CN106803012A - Prescription function prediction method based on probability topic model and Chinese medicine base attribute - Google Patents
Prescription function prediction method based on probability topic model and Chinese medicine base attribute Download PDFInfo
- Publication number
- CN106803012A CN106803012A CN201611244641.7A CN201611244641A CN106803012A CN 106803012 A CN106803012 A CN 106803012A CN 201611244641 A CN201611244641 A CN 201611244641A CN 106803012 A CN106803012 A CN 106803012A
- Authority
- CN
- China
- Prior art keywords
- prescription
- chinese medicine
- effect
- drug
- probability
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 236
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000000694 effects Effects 0.000 claims abstract description 97
- 229940079593 drug Drugs 0.000 claims abstract description 79
- 239000013598 vector Substances 0.000 claims abstract description 48
- 241000721047 Danaus plexippus Species 0.000 claims abstract description 25
- 238000005192 partition Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 12
- 239000000796 flavoring agent Substances 0.000 claims description 11
- 235000019634 flavors Nutrition 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 11
- 229940126678 chinese medicines Drugs 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 239000003795 chemical substances by application Substances 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000011282 treatment Methods 0.000 claims description 5
- 206010007247 Carbuncle Diseases 0.000 claims description 3
- 241000607479 Yersinia pestis Species 0.000 claims description 3
- 235000009508 confectionery Nutrition 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 3
- 241000411851 herbal medicine Species 0.000 claims description 3
- 210000003734 kidney Anatomy 0.000 claims description 3
- 210000002429 large intestine Anatomy 0.000 claims description 3
- 239000008141 laxative Substances 0.000 claims description 3
- 210000004185 liver Anatomy 0.000 claims description 3
- 208000030208 low-grade fever Diseases 0.000 claims description 3
- 210000004072 lung Anatomy 0.000 claims description 3
- 210000003516 pericardium Anatomy 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000001543 purgative effect Effects 0.000 claims description 3
- 238000011002 quantification Methods 0.000 claims description 3
- 239000000932 sedative agent Substances 0.000 claims description 3
- 230000001624 sedative effect Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 210000000813 small intestine Anatomy 0.000 claims description 3
- 210000000952 spleen Anatomy 0.000 claims description 3
- 210000002784 stomach Anatomy 0.000 claims description 3
- 210000003932 urinary bladder Anatomy 0.000 claims description 3
- 238000010792 warming Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 claims description 2
- 206010010774 Constipation Diseases 0.000 claims 1
- 230000008901 benefit Effects 0.000 claims 1
- 230000008859 change Effects 0.000 claims 1
- 201000006549 dyspepsia Diseases 0.000 claims 1
- 239000003172 expectorant agent Substances 0.000 claims 1
- 230000003419 expectorant effect Effects 0.000 claims 1
- 238000012549 training Methods 0.000 abstract description 3
- 238000003556 assay Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 206010062717 Increased upper airway secretion Diseases 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 229910052602 gypsum Inorganic materials 0.000 description 2
- 239000010440 gypsum Substances 0.000 description 2
- 208000026435 phlegm Diseases 0.000 description 2
- 231100000614 poison Toxicity 0.000 description 2
- 238000000547 structure data Methods 0.000 description 2
- 239000003440 toxic substance Substances 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
Classifications
-
- G06F19/34—
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Medicines Containing Plant Substances (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention discloses a kind of Prescription Effect Forecasting Methodology based on probability topic model and Chinese medicine base attribute.Structural data is extracted from prescription voluminous dictionary database and TCM Databases by traditional Chinese medicine and pharmacy language Words partition system first.Then, according to prescription Chinese medicine corresponding with its, obtain being treated between Prescription Effect and Chinese medicine the probability attribute vector of relation using LDA models.According to the Chinese medicine and the dosage of drug of every width prescription, monarch drug in a prescription and ministerial drug are extracted, the attribute vector of monarch drug in a prescription and ministerial drug, and the prescription weight vectors based on TFIDF models are integrated on its basis, constitute the characteristic vector of prescription, input SVM multi-categorizers are trained.Finally, user input needs the new prescription information of prediction, and the SVM multi-categorizers for modeling and training using theme obtain effect of prescription.The present invention can effectively predict effect of the prescription according to the drug matching of new prescription, and the pre-clinical assay for automatic prescription, prescription is significant.
