CN110322961B - Traditional Chinese medicine viscera syndrome differentiation quantitative method and device based on symptom degree - Google Patents
Traditional Chinese medicine viscera syndrome differentiation quantitative method and device based on symptom degree Download PDFInfo
- Publication number
- CN110322961B CN110322961B CN201910547481.0A CN201910547481A CN110322961B CN 110322961 B CN110322961 B CN 110322961B CN 201910547481 A CN201910547481 A CN 201910547481A CN 110322961 B CN110322961 B CN 110322961B
- Authority
- CN
- China
- Prior art keywords
- matrix
- value
- viscera
- symptom
- symptoms
- 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
- 208000024891 symptom Diseases 0.000 title claims abstract description 152
- 210000001835 viscera Anatomy 0.000 title claims abstract description 80
- 208000011580 syndromic disease Diseases 0.000 title claims abstract description 40
- 239000003814 drug Substances 0.000 title claims abstract description 34
- 230000004069 differentiation Effects 0.000 title claims abstract description 30
- 238000004445 quantitative analysis Methods 0.000 title claims abstract description 10
- 239000013598 vector Substances 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000009278 visceral effect Effects 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 138
- 238000004364 calculation method Methods 0.000 claims description 43
- 210000000056 organ Anatomy 0.000 claims description 17
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000007812 deficiency Effects 0.000 description 12
- 210000003734 kidney Anatomy 0.000 description 10
- 210000000232 gallbladder Anatomy 0.000 description 7
- 210000002216 heart Anatomy 0.000 description 7
- 210000002429 large intestine Anatomy 0.000 description 7
- 210000004185 liver Anatomy 0.000 description 7
- 210000004072 lung Anatomy 0.000 description 7
- 210000000813 small intestine Anatomy 0.000 description 7
- 210000000952 spleen Anatomy 0.000 description 7
- 210000002784 stomach Anatomy 0.000 description 7
- 206010019233 Headaches Diseases 0.000 description 6
- 231100000869 headache Toxicity 0.000 description 6
- 206010063659 Aversion Diseases 0.000 description 3
- 206010011224 Cough Diseases 0.000 description 3
- 244000241872 Lycium chinense Species 0.000 description 3
- 235000015468 Lycium chinense Nutrition 0.000 description 3
- 206010028748 Nasal obstruction Diseases 0.000 description 3
- 208000002193 Pain Diseases 0.000 description 3
- 208000006673 asthma Diseases 0.000 description 3
- 239000011248 coating agent Substances 0.000 description 3
- 238000000576 coating method Methods 0.000 description 3
- 208000011726 slow pulse Diseases 0.000 description 3
- 206010041232 sneezing Diseases 0.000 description 3
- 210000004243 sweat Anatomy 0.000 description 3
- 206010039101 Rhinorrhoea Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000020169 heat generation Effects 0.000 description 2
- 208000010753 nasal discharge Diseases 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 235000008216 herbs Nutrition 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Complex Calculations (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a traditional Chinese medicine viscera syndrome differentiation quantitative method and a device based on symptom degrees, wherein the method comprises the following steps: step 1, obtaining a symptom group, and determining the magnitude of the attribute of each symptom in the symptom group, wherein the magnitude of the attribute comprises: degree of symptom value, primary and secondary value of symptom; step 2, obtaining a ranking value of which the Boolean value of the eight classes and the viscera corresponding to the symptoms is 1; step 3, calculating the coefficient beta of the eight-dimensionals and the visceral parameters corresponding to the symptomsnm(ii) a Step 4, constructing a first two-dimensional data table A1 with symptoms of rows, eight lines and viscera as columns; step 5, calculating the maximum characteristic value and the corresponding characteristic vector thereof through a two-dimensional data table A1; step 6, sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2; and 7, calculating the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimensionals and the viscera.
Description
Technical Field
The invention relates to the field of traditional Chinese medicine syndrome differentiation, in particular to a traditional Chinese medicine viscera syndrome differentiation quantitative method and a device based on symptom degrees.
Background
The syndrome differentiation 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 judgment (syndrome differentiation) on the symptom and sign of the patient, and then determine a treatment scheme (treatment). In clinical practice, there are the saying that the herbs do not leave the prescription, the prescription does not leave the syndrome, and the syndrome does not leave the symptom, and the syndrome seems to play a bridge role between the prescription and the symptom. 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 zang-fu organs of traditional Chinese medicine are differentiated by eight principles, five zang organs and six fu organs, each of which has its attributes, for example, eight principles (yin, yang, exterior, interior, cold, heat, deficiency and excess), five zang organs (heart, liver, spleen, lung and kidney), six fu organs (stomach, large intestine, small intestine, triple energizer, bladder and gallbladder).
In the past, the syndrome differentiation of TCM has been described by words of perceptual knowledge, such as half exterior and half interior, exterior cold and interior heat, exterior excess and interior deficiency, excess cold, excess heat, deficiency cold, and the like. With the rapid development of modern science and technology, especially the advent of computers, it is a necessary way to realize the development of traditional Chinese medicine syndrome differentiation from perceptual character description to rational digital description. After the traditional Chinese medicine syndrome differentiation and digitization, the change degree of the illness state (syndrome) of a patient can be intuitively told to a doctor.
Disclosure of Invention
In view of this, the embodiment of the present invention provides a method and a device for quantitative differentiation of visceral syndromes in traditional Chinese medicine based on symptom degrees, which can intuitively tell doctors how the patients' conditions (syndromes) change.
A Chinese medicine viscera dialectical quantification method based on symptom degrees comprises the following steps:
step 1, obtaining a symptom group, and determining the magnitude of the attribute of each symptom in the symptom group, wherein the magnitude of the attribute comprises: degree of symptom value, primary and secondary value of symptom;
step 2, obtaining a ranking value of which the Boolean value of the eight classes and the viscera corresponding to the symptoms is 1;
step 3, calculating the coefficient beta of the parameters of the eight classes and the viscera corresponding to the symptoms according to the degree value of the symptoms, the primary and secondary values of the symptoms and the Boolean value of the eight classes and the viscera corresponding to the symptoms as 1nm；
Step 4, according to the coefficient beta of the eight-dimensionals and the zang-fu organ parameters corresponding to the symptomsnmConstructing a first two-dimensional data table A1 with symptoms as rows, eight lines and viscera as columns;
step 5, calculating the maximum characteristic value and the corresponding characteristic vector thereof through a two-dimensional data table A1;
step 6, sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2;
and 7, calculating the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimensionals and the viscera.
