A (en) * | 2000-08-15 | 2002-02-27 | 李景唐 | Improved Chinese medical pulse condition detector |
| CN1759804A (en) * | 2005-11-02 | 2006-04-19 | 浙江大学 | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis |
| CN103340609A (en) * | 2013-07-04 | 2013-10-09 | 李文博 | Method for automatically analyzing pulse conditions and extracting characteristics of pulse conditions |
| CN106055896A (en) * | 2016-05-31 | 2016-10-26 | 深圳市中识创新科技有限公司 | TCM (Traditional Chinese Medicine) in-vitro diagnosis method and device |
| WO2019100584A1 (en) * | 2017-11-25 | 2019-05-31 | 深圳市前海安测信息技术有限公司 | Traditional chinese medicine disease prevention management system and method based on traditional chinese medicine four diagnostic instrument |
| CN110974191A (en) * | 2019-12-18 | 2020-04-10 | 深圳市精气生物技术有限公司 | Radial artery waveform data identification algorithm |
-
2021
- 2021-04-14 CN CN202110401491.0A patent/CN113223700B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1337208A (en) * | 2000-08-15 | 2002-02-27 | 李景唐 | Improved Chinese medical pulse condition detector |
| CN1759804A (en) * | 2005-11-02 | 2006-04-19 | 浙江大学 | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis |
| CN103340609A (en) * | 2013-07-04 | 2013-10-09 | 李文博 | Method for automatically analyzing pulse conditions and extracting characteristics of pulse conditions |
| CN106055896A (en) * | 2016-05-31 | 2016-10-26 | 深圳市中识创新科技有限公司 | TCM (Traditional Chinese Medicine) in-vitro diagnosis method and device |
| WO2019100584A1 (en) * | 2017-11-25 | 2019-05-31 | 深圳市前海安测信息技术有限公司 | Traditional chinese medicine disease prevention management system and method based on traditional chinese medicine four diagnostic instrument |
| CN110974191A (en) * | 2019-12-18 | 2020-04-10 | 深圳市精气生物技术有限公司 | Radial artery waveform data identification algorithm |
Non-Patent Citations (3)
| Title |
|---|
| 刘峰等: "新型全方位脉象仪设计方案", 《现代科学仪器》 * |
| 周持恒: "基于多种信息处理技术的中医脉诊信息提取与识别的研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
| 李景唐: "中医脉象的客观描述和检测", 《中国医疗器械杂志》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114224297A (en) * | 2022-01-14 | 2022-03-25 | 平安科技（深圳）有限公司 | Pulse condition identification method, device, equipment and storage medium based on pulse characteristics |
| CN114224297B (en) * | 2022-01-14 | 2023-07-11 | 平安科技（深圳）有限公司 | Pulse condition identification method, device, equipment and storage medium based on pulse characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113223700B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hammad et al. | A novel two-dimensional ECG feature extraction and classification algorithm based on convolution neural network for human authentication | |
| CN109276241B (en) | Pressure identification method and equipment | |
| CN111095232B (en) | Discovery of genomes for use in machine learning techniques | |
| CN109117730A (en) | Electrocardiogram auricular fibrillation real-time judge method, apparatus, system and storage medium | |
| CN103034837B (en) | Characteristic parameter is associated with pulse condition key element | |
| US11213240B2 (en) | Identifying ECG signals having the same morphology | |
| CN108324271B (en) | Electrocardiosignal identification method and system and electrocardiosignal monitoring equipment | |
| CN110432895B (en) | Training data processing method, electrocardiographic waveform detection method and electronic equipment | |
| CN111739647B (en) | Magnetic resonance image-based bipolar disorder suicide risk prediction method and related device | |
| CN110786849B (en) | Electrocardiosignal identity recognition method and system based on multi-view discriminant analysis | |
| CN110033432B (en) | Urinary calculus component analysis method and system based on machine learning and energy spectrum CT | |
| CN113223700B (en) | Traditional Chinese medicine pulse condition identification method and device based on pulse condition data | |
| Jaafar et al. | Acceleration plethysmogram based biometric identification | |
| Cordoș et al. | ECG signal classification using convolutional neural networks for biometric identification | |
| CN112529918B (en) | Method, device and equipment for segmenting brain room area in brain CT image | |
| CN115251856B (en) | Pulse strength judging method and device, electronic equipment and storage medium | |
| CN107837083A (en) | J ripple automatic testing methods based on least square method supporting vector machine | |
| JP3647970B2 (en) | Region extraction device | |
| CN116451110A (en) | Blood glucose prediction model construction method based on signal energy characteristics and pulse period | |
| RU2461877C1 (en) | Method for neural network analysis of cardial condition | |
| Du et al. | Curriculum classification network based on margin balancing multi-loss and ensemble learning | |
| CN111345815B (en) | Method, device, equipment and storage medium for detecting QRS wave in electrocardiosignal | |
| CN109394197B (en) | Heart rate variability measuring method, device and equipment based on time-frequency analysis | |
| CN110786839A (en) | Method, device, equipment and medium for generating instantaneous waveform-free ratio | |
| CN113712525A (en) | Physiological parameter processing method and device and medical equipment |
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 |