Description
Technical field
The present invention relates to text mining and traditional Chinese medicine field of information processing.Probability topic model is based on more particularly, to one kind
With the prescription function prediction method of Chinese medicine base attribute.
Background technology
The traditional Chinese medical science is the medical science based on traditional medicine of Created in China.It is rich that the accumulation of more than one thousand years causes that the traditional Chinese medical science have accumulated content
Rich medical science ancient books and records have contained a large amount of unknown knowledge with record, these resources.With the development of digitizing technique, traditional Chinese medicine number
Word resource is more and more huger, and data mining technology also is applied to traditional Chinese medicine to realize specific purpose by increasing scholar
Analysis and law discovery.The pharmacology of traditional Chinese medical formulae is as a research branch of traditional Chinese medicine and pharmacy, it is necessary to according to the principles of formulating prescriptions, select appropriate medicine
Thing reasonable compatibility, decides suitable dosage, formulation and usage.Wherein, effect of a prescription is generally required by excessively very long multiple
Miscellaneous animal or clinical trial, but clinical or zoopery expends substantial amounts of human and material resources and time.If passing through trusted computer
Breath digging technology is predicted to the new prescription for being formed, and obtains the partial efficacy information of the prescription, it is possible to extensive to carry out
Clinical or zoopery provides extremely valuable reference, greatly promotes the conventional efficient of clinic.In consideration of it, inventor
Focus is, how by computerized information digging technology, to realize that effect of prescription is pre- using existing traditional Chinese medicine digital resource
Survey, so that for prescription research provides valuable clinical evidence.
The content of the invention
The purpose of the present invention is to overcome the deficiencies in the prior art, there is provided one kind is belonged to substantially based on probability topic model and Chinese medicine
The prescription function prediction method of property.
The technical solution adopted for the present invention to solve the technical problems is comprised the following steps：
Step 1, data prediction
For prescription voluminous dictionary database, word segmentation processing is carried out to prescription information using traditional Chinese medicine and pharmacy language Words partition system, carried
Prescription name, Prescription Effect, the corresponding Chinese medicine of prescription, the dosage of drug and dosage unit are taken out, dosage unit is unitized, it is right
The dosage of drug in prescription is standardized；For TCM Databases, effect, property using traditional Chinese medicine and pharmacy Words partition system to Chinese medicine
Taste and the large attribute of return through three carry out participle, remove stop words, and the structured attributes data to extracting carry out 0-1 quantification treatments,
The attribute vector of every taste Chinese medicine is obtained, database is stored in, described prescription voluminous dictionary database and TCM Databases are half hitch
Structure data.
Step 2, according to prescription corresponding with the prescription Chinese medicine of name, " prescription-Chinese medicine " matrix is obtained, using Prescription Effect as hidden
Containing theme, theme modeling is carried out to " prescription-Chinese medicine " matrix using LDA probability topics model, in a model with reference to compatibility data
Storehouse obtains being treated between Prescription Effect and Chinese medicine the probability attribute vector of relation, is stored in database.
Step 3, the Chinese medicine list according to every width prescription and it is unitized after the dosage of drug, calculate frequency of the Chinese medicine in prescription
It is secondary, the taste Chinese medicine of frequency highest two is taken as monarch drug in a prescription and ministerial drug, and is existed using TFIDF model extraction Chinese medicines according to the frequency of Chinese medicine
Weight coefficient in prescription, constructs the weight vectors of prescription, is stored in database.
Step 4, according to the principles of formulating prescriptions in traditional Chinese medical science traditional theory, the Chinese medicine in prescription have monarch point, and prescription
Effect mainly determined by monarch drug in a prescription and ministerial drug.In for prescription voluminous dictionary database per pair prescription, merge monarch drug in a prescription attribute to
The weight vectors of amount, the attribute vector of ministerial drug and prescription, constitute the characteristic vector of prescription, and input SVM classifier is entered to model
Row training, by the multi-class grader of one-versus-rest method constructs.