A traditional Chinese medicine viscera syndrome differentiation quantitative device based on symptom degrees comprises:
a first obtaining unit that obtains a symptom group, determines a magnitude of an attribute of each symptom within the symptom group, the magnitude of the attribute including: degree of symptom value, primary and secondary value of symptom;
a second obtaining unit for obtaining the ranking value of Boolean value of 1 corresponding to the eight classes and viscera;
first calculation Unit, rootCalculating the coefficient beta of the eight classes and the viscera parameters corresponding to the symptoms according to the degree of the symptoms, the primary and secondary values of the symptoms and the Boolean value of the eight classes and the viscera corresponding to the symptoms as 1nm；
A first constructing unit for constructing a coefficient beta of the eight-dimensionals and the visceral parameters according to the symptomsnmConstructing a first two-dimensional data table A1 with symptoms as rows, eight lines and viscera as columns;
the second calculation unit is used for calculating the maximum characteristic value and the corresponding characteristic vector through the two-dimensional data table A1;
the sorting unit is used for sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2;
and the third calculating unit calculates the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimentional system and the viscera.
The invention digitalizes the syndrome differentiation result of the traditional Chinese medicine, and can intuitively tell doctors about the change degree of the illness state (syndrome) of patients.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of the method for the quantitative differentiation of visceral syndromes according to the present invention;
FIG. 2 is a schematic view of a flow chart of a method for quantifying visceral syndrome differentiation in traditional Chinese medicine based on symptom degree according to an application scenario of the present invention;
FIG. 3 is a schematic diagram of the symptom level and primary and secondary selections of an application of the present invention.
Fig. 4a, 4b, 4c and 4d are schematic views showing the data of eight classes, five zang organs and six fu organs calculated by the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For convenience of description, the above devices are described separately in terms of functional division into various units/modules. Of course, the functionality of the units/modules may be implemented in one or more software and/or hardware implementations of the invention.
As shown in FIG. 1, a Chinese medicine viscera syndrome differentiation quantitative method based on symptom degrees comprises the following steps:
step 1, obtaining a symptom group, and determining the magnitude of the attribute of each symptom in the symptom group, wherein the magnitude of the attribute comprises: degree of symptom value, primary and secondary value of symptom;
step 2, obtaining a ranking value of which the Boolean value of the eight classes and the viscera corresponding to the symptoms is 1;
step 3, calculating the coefficient beta of the parameters of the eight classes and the viscera corresponding to the symptoms according to the degree value of the symptoms, the primary and secondary values of the symptoms and the Boolean value of the eight classes and the viscera corresponding to the symptoms as 1nm；
The step 3 specifically includes:
βnm＝Y1×Ci×Zj
wherein the symptom degree value is CiThe primary value of the symptom is ZjN represents the serial number of symptoms, m represents the serial numbers of eight classes and viscera;
wherein,
in the formula, n is 1, 2, 3, 4 and … are ranking values of which the Boolean values of 19 octaves and viscera parameters corresponding to symptoms in the viscera database are 1; when the Boolean value is 1, the sorting value is obtained, and when the Boolean value is 0, the sorting value is not obtained.
Step 4, according to the coefficient beta of the eight-dimensionals and the zang-fu organ parameters corresponding to the symptomsnmConstructing a first two-dimensional data table A1 with symptoms as rows, eight lines and viscera as columns;
step 5, calculating the maximum characteristic value and the corresponding characteristic vector thereof through a two-dimensional data table A1;
the step 5 comprises the following steps:
step 51, carrying out standardized calculation on the data based on a first two-dimensional data table A1;
step 52, generating a first matrix B through a standardization technology;
step 53, generating a transposed matrix B based on the first matrix BT；
Step 54, the first matrix B and the transposed matrix BTMultiplying to obtain a square matrix C;
step 55, calculating the data of the area above the diagonal of the square matrix C to obtain the maximum value | VmaxL, according to the absolute value number of the maximum value, finding out the row number p and the column number q of the matrix C where the maximum value is located;
step 56, obtaining data of the row number p and the column number q of the C matrix, namely: deltapp、δqq、δpqAfter the value is obtained, calculating Jcos and Jsin values;
step 57, based on the Jcos and Jsin values, an identity matrix E and a transpose matrix E are establishedTThe corresponding Jcos and Jsin values of p rows and q columns are substituted into the matrices E and ETPerforming the following steps;
calculating Cj ═ ETAfter multiplying the multiplied matrix by the multiplied matrix of XCxE, replacing the original matrix C data with the result;
step 58, proceed | V based on matrix C datamaxI, iterative computation; setting the iterative calculation precision to b 0.000001 if | VmaxIf the | is less than b, the data iterative computation is ended; finding out the maximum characteristic value and the characteristic vector value of the corresponding column from the diagonal line of the C matrix;
step 59, if the characteristic vector value has data less than zero, floating the progress data of the characteristic vector data, and sorting the characteristic vector after the processing is finished;
G＝[T1，T2，T3，T4，T5，...]
step 510, based on the maximum value of the feature vectors (T1) as the numerator, each feature vector is calculated as the denominator, with the result:
in step 511, a two-dimensional matrix a2 is constructed based on the H one-dimensional matrix.