Step 5, the new prescription information of input needs prediction, new prescription information include Chinese medicine name and corresponding dosage；According to
The probability attribute vector of relation, calculates the prescription and is under the jurisdiction of certain effect using Bayesian formula between Prescription Effect and Chinese medicine
Probable value, sorts from big to small according to probable value, is chosen at the effect in the range of specific threshold, obtains effect collection unification U1(U1Have
May be empty set).
Step 6, the characteristic vector that prescription to be predicted is obtained according to step 4, it is pre- that input SVM multi-categorizers carry out Prescription Effect
Survey, obtain the U of effect set two2。
Step 7, by effect collection unification and effect set two make union operation, obtain final Prescription Effect set U=U1
∪U2。
The content that implements of the step 1 includes：
1. by the various dose unit of Chinese medicine according to following rules equivalent Cheng Ke：
One or two=31.25 gram
One money=3.125 gram
One point=0.3125 gram
2. the dosage according to the following formula to different Chinese medicines in prescription continues to standardize：
Wherein：diThe dosage of certain Chinese medicine in prescription is represented,Represent the dosage of drug after standardization, dmaxRepresent certain Chinese medicine
Maximum in common dose；dminRepresent the minimum value in certain Chinese medicine common dose；
3. described Prescription Effect include harmonizing prescription, astringent prescription, sedative drugs prescriptions, resuscitative prescription, dryness-moistening prescription, wind-curing prescription, purgative drugs prescriptions,
Clearing food stagnation prescriptions, exterior-interior relieving prescription, heat-clearing formula, warming interior formula, qi-regulating prescription, blood-regulating prescription, prescriptions for boil and carbuncle, summer-heat clearing prescription, dampclearing prescription, eliminating the phlegm
Agent, tonifying recipes, diaphoretic recipes, pest repellant.
4. described Chinese herbal medicine nature and flavor refer to the property and smell of medicine, i.e. four natures and five flavors of drug, including cold, hot, warm, cool, pungent,
It is sweet, sour, bitter, salty.Return through using 12 zang-fu differentiation methods state, the thoughts of returning home, liver, spleen, lung, kidney, stomach, large intestine, small intestine, bladder, courage,
Pericardium, tri-jiao channel.Effect is described in units of two-character word, such as " heat-clearing ", " removing toxic substances ", " cool blood ".Wherein, occur in nature and flavor
" being slightly cold ", " low-grade fever " etc. are stated, and are quantified with 0.5, and remaining quantifies construction vector space using 0-1.
The step 2 to implement process as follows：
2-1. setting hyper parameters α=2.5, β=0.1；
2-2. carries out parameter Estimation using the Gibbs method of samplings to LDA probability topics model, and iterations is 100；
After 2-3. completes sampling, drug matching database is inquired about:
If Chinese medicine hiDo not possess the compatibility drug of correlation, the probability matrix ψ of " Chinese medicine-effect " is calculated according to the following formula：
If Chinese medicine hiAnd hjIt is compatibility drug pair, calculates the probability matrix θ of " the p- effect of medicine "：
Wherein, W represents the sum of Chinese medicine,Represent Chinese medicine hiThe number of times of effect k is distributed to, not including current distribution；The Chinese medicine total degree of effect k is distributed in representative, not including Chinese medicine hiDistribute to the number of times of effect k；Representative is distributed to
The Chinese medicine total degree of effect k, not including Chinese medicine hi、hjDistribute to the number of times of effect k.
The step 3 to implement process as follows：
3-1. is directed to every width prescription p, it is assumed that taste of traditional Chinese medicine number is Np, calculate Chinese medicine hiFrequency F (h in prescriptioni), take frequency
The taste Chinese medicine of secondary highest two is used as monarch drug in a prescription and ministerial drug.
3-2. calculates Chinese medicine h using TFIDF modelsiTo the significance level of prescription, according to every taste Chinese medicine in prescription
The weight vectors of TFIDF values construction prescription pUnique Chinese medicine during m is represented from prescription database is total.
Wherein, if prescription p includes Chinese medicine hi, then ti=TFIDF (hi), otherwise ti=0.