In step 51, the data minus the mean is divided by the standard deviation, and the formula is:
wherein: p is the average value of the two-dimensional matrix array, V is the standard deviation of the two-dimensional matrix array, and X is data of a certain row and a certain column of the two-dimensional matrix array;
the first matrix B of step 52 is
The transposed matrix B of the step 5TIs composed of
The step 54 is specifically
The step 56 specifically includes:
if deltapp＝δqqCalculating Jcos and Jsin values, wherein Je is an intermediate variable;
Jcos＝Cos(Je)
Jsin＝Sin(Je)
if δ pp ≠ δ qq, then calculate Jcos and Jsin values, where CiAnd Tc isAn intermediate variable;
the step 57 is specifically:
step 6, sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2;
and 7, calculating the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimensionals and the viscera.
The step 7 specifically comprises the following steps:
the calculation result of the first two-dimensional data table a1 is:
the calculation result of the second two-dimensional data table a2 is:
K2＝[θ1，θ2，θ3，...，m]；
the weight value calculation formula of the eight classes and viscera is as follows:
the following describes an application scenario of the present invention. The invention provides a Chinese medicine viscera syndrome differentiation quantitative method based on symptom degrees, which can determine 19 parameter weights related to Chinese medicine viscera syndrome differentiation according to the interrelation between the symptom degrees and the eight classes (yin, yang, exterior, interior, cold, heat, deficiency and excess) five organs (heart, liver, spleen, lung and kidney) and six entrails (stomach, large intestine, small intestine, triple energizer, bladder and gallbladder).
FIG. 2 is a schematic view of a flow chart of a method for quantifying visceral syndrome differentiation in traditional Chinese medicine based on symptom degree according to an application scenario of the present invention; FIG. 3 is a schematic diagram of the symptom level and primary and secondary selections of an application of the present invention. Fig. 4a, 4b, 4c and 4d are schematic views showing the data of eight classes, five zang organs and six fu organs calculated by the present invention. Described below in conjunction with the figures. The method comprises the following steps:
obtaining symptom attributes and magnitudes, comprising: degree (mild 2.36, moderate 6.18, severe 8.54); major and minor (major symptom 10, minor symptom 3.82, and concomitant symptom 1.46);
obtaining Boolean values and their ordering of the symptoms corresponding to the zang-fu organs in traditional Chinese medicine, which comprises: a class eight boolean value, a viscera boolean value, a six-fu boolean value;
after each attribute is obtained, performing logic formula calculation on Boolean values, sorting and symptom degree values and primary and secondary accompanying values of yin, yang, exterior, interior, cold, heat, deficiency, excess, heart, liver, spleen, lung, kidney, stomach, large intestine, small intestine, triple energizer, bladder and gallbladder corresponding to each symptom in the symptom group to obtain a two-dimensional data table A1 with the symptoms of rows and viscera as columns;
calculating a maximum characteristic value and a corresponding characteristic vector thereof through the two-dimensional data table;
then sorting the eigenvectors (symptoms) corresponding to the maximum eigenvalues to obtain a new two-dimensional data table A2;
the sum-product method of the hierarchical method is used for calculating A1 and A2, and finally the weight values of 19 parameters of the viscera in the traditional Chinese medicine are obtained.
The following is a detailed description.
A Chinese medicine viscera dialectical quantitative method and a system based on symptom degrees comprise: obtaining a symptom group, and determining each symptom attribute in the symptom group, wherein the attributes comprise: degree, primary and secondary; acquiring coefficients of 19 parameters of yin, yang, exterior, interior, cold, heat, deficiency, excess, heart, liver, spleen, lung, kidney, stomach, large intestine, small intestine, triple energizer, bladder and gallbladder in an viscera database corresponding to symptoms; calculating symptom and viscera data to obtain a two-dimensional data table; calculating the maximum eigenvalue of the two-dimensional data table and the corresponding eigenvector for sorting; and calculating the weight of the two-dimensional data table by a sum-product method of a hierarchical method.
The degree of symptoms is divided into three levels: mild, moderate, and severe. The quantization value settings for the degree are: mild equals 2.36, moderate equals 6.18, and severe equals 8.54.
The symptoms are divided into three levels: major symptoms, minor symptoms and concomitant symptoms. The primary and secondary quantization settings are: the primary symptom equals 10, the secondary symptom equals 3.82 and the secondary symptom equals 1.46.
Based on Boolean values of the eight classes and viscera corresponding to symptoms in the database and the sequence thereof, the method for calculating the coefficients of the parameters of the symptoms corresponding to yin, yang, exterior, interior, cold, heat, deficiency, excess, heart, liver, spleen, lung, kidney, stomach, large intestine, small intestine, triple energizer, bladder and gallbladder 19 is as follows:
firstly, calculating the value formula of eight classes corresponding to symptoms and the viscera coefficient Y1 in a database:
in the formula, n is 1, 2, 3, 4 and … are ranking values of 19 parameters corresponding to symptoms in the viscera database, and the Boolean values of the parameters are 1. When the Boolean value is 1, the sorting value is obtained, and when the Boolean value is 0, the sorting value is not obtained.
Secondly, calculating the coefficient beta of the corresponding viscera parameters of the symptomsnmValue formula:
βnm＝Y1×Ci×Zj
wherein, the symptom degree value is CiLet the primary and secondary symptom values be ZjThe n rows represent the number of symptoms, and the m columns represent the visceral parameters.
A two-dimensional data table is formed based on symptoms and viscera.
A matrix A1 is obtained by using 19 parameters of viscera based on a two-dimensional data table of symptoms and viscera composition.
The data were normalized based on the matrix a1 by subtracting the mean from the data and dividing by the standard deviation, the formula is:
wherein: p is the average value of the two-dimensional matrix array, V is the standard deviation of the two-dimensional matrix array, and X is data of a certain row and a certain column of the two-dimensional matrix array.
Obtaining matrix B by normalization techniques
Generating a transposed matrix B based on the matrix BT。
Based on matrices B and BTThe multiplication results in a square matrix C.
Maximum value | V is calculated based on area data diagonally (from left and right) above matrix CmaxAnd finding out the row (represented by p) and the column (represented by q) of the matrix C where the maximum value is located according to the absolute value number of the maximum value.