The step 5 to implement process as follows：
5-1. user inputs prescription H to be predicted(p)={ h1,h2,...hNp, hiChinese medicine is represented, is calculated using Bayesian formula
The prescription is under the jurisdiction of the probability of effect k：
Wherein, xi=1 represents Chinese medicine hiThere is compatibility drug pair, otherwise xi=0.
5-2. is directed to prescription H(p), effect k for meeting following formula is returned, threshold value T=1e-8 is taken, obtain the unification of effect collection：
p(k|H(p)) ＞ T.
The present invention has the beneficial effect that：
The present invention on the basis of existing traditional Chinese medicine digital resource, by probability topic model excavate Prescription Effect and
Treatment relation between Chinese medicine, the function of prescription is effectively calculated by Bayesian formula.Additionally, existing with reference to monarch drug in a prescription and ministerial drug
The Main Function played in Prescription Effect, the frequency by Chinese medicine in prescription calculates monarch, the ministerial drug automatically derived in prescription, and
Using the weight vectors of TFIDF model extraction prescriptions, merge the power of the attribute vector, the attribute vector of ministerial drug and prescription of monarch drug in a prescription
Weight vector further improves the degree of accuracy of Prescription Effect prediction using SVM multi-categorizers as the characteristic vector of prescription, so that
For prescription research provides valuable clinical evidence.
Brief description of the drawings
Fig. 1 is flow chart of the invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
As shown in figure 1, the prescription function prediction method based on probability topic model and Chinese medicine base attribute includes following step
Suddenly：
Step 1, data prediction
For prescription voluminous dictionary database, word segmentation processing is carried out to prescription information using traditional Chinese medicine and pharmacy language Words partition system, carried
Prescription name, Prescription Effect, the corresponding Chinese medicine of prescription, the dosage of drug and dosage unit are taken out, dosage unit is unitized, it is right
The dosage of drug in prescription is standardized；For TCM Databases, effect, property using traditional Chinese medicine and pharmacy Words partition system to Chinese medicine
Taste and the large attribute of return through three carry out participle, remove stop words, and the structured attributes data to extracting carry out 0-1 quantification treatments,
The attribute vector of every taste Chinese medicine is obtained, database is stored in, described prescription voluminous dictionary database and TCM Databases are half hitch
Structure data.
Step 2, according to prescription corresponding with the prescription Chinese medicine of name, " prescription-Chinese medicine " matrix is obtained, using Prescription Effect as hidden
Containing theme, theme modeling is carried out to " prescription-Chinese medicine " matrix using LDA probability topics model, in a model with reference to compatibility data
Storehouse obtains being treated between Prescription Effect and Chinese medicine the probability attribute vector of relation, is stored in database.
Step 3, the Chinese medicine list according to every width prescription and it is unitized after the dosage of drug, calculate frequency of the Chinese medicine in prescription
It is secondary, the taste Chinese medicine of frequency highest two is taken as monarch drug in a prescription and ministerial drug, and is existed using TFIDF model extraction Chinese medicines according to the frequency of Chinese medicine
Weight coefficient in prescription, constructs the weight vectors of prescription, is stored in database.
Step 4, according to the principles of formulating prescriptions in traditional Chinese medical science traditional theory, the Chinese medicine in prescription have monarch point, and prescription
Effect mainly determined by monarch drug in a prescription and ministerial drug.In for prescription voluminous dictionary database per pair prescription, merge monarch drug in a prescription attribute to
The weight vectors of amount, the attribute vector of ministerial drug and prescription, constitute the characteristic vector of prescription, and input SVM classifier is entered to model
Row training, by the multi-class grader of one-versus-rest method constructs.
Step 5, the new prescription information of input needs prediction, new prescription information include Chinese medicine name and corresponding dosage；According to
The probability attribute vector of relation, calculates the prescription and is under the jurisdiction of certain effect using Bayesian formula between Prescription Effect and Chinese medicine
Probable value, sorts from big to small according to probable value, is chosen at the effect in the range of specific threshold, obtains effect collection unification U1(U1Have
May be empty set).
Step 6, the characteristic vector that prescription to be predicted is obtained according to step 4, it is pre- that input SVM multi-categorizers carry out Prescription Effect
Survey, obtain the U of effect set two2。
Step 7, by effect collection unification and effect set two make union operation, obtain final Prescription Effect set U=U1
∪U2。
The content that implements of the step 1 includes：
1. by the various dose unit of Chinese medicine according to following rules equivalent Cheng Ke：
One or two=31.25 gram
One money=3.125 gram
One point=0.3125 gram
2. the dosage according to the following formula to different Chinese medicines in prescription continues to standardize：
Wherein：diThe dosage of certain Chinese medicine in prescription is represented,Represent the dosage of drug after standardization, dmaxRepresent certain Chinese medicine
Maximum in common dose；dminRepresent the minimum value in certain Chinese medicine common dose.
3. described Prescription Effect include harmonizing prescription, astringent prescription, sedative drugs prescriptions, resuscitative prescription, dryness-moistening prescription, wind-curing prescription, purgative drugs prescriptions,
Clearing food stagnation prescriptions, exterior-interior relieving prescription, heat-clearing formula, warming interior formula, qi-regulating prescription, blood-regulating prescription, prescriptions for boil and carbuncle, summer-heat clearing prescription, dampclearing prescription, eliminating the phlegm
Agent, tonifying recipes, diaphoretic recipes, pest repellant.
4. described Chinese herbal medicine nature and flavor refer to the property and smell of medicine, i.e. four natures and five flavors of drug, including cold, hot, warm, cool, pungent,
It is sweet, sour, bitter, salty.Return through using 12 zang-fu differentiation methods state, the thoughts of returning home, liver, spleen, lung, kidney, stomach, large intestine, small intestine, bladder, courage,
Pericardium, tri-jiao channel.Effect is described in units of two-character word, such as " heat-clearing ", " removing toxic substances ", " cool blood ".Wherein, occur in nature and flavor
" being slightly cold ", " low-grade fever " etc. are stated, and are quantified with 0.5, and remaining quantifies construction vector space using 0-1.
The step 2 to implement process as follows：
2-1. setting hyper parameters α=2.5, β=0.1；
2-2. carries out parameter Estimation using the Gibbs method of samplings to LDA probability topics model, and iterations is 100；
After 2-3. completes sampling, drug matching database is inquired about:
If Chinese medicine hiDo not possess the compatibility drug of correlation, the probability matrix ψ of " Chinese medicine-effect " is calculated according to the following formula：
If Chinese medicine hiAnd hjIt is compatibility drug pair, calculates the probability matrix θ of " the p- effect of medicine "：
Wherein, W represents the sum of Chinese medicine,Represent Chinese medicine hiThe number of times of effect k is distributed to, not including current distribution；The Chinese medicine total degree of effect k is distributed in representative, not including Chinese medicine hiDistribute to the number of times of effect k.Representative is distributed to
The Chinese medicine total degree of effect k, not including Chinese medicine hi、hjDistribute to the number of times of effect k.
The step 3 to implement process as follows：
3-1. is directed to every width prescription p, it is assumed that taste of traditional Chinese medicine number is Np, calculate Chinese medicine hiFrequency F (h in prescriptioni), take frequency
The taste Chinese medicine of secondary highest two is used as monarch drug in a prescription and ministerial drug.
3-2. calculates Chinese medicine h using TFIDF modelsiTo the significance level of prescription, according to every taste Chinese medicine in prescription
The weight vectors of TFIDF values construction prescription pUnique Chinese medicine during m is represented from prescription database is total.
Wherein, if prescription p includes Chinese medicine hi, then ti=TFIDF (hi), otherwise ti=0.
The step 5 to implement process as follows：
5-1. user inputs prescription H to be predicted(p)={ h1,h2,...hNp, hiChinese medicine is represented, is calculated using Bayesian formula
The prescription is under the jurisdiction of the probability of effect k：
Wherein, xi=1 represents Chinese medicine hiThere is compatibility drug pair, otherwise xi=0.
5-2. is directed to prescription H(p), effect k for meeting following formula is returned, threshold value T=1e-8 is taken, obtain the unification of effect collection：
p(k|H(p)) ＞ T.
Embodiment
1st, a new prescription is input into, comprising each Chinese medicine and corresponding dosage.