Obtain C matrix p (number of rows) q (number of columns) data, i.e.: deltapp、δqq、δpqAfter the value, Jcos and Jsin values are calculated.
Establishing an identity matrix E and a transposed matrix E based on Jcos and Jsin valuesTThe corresponding Jcos and Jsin values of p rows and q columns are substituted into the matrices E and ETIn (1). Calculating Cj ═ ETAnd multiplying the multiplied matrix by the multiplied matrix multiplied by the multiplied by.
Performing | V based on matrix C datamaxAnd | iteratively calculating. Setting the iterative calculation precision to b 0.000001 if | VmaxIf the | is less than b, the data iteration calculation is finished, and the maximum characteristic value and the characteristic vector value of the corresponding column can be found from the diagonal line of the C matrix. And if the characteristic vector value has data smaller than zero, floating the progress data of the characteristic vector data, and sequencing the characteristic vector after the processing is finished.
G＝[T1，T2，T3，T4，T5，...]
Based on the maximum value of the feature vectors (T1) as the numerator, each feature vector is calculated as the denominator with the result:
a two-dimensional matrix a2 is constructed based on the H one-dimensional matrix. And thirdly, multiplying and summing the eigenvector generated by A2 and the eigenvector generated by A1 to finally obtain the weight of 19 parameters of the viscera in the traditional Chinese medicine by using a sum-product calculation rule to firstly obtain the eigenvector of a decision layer of the two-dimensional matrix A2 and secondly obtain the eigenvector of a target layer of the two-dimensional matrix A1.
The invention aims to solve the technical problem of a traditional Chinese medicine viscera syndrome differentiation quantitative method and a traditional Chinese medicine viscera syndrome differentiation quantitative system based on symptom degrees, and solves the problems that the traditional syndrome differentiation in the prior art can only describe the symptoms of a patient by characters and the change of a plurality of symptoms cannot be described in detail.
The invention provides a Chinese medicine viscera syndrome differentiation quantitative method based on symptom degree, which comprises the following steps:
the degree of symptoms was classified into mild, moderate and severe, and was assigned a value of CMild degree of＝2.36、COf moderate degree＝6.18、CSevere degree＝8.54。
The symptoms are divided into major symptoms, minor symptoms and concomitant symptoms, and the value is ZPrincipal symptoms＝10、ZThe secondary symptoms＝3.82、ZAccompanying disease＝1.46。
The symptoms in the database correspond to Boolean values of eight classes and viscera and their ordering, i.e. the symptoms correspond to 19 coefficients of yin, yang, exterior, interior, cold, heat, deficiency, excess, heart, liver, spleen, lung, kidney, stomach, large intestine, small intestine, triple energizer, bladder and gallbladder. The specific calculation method is as follows: the Y1 value is first calculated.
The syndrome corresponds to the coefficient beta of the eight classes and the zang-fu organs parametersnmThe calculation formula of (2) is:
βnm＝Y1×Ci×Zj
wherein, the symptom degree value is CiLet the primary and secondary symptom values be ZjThe n rows represent the symptoms, and the m columns represent the visceral parameters.
The symptoms and the data after calculation of the eight classes and the viscera are put into a two-dimensional matrix table:
the two-dimensional matrix of symptoms and the combination of the eight classes and the zang-fu organs is denoted by A1:
the matrix a1 normalizes the data by subtracting the mean value from the data and dividing by the standard deviation, where:
p is the average value of the two-dimensional matrix array;
v is the standard deviation of the two-dimensional matrix array;
x is a certain row and a certain column of data of a two-dimensional matrix column.
Calculating to obtain a matrix B
Matrix B generates a transposed matrix BT。
Matrices B and BTThe multiplication results in a square matrix C.
The maximum value | V is calculated for the area data diagonally above (from left to right) the matrix CmaxAnd finding out the row (p represents) and the column (q represents) of the matrix C where the maximum value is located according to the absolute value number of the maximum value.
Obtain C matrix p (number of rows) q (number of columns) data, i.e.: deltapp、δqq、δpqCalculating Jcos and Jsin values after the value, and calculatingThe calculation method comprises the following steps:
if deltapp＝δqqThen the Jcos and Jsin values are calculated with Je intermediate variables.
Jcos＝Cos(Je)
Jsin＝Sin(Je)
Calculating Jcos and Jsin values if δ pp ≠ δ qq, where CiAnd TcAn intermediate variable.
Calculating Jcos and Jsin values to establish an identity matrix E and a transposed matrix ETThe corresponding Jcos and Jsin values of p rows and q columns are substituted into the matrices E and ETIn (1). Calculating Cj ═ ETAnd multiplying the multiplied matrix by the multiplied matrix multiplied by the multiplied by.
Matrix C data go on | VmaxAnd | iteratively calculating. Setting the iterative calculation precision to b 0.000001 if | VmaxIf the | is less than b, the data iteration calculation is finished, and the maximum characteristic value and the characteristic vector value of the corresponding column can be found from the diagonal line of the C matrix. If specialIf the eigenvector value has data smaller than zero, floating up the progress data of the eigenvector data, and sorting the eigenvector after the processing is finished.
G＝[T1，T2，T3，T4，T5，...]
The maximum value of the feature vectors (T1) is taken as the numerator, and each feature vector is taken as the denominator and the result is calculated as:
the H one-dimensional matrix constructs a two-dimensional matrix a 2. And thirdly, multiplying and summing the eigenvector generated by A2 and the eigenvector generated by A1 to finally obtain the weight of 19 parameters of the viscera in the traditional Chinese medicine by using a sum-product calculation rule to firstly obtain the eigenvector of a decision layer of the two-dimensional matrix A2 and secondly obtain the eigenvector of a target layer of the two-dimensional matrix A1. The specific calculation method is as follows:
the calculation result of the A2 feature vector is:
K2＝[θ1，θ2，θ3，...，m]
the calculation result of the A1 feature vector is:
the traditional Chinese medicine viscera weight value calculation formula is as follows:
the technical scheme of the invention has the following beneficial effects:
in the scheme, the weight value is calculated by the five viscera (heart, liver, spleen, lung and kidney) of the eight classes (yin, yang, exterior, interior, cold, heat, deficiency and excess) and the six bowels (stomach, large intestine, small intestine, triple energizer, bladder and gallbladder) to provide a powerful measure for the differentiation of the syndromes of the internal organs of doctors.
Another application scenario of the present invention is described below.
The method for calculating the eight-class and viscera coefficient Y1 corresponding to the symptoms in the database comprises the following steps:
calculating Y1 value formula'
Secondly, calculating the coefficient beta of the corresponding viscera parameters of the symptomsnmThe value is obtained.
The two-dimensional matrix of symptoms and the combination of the eight classes and the zang-fu organs is denoted by A1:
calculating to obtain a matrix B
Matrix B
Matrix B generates a transposed matrix BT。
B matrix
BTMatrix array
Matrices B and BTThe multiplication results in a square matrix C.
C matrix
| 19.7475 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0216 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.5515 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 3.7167 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 18.9249 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.9436 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 44.5526 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 6.5417 |
The maximum value | V is calculated for the area data diagonally above (from left to right) the matrix CmaxAnd finding out the row (p represents) and the column (q represents) of the matrix C where the maximum value is located according to the absolute value number of the maximum value.
C matrix calculation result
| 0.0000 | 5.0000 | 7.0000 | 44.5526 | 18.9249 | 0.0000 | 0.0000 | 1.0000 |
| Absolute maximum value | Line number | Column number | pp | pq | Jcos | Jsin |
C matrix upper left corner calculation data
| 0.0000 | 1.0000 | 1.0000 | 2.0000 | 0.0000 |
| 0.0000 | 2.0000 | 1.0000 | 3.0000 | 0.0000 |
| 0.0000 | 3.0000 | 1.0000 | 4.0000 | 0.0000 |
| 0.0000 | 4.0000 | 1.0000 | 5.0000 | 0.0000 |
| 0.0000 | 5.0000 | 1.0000 | 6.0000 | 0.0000 |
| 0.0000 | 6.0000 | 1.0000 | 7.0000 | 0.0000 |
| 0.0000 | 7.0000 | 1.0000 | 8.0000 | 0.0000 |
| 0.0000 | 8.0000 | 2.0000 | 3.0000 | 0.0000 |
| 0.0000 | 9.0000 | 2.0000 | 4.0000 | 0.0000 |
| 0.0000 | 10.0000 | 2.0000 | 5.0000 | 0.0000 |
| 0.0000 | 11.0000 | 2.0000 | 6.0000 | 0.0000 |
| 0.0000 | 12.0000 | 2.0000 | 7.0000 | 0.0000 |
| 0.0000 | 13.0000 | 2.0000 | 8.0000 | 0.0000 |
| 0.0000 | 14.0000 | 3.0000 | 4.0000 | 0.0000 |
| 0.0000 | 15.0000 | 3.0000 | 5.0000 | 0.0000 |
| 0.0000 | 16.0000 | 3.0000 | 6.0000 | 0.0000 |
| 0.0000 | 17.0000 | 3.0000 | 7.0000 | 0.0000 |
| 0.0000 | 18.0000 | 3.0000 | 8.0000 | 0.0000 |
| 0.0000 | 19.0000 | 4.0000 | 5.0000 | 0.0000 |
| 0.0000 | 20.0000 | 4.0000 | 6.0000 | 0.0000 |
| 0.0000 | 21.0000 | 4.0000 | 7.0000 | 0.0000 |
| 0.0000 | 22.0000 | 4.0000 | 8.0000 | 0.0000 |
| 0.0000 | 23.0000 | 5.0000 | 6.0000 | 0.0000 |
| 0.0000 | 24.0000 | 5.0000 | 7.0000 | 0.0000 |
| 0.0000 | 25.0000 | 5.0000 | 8.0000 | 0.0000 |
Calculating Jcos and Jsin values to establish an identity matrix E and a transposed matrix ETThe corresponding Jcos and Jsin values of p rows and q columns are substituted into the matrices E and ETIn (1). Calculating Cj ═ ETAnd multiplying the multiplied matrix by the multiplied matrix multiplied by the multiplied by.
ETMatrix array
| 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | -1.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0000 |
C matrix
| 19.7475 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0216 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.5515 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 3.7167 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 18.9249 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.9436 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 44.5526 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 6.5417 |
E matrix
| 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | -1.0000 | 0.0000 | 0.0000 | 0.0000 |
| 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0000 |
Matrix C data go on | VmaxAnd | iteratively calculating. Setting the iterative calculation precision to b 0.000001 if | VmaxIf the | is less than b, the data iteration calculation is finished, and the maximum characteristic value and the characteristic vector value of the corresponding column can be found from the diagonal line of the C matrix. And if the characteristic vector value has data smaller than zero, floating the progress data of the characteristic vector data, and sequencing the characteristic vector after the processing is finished.
G＝[T1，T2，T3，T4，T5，...]
Symptom feature vector:
| 1.7089 | without sweat | Z1 |
| 4.9243 | Headache (headache) | Z2 |
| 4.5877 | Body pain | Z3 |
| 0.5873 | Thin and white coating | Z4 |
| 1.1274 | Sneezing | Z5 |
| 1.9481 | Superficial and tense pulse | Z6 |
| 1.9634 | Superficial and slow pulse | Z7 |
| 10.3107 | Clear nasal discharge | Z8 |
| 2.4290 | Cough with asthma | Z9 |
| -0.6860 | Generate heat | Z10 |
| 21.1135 | Aversion to cold | Zll |
| 1.9389 | Nasal obstruction | Z12 |
The maximum value of the feature vectors (T1) is taken as the numerator, and each feature vector is taken as the denominator and the result is calculated as:
sorting the feature vectors:
| aversion to cold | 22.7995 | 1.0000 |
| Clear nasal discharge | 11.9968 | 1.9003 |
| Headache (headache) | 6.6104 | 3.4491 |
| Body pain | 6.2738 | 3.6341 |
| Cough with asthma | 4.1150 | 5.5405 |
| Superficial and slow pulse | 3.6494 | 6.2474 |
| Superficial and tense pulse | 3.6342 | 6.2737 |
| Nasal obstruction | 3.6249 | 6.2896 |
| Without sweat | 3.3950 | 6.7156 |
| Sneezing | 2.8135 | 8.1037 |
| Thin and white coating | 2.2733 | 10.0291 |
| Generate heat | 1.0000 | 22.7995 |
The H one-dimensional matrix constructs a two-dimensional matrix a 2. And thirdly, multiplying and summing the eigenvector generated by A2 and the eigenvector generated by A1 to finally obtain the weight of 19 parameters of the viscera in the traditional Chinese medicine by using a sum-product calculation rule to firstly obtain the eigenvector of a decision layer of the two-dimensional matrix A2 and secondly obtain the eigenvector of a target layer of the two-dimensional matrix A1.