2nd, according to the probability attribute vector data storehouse of relation between Prescription Effect and Chinese medicine, calculate new using Bayesian formula
Prescription is under the jurisdiction of the probable value of certain effect, is sorted from big to small according to probable value, is chosen at the effect in the range of specific threshold,
Obtain effect collection unification U1。
3rd, for the Chinese medicine list in new prescription and it is unitized after the dosage of drug, calculate the frequency of the Chinese medicine in prescription,
The taste Chinese medicine of frequency highest two is taken as monarch drug in a prescription and ministerial drug, and TFIDF model extraction Chinese medicines are utilized in side according to the frequency of Chinese medicine
Weight coefficient in agent, constructs the weight vectors of prescription.
4th, Chinese medicine attribute database is searched, the attribute vector of monarch drug in a prescription and ministerial drug is obtained, merges attribute vector, the ministerial drug of monarch drug in a prescription
Attribute vector and prescription weight vectors, constitute the characteristic vector of new prescription, input SVM multi-categorizers carry out Prescription Effect
Prediction, obtains the U of effect set two2。
5th, merge the unification of effect collection and effect set two, obtain the forecasting power of new prescription.
Described step 2 is realized by following sub-step：
2.1) the new prescription for assuming input is H(p)={ h1,h2,...hNp, hiChinese medicine is represented, is calculated using Bayesian formula
The prescription is under the jurisdiction of the probability of effect k：
Wherein, xi=1 represents Chinese medicine hiThere is compatibility drug pair, otherwise xi=0.
2.2) for new prescription H(p), effect k for meeting following formula is returned, threshold value T=1e-8 is taken, obtain the unification of effect collection：
p(k|H(p)) ＞ T
Described step 3 is realized by following sub-step：
3.1) for new prescription, it is assumed that taste of traditional Chinese medicine number is Np, calculate Chinese medicine hiFrequency F (h in prescriptioni), take the frequency most
Two taste Chinese medicines high are used as monarch drug in a prescription and ministerial drug.
3.2) Chinese medicine h is calculated using TFIDF modelsiTo the significance level of new prescription, according to every taste Chinese medicine in new prescription
TFIDF values construct the weight vectors of new prescriptionUnique Chinese medicine during m is represented from prescription database is total
Number.
Wherein, if new prescription includes Chinese medicine hi, then ti=TFIDF (hi), otherwise ti=0.
The new prescription information of input of this example is gypsum (50g), and the wind-weed (18g), Radix Glycyrrhizae (6g), polished rice (9g) is calculated
The monarch drug in a prescription and ministerial drug for arriving respectively gypsum and the wind-weed, effect collection unification U1={ heat-clearing formula }, the U of effect set two2=resuscitative prescription, clearly
Thermit powder }, the forecasting power for finally giving is resuscitative prescription and heat-clearing formula.
It should be noted that this embodiment assumes that SVM multi-categorizers are trained finishes.