The specific calculation method is as follows:
the calculation result of the A2 feature vector is:
K2＝[θ1，θ2，θ3，...，m]
the calculation result of the A1 feature vector is:
the traditional Chinese medicine viscera weight value calculation formula is as follows:
a2 matrix
A2 matrix calculation of feature vectors using the sum-product method
A1 matrix
A1 characteristic vector calculation table
| Yin (kidney) | Yang (Yang) | Watch (A) | Lining (Chinese character of 'li') | Cold syndrome | Heat generation | Deficiency of Qi | Fruit of Chinese wolfberry | Feature vector | |
| Yin (kidney) | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| Yang (Yang) | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| Watch (A) | 0.0000 | 0.0000 | 0.5455 | 0.0000 | 0.5455 | 0.5455 | 0.0000 | 0.0000 | 0.5455 |
| Lining (Chinese character of 'li') | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| Cold syndrome | 0.0000 | 0.0000 | 0.2727 | 0.0000 | 0.2727 | 0.2727 | 0.0000 | 0.0000 | 0.2727 |
| Heat generation | 0.0000 | 0.0000 | 0.1818 | 0.0000 | 0.1818 | 0.1818 | 0.0000 | 0.0000 | 0.1818 |
| Deficiency of Qi | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
| Fruit of Chinese wolfberry | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
Calculation of weight values by performing and product method on A1 and A2 feature vectors
| Guidelines | Without sweat | Headache (headache) | Body pain | Thin and white coating | Sneezing | Superficial and tense pulse | Superficial and slow pulse | Running nose | Cough with asthma | Generate heat | Aversion to cold | Nasal obstruction | Total weight value | Rate of contribution |
| 0.0268 | 0.1400 | 0.1074 | 0.0145 | 0.0202 | 0.0481 | 0.0631 | 0.1883 | 0.0823 | 0.0101 | 0.2631 | 0.0361 | |||
| Yin (kidney) | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.1200 | 0.0000 | 0.1818 | 0.0000 | 0.0000 | 0.1928 | 0.0000 | 0.0907 | 9.07％ |
| Yang (Yang) | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.3333 | 0.0551 | 0.0000 | 0.0179 | 1.79％ |
| Watch (A) | 0.4380 | 0.4082 | 0.4380 | 0.6667 | 0.5455 | 0.4800 | 0.6667 | 0.5455 | 0.4800 | 0.0000 | 0.1286 | 0.5455 | 0.3975 | 39.75％ |
| Lining (Chinese character of 'li') | 0.0876 | 0.1361 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.2400 | 0.0000 | 0.0771 | 0.0000 | 0.0614 | 6.14％ |
| Cold syndrome | 0.2190 | 0.2041 | 0.2190 | 0.3333 | 0.2727 | 0.1600 | 0.0000 | 0.2727 | 0.0000 | 0.0000 | 0.3857 | 0.2727 | 0.2387 | 23.87％ |
| Handle | 0.0000 | 0.1020 | 0.0876 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.6667 | 0.0000 | 0.1818 | 0.0370 | 3.70％ |
| Deficiency of Qi | 0.1095 | 0.0680 | 0.1095 | 0.0000 | 0.0000 | 0.0000 | 0.3333 | 0.0000 | 0.1200 | 0.0000 | 0.0964 | 0.0000 | 0.0805 | 8.05％ |
| Fruit of Chinese wolfberry | 0.1460 | 0.0816 | 0.1460 | 0.0000 | 0.1818 | 0.2400 | 0.0000 | 0.0000 | 0.1600 | 0.0000 | 0.0643 | 0.0000 | 0.0763 | 7.63％ |
The invention also provides a traditional Chinese medicine viscera syndrome differentiation quantitative device based on symptom degrees, which comprises:
a first obtaining unit that obtains a symptom group, determines a magnitude of an attribute of each symptom within the symptom group, the magnitude of the attribute including: degree of symptom value, primary and secondary value of symptom;
a second obtaining unit for obtaining the ranking value of Boolean value of 1 corresponding to the eight classes and viscera;
a first calculating unit for calculating the coefficient beta of the eight lines and viscera parameters corresponding to the symptoms according to the degree of the symptoms, the primary and secondary values of the symptoms and the Boolean value of the eight lines and viscera corresponding to the symptoms as 1nm；
A first constructing unit for constructing a coefficient beta of the eight-dimensionals and the visceral parameters according to the symptomsnmConstructing a first two-dimensional data table A1 with symptoms as rows, eight lines and viscera as columns;
the second calculation unit is used for calculating the maximum characteristic value and the corresponding characteristic vector through the two-dimensional data table A1;
the sorting unit is used for sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2;
and the third calculating unit calculates the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimentional system and the viscera.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. A Chinese medicine viscera syndrome differentiation quantitative method based on symptom degrees is characterized by comprising the following steps:
step 1, obtaining a symptom group, and determining the magnitude of the attribute of each symptom in the symptom group, wherein the magnitude of the attribute comprises: degree of symptom value, primary and secondary value of symptom;
step 2, obtaining a ranking value of which the Boolean value of the eight classes and the viscera corresponding to the symptoms is 1;
step 3, calculating the coefficient beta of the parameters of the eight classes and the viscera corresponding to the symptoms according to the degree value of the symptoms, the primary and secondary values of the symptoms and the Boolean value of the eight classes and the viscera corresponding to the symptoms as 1nm；
Step 4, according to the coefficient beta of the eight-dimensionals and the zang-fu organ parameters corresponding to the symptomsnmConstructing a first two-dimensional data table A1 with symptoms as rows, eight lines and viscera as columns;
step 5, calculating the maximum characteristic value and the corresponding characteristic vector thereof through a two-dimensional data table A1;
wherein the step 5 comprises:
step 51, carrying out standardized calculation on the data based on a first two-dimensional data table A1;
step 52, generating a first matrix B through a standardization technology;
step 53, generating a transposed matrix B based on the first matrix BT；
Step 54, the first matrix B and the transposed matrix BTMultiplying to obtain a square matrix C;
step 55, calculating the data of the area above the diagonal of the square matrix C to obtain the maximum value | VmaxL, according to the absolute value number of the maximum value, finding out the row number p and the column number q of the matrix C where the maximum value is located;
step 56, obtaining data of the row number p and the column number q of the C matrix, namely: deltapp、δqq、δpqAfter the value is obtained, calculating Jcos and Jsin values;
step 57, based on the Jcos and Jsin values, an identity matrix E and a transpose matrix E are establishedTThe corresponding Jcos and Jsin values of p rows and q columns are substituted into the matrices E and ETPerforming the following steps;
calculating Cj ═ ETAfter multiplying the multiplied matrix by the multiplied matrix of XCxE, replacing the original matrix C data with the result;
step 58, proceed | V based on matrix C datamaxI, iterative computation; setting the iterative calculation precision to b 0.000001 if | VmaxIf the | is less than b, the data iterative computation is ended; finding out the maximum characteristic value and the characteristic vector value of the corresponding column from the diagonal line of the C matrix;
step 59, if the characteristic vector value has data less than zero, floating the progress data of the characteristic vector data, and sorting the characteristic vector after the processing is finished;
G＝[T1，T2，T3，T4，T5，...]
step 510, based on the maximum value of the feature vectors (T1) as the numerator, each feature vector is calculated as the denominator, with the result:
step 511, constructing a two-dimensional matrix A2 based on the H one-dimensional matrix;
step 6, sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2;
and 7, calculating the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimensionals and the viscera.
2. The method according to claim 1, wherein step 3 specifically comprises:
βnm＝Y1×Ci×Zj
wherein the symptom degree value is CiThe primary value of the symptom is ZjN represents the serial number of symptoms, m represents the serial numbers of eight classes and viscera;
wherein,
in the formula, n is 1, 2, 3, 4 and … are ranking values of which the Boolean values of 19 octaves and viscera parameters corresponding to symptoms in the viscera database are 1; when the Boolean value is 1, the sorting value is obtained, and when the Boolean value is 0, the sorting value is not obtained.
3. The method of claim 1,
in step 51, the data minus the mean is divided by the standard deviation, and the formula is:
wherein: p is the average value of the two-dimensional matrix array, V is the standard deviation of the two-dimensional matrix array, and X is data of a certain row and a certain column of the two-dimensional matrix array;
the first matrix B of step 52 is
The transposed matrix B of the step 5TIs composed of
The step 54 is specifically
The step 56 specifically includes:
if deltapp＝δqqCalculating Jcos and Jsin values, wherein Je is an intermediate variable;
Jcos＝Cos(Je)
Jsin＝Sin(Je)
if δ pp ≠ δ qq, then calculate Jcos and Jsin values, where CiAnd Tc isAn intermediate variable;
the step 57 is specifically:
4. the method according to claim 1, wherein step 7 is specifically: the calculation result of the first two-dimensional data table a1 is:
the calculation result of the second two-dimensional data table a2 is:
K2＝[θ1，θ2，θ3，...，m]；
the weight value calculation formula of the eight classes and viscera is as follows:
5. a traditional Chinese medicine viscera syndrome differentiation quantitative device based on symptom degrees is characterized by comprising:
a first obtaining unit that obtains a symptom group, determines a magnitude of an attribute of each symptom within the symptom group, the magnitude of the attribute including: degree of symptom value, primary and secondary value of symptom;
a second obtaining unit for obtaining the ranking value of Boolean value of 1 corresponding to the eight classes and viscera;
a first calculating unit for calculating the coefficient beta of the eight lines and viscera parameters corresponding to the symptoms according to the degree of the symptoms, the primary and secondary values of the symptoms and the Boolean value of the eight lines and viscera corresponding to the symptoms as 1nm；
A first constructing unit for constructing a coefficient beta of the eight-dimensionals and the visceral parameters according to the symptomsnmConstructing a first two-dimensional data table A1 with symptoms as rows, eight lines and viscera as columns;
the second calculation unit is used for calculating the maximum characteristic value and the corresponding characteristic vector through the two-dimensional data table A1;
wherein the second computing unit is configured to perform the following steps:
step 51, carrying out standardized calculation on the data based on a first two-dimensional data table A1;
step 52, generating a first matrix B through a standardization technology;
step 53, generating a transposed matrix B based on the first matrix BT；
Step 54, the first matrix B and the transposed matrix BTMultiplying to obtain a square matrix C;
step 55, calculating the data of the area above the diagonal of the square matrix C to obtain the maximum value | VmaxL, according to the absolute value number of the maximum value, finding out the row number p and the column number q of the matrix C where the maximum value is located;
step 56, obtaining data of the row number p and the column number q of the C matrix, namely: deltapp、δqq、δpqAfter the value is obtained, calculating Jcos and Jsin values;
step 57, based on the Jcos and Jsin values, an identity matrix E and a transpose matrix E are establishedTThe corresponding Jcos and Jsin values of p rows and q columns are substituted into the matrices E and ETPerforming the following steps;
calculating Cj ═ ETAfter multiplying the multiplied matrix by the multiplied matrix of XCxE, replacing the original matrix C data with the result;
step 58, proceed | V based on matrix C datamaxI, iterative computation; setting the iterative calculation precision to b 0.000001 if | VmaxIf the | is less than b, the data iterative computation is ended; finding out the maximum characteristic value and the characteristic vector value of the corresponding column from the diagonal line of the C matrix;
step 59, if the characteristic vector value has data less than zero, floating the progress data of the characteristic vector data, and sorting the characteristic vector after the processing is finished;
G＝[T1，T2，T3，T4，T5，...]
step 510, based on the maximum value of the feature vectors (T1) as the numerator, each feature vector is calculated as the denominator, with the result:
step 511, constructing a two-dimensional matrix A2 based on the H one-dimensional matrix;
the sorting unit is used for sorting the eigenvectors corresponding to the maximum eigenvalues to obtain a second two-dimensional data table A2;
and the third calculating unit calculates the first two-dimensional data table A1 and the second two-dimensional data table A2 by using a sum-product method of a hierarchical method to obtain the weight values of the parameters of the eight-dimentional system and the viscera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910547481.0A CN110322961B (en) | 2019-06-24 | 2019-06-24 | Traditional Chinese medicine viscera syndrome differentiation quantitative method and device based on symptom degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910547481.0A CN110322961B (en) | 2019-06-24 | 2019-06-24 | Traditional Chinese medicine viscera syndrome differentiation quantitative method and device based on symptom degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110322961A CN110322961A (en) | 2019-10-11 |
| CN110322961B true CN110322961B (en) | 2021-09-07 |
Family
ID=68121284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910547481.0A Active CN110322961B (en) | 2019-06-24 | 2019-06-24 | Traditional Chinese medicine viscera syndrome differentiation quantitative method and device based on symptom degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110322961B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604479A (en) * | 2009-07-14 | 2009-12-16 | 北京交通大学 | The evaluation method of service level of plane signal intersection under mixed traffic environment |
| CN102298662A (en) * | 2010-06-24 | 2011-12-28 | 上海中医药大学 | Neural network traditional Chinese medicinal syndrome diagnostic system based on self-adapting resonance theory |
| CN104699660A (en) * | 2013-12-04 | 2015-06-10 | 国际商业机器公司 | Sketch of structured matrices with problems of nonlinear regression |
| CN109920535A (en) * | 2019-02-28 | 2019-06-21 | 彭明德 | A kind of mobile Chinese medical discrimination analysis method and device |
-
2019
- 2019-06-24 CN CN201910547481.0A patent/CN110322961B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101604479A (en) * | 2009-07-14 | 2009-12-16 | 北京交通大学 | The evaluation method of service level of plane signal intersection under mixed traffic environment |
| CN102298662A (en) * | 2010-06-24 | 2011-12-28 | 上海中医药大学 | Neural network traditional Chinese medicinal syndrome diagnostic system based on self-adapting resonance theory |
| CN104699660A (en) * | 2013-12-04 | 2015-06-10 | 国际商业机器公司 | Sketch of structured matrices with problems of nonlinear regression |
| CN109920535A (en) * | 2019-02-28 | 2019-06-21 | 彭明德 | A kind of mobile Chinese medical discrimination analysis method and device |
Non-Patent Citations (1)
| Title |
|---|
| "一种基于数据挖掘的中医定量诊断方法";王学伟等;《北京中医药大学学报》;20050130(第1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110322961A (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Weistrand et al. | The ANACONDA algorithm for deformable image registration in radiotherapy | |
| US9697602B1 (en) | System and method for auto-contouring in adaptive radiotherapy | |
| Zhong et al. | FEM-based evaluation of deformable image registration for radiation therapy | |
| CN107230223A (en) | Liver's three-dimensional multimode state method for registering images based on discontinuous fluid | |
| Rios et al. | Population model of bladder motion and deformation based on dominant eigenmodes and mixed-effects models in prostate cancer radiotherapy | |
| Yang et al. | Nonrigid registration of medical image based on adaptive local structure tensor and normalized mutual information | |
| Shusharina et al. | Analytic regularization for landmark-based image registration | |
| Wang et al. | Liver segmentation from CT images using a sparse priori statistical shape model (SP-SSM) | |
| WO2020054503A1 (en) | Machine learning device, inference device, program, and learned model | |
| US11769310B2 (en) | Combining three-dimensional morphable models | |
| Hanson | The quaternion-based spatial-coordinate and orientation-frame alignment problems | |
| CN110322961B (en) | Traditional Chinese medicine viscera syndrome differentiation quantitative method and device based on symptom degree | |
| Joshi et al. | Surface shape morphometry for hippocampal modeling in Alzheimer's disease | |
| CN117726614A (en) | Quality perception network and attention-like Siamese network collaborative medical fusion image quality evaluation method | |
| Cho et al. | Efficient Segmentation for Left Atrium With Convolution Neural Network Based on Active Learning in Late Gadolinium Enhancement Magnetic Resonance Imaging | |
| CN111798500B (en) | Differential synblast non-rigid registration algorithm based on hierarchical neighborhood spectral features | |
| WO2022183851A1 (en) | Lung lobe segmentation method based on digital human technology | |
| JP7551620B2 (en) | Data Augmentation | |
| Krantz | Canonical kernels versus constructible kernels | |
| Kruggel | Robust parametrization of brain surface meshes | |
| Luo et al. | Moment-type estimators for the proportional likelihood ratio model with longitudinal data | |
| CN111862320B (en) | Automatic steering method for SPECT three-dimensional reconstruction image to standard view | |
| Min et al. | Feature Imitating Networks Enhance The Performance, Reliability And Speed Of Deep Learning On Biomedical Image Processing Tasks | |
| Nadeem et al. | LMap: shape-preserving local mappings for biomedical visualization | |
| CN113808753B (en) | Method for predicting auxiliary radiotherapy and chemotherapy curative effect based on decomposition expression learning of multiple losses |
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 |