Claims (5)
1. the prescription function prediction method of probability topic model and Chinese medicine base attribute is based on, it is characterised in that including following step
Suddenly：
Step 1, data prediction
For prescription voluminous dictionary database, word segmentation processing is carried out to prescription information using traditional Chinese medicine and pharmacy language Words partition system, extracted
Prescription name, Prescription Effect, the corresponding Chinese medicine of prescription, the dosage of drug and dosage unit, unitize, to prescription to dosage unit
In the dosage of drug be standardized；For TCM Databases, using traditional Chinese medicine and pharmacy Words partition system to effect of Chinese medicine, nature and flavor and
The large attribute of return through three carries out participle, removes stop words, and the structured attributes data to extracting carry out 0-1 quantification treatments, obtain
Per the attribute vector of taste Chinese medicine, database is stored in, described prescription voluminous dictionary database and TCM Databases are semi-structured
Data；
Step 2, according to prescription corresponding with the prescription Chinese medicine of name, " prescription-Chinese medicine " matrix is obtained, using Prescription Effect as implicit master
Topic, theme modeling is carried out using LDA probability topics model to " prescription-Chinese medicine " matrix, is obtained with reference to compatibility database in a model
To the probability attribute vector that relation is treated between Prescription Effect and Chinese medicine, database is stored in；
Step 3, the Chinese medicine list according to every width prescription and it is unitized after the dosage of drug, calculate the frequency of the Chinese medicine in prescription,
The taste Chinese medicine of frequency highest two is taken as monarch drug in a prescription and ministerial drug, and TFIDF model extraction Chinese medicines are utilized in side according to the frequency of Chinese medicine
Weight coefficient in agent, constructs the weight vectors of prescription, is stored in database；
Step 4, according to the principles of formulating prescriptions in traditional Chinese medical science traditional theory, the Chinese medicine in prescription have monarch point, and the work(of prescription
Effect is mainly determined by monarch drug in a prescription and ministerial drug；Every pair prescription in for prescription voluminous dictionary database, merges attribute vector, the minister of monarch drug in a prescription
The attribute vector of medicine and the weight vectors of prescription, constitute the characteristic vector of prescription, and input SVM classifier is instructed to model
Practice, by the multi-class grader of one-versus-rest method constructs；
Step 5, the new prescription information of input needs prediction, new prescription information include Chinese medicine name and corresponding dosage；According to prescription
The probability attribute vector of relation, the probability that the prescription is under the jurisdiction of certain effect is calculated using Bayesian formula between effect and Chinese medicine
Value, sorts from big to small according to probable value, is chosen at the effect in the range of specific threshold, obtains effect collection unification U1；
Step 6, the characteristic vector that prescription to be predicted is obtained according to step 4, input SVM multi-categorizers carry out Prescription Effect prediction,
Obtain the U of effect set two2；
Step 7, by effect collection unification and effect set two make union operation, obtain final Prescription Effect set U=U1∪U2。
2. the prescription function prediction method based on probability topic model and Chinese medicine base attribute according to claim 1, its
Being characterised by the content that implements of the step 1 includes：
1. by the various dose unit of Chinese medicine according to following rules equivalent Cheng Ke：
One or two=31.25 gram
One money=3.125 gram
One point=0.3125 gram
2. the dosage according to the following formula to different Chinese medicines in prescription continues to standardize：
Wherein：diThe dosage of certain Chinese medicine in prescription is represented,Represent the dosage of drug after standardization, dmaxRepresent that certain Chinese medicine commonly uses agent
Maximum in amount；dminRepresent the minimum value in certain Chinese medicine common dose；
3. described Prescription Effect includes harmonizing prescription, astringent prescription, sedative drugs prescriptions, resuscitative prescription, dryness-moistening prescription, wind-curing prescription, purgative drugs prescriptions, treatment for relieving indigestion and constipation
Change product agent, exterior-interior relieving prescription, heat-clearing formula, warming interior formula, qi-regulating prescription, blood-regulating prescription, prescriptions for boil and carbuncle, summer-heat clearing prescription, dampclearing prescription, expectorant, benefit
Beneficial agent, diaphoretic recipes, pest repellant；
4. described Chinese herbal medicine nature and flavor refer to the property and smell of medicine, i.e. four natures and five flavors of drug, including cold, hot, warm, cool, pungent, sweet, sour,
It is bitter, salty；Return through using 12 zang-fu differentiation methods state, the thoughts of returning home, liver, spleen, lung, kidney, stomach, large intestine, small intestine, bladder, courage, pericardium,
Tri-jiao channel；Effect is described in units of two-character word, is quantified with 0.5 for " being slightly cold " and " low-grade fever " occurred in nature and flavor, in nature and flavor
The description of remaining two-character word quantifies construction vector space using 0-1.
3. the prescription function prediction method based on probability topic model and Chinese medicine base attribute according to claim 2, its
Be characterised by the step 2 to implement process as follows：
2-1. setting hyper parameters α=2.5, β=0.1；
2-2. carries out parameter Estimation using the Gibbs method of samplings to LDA probability topics model, and iterations is 100；
After 2-3. completes sampling, drug matching database is inquired about:
If Chinese medicine hiDo not possess the compatibility drug of correlation, the probability matrix ψ of " Chinese medicine-effect " is calculated according to the following formula：
If Chinese medicine hiAnd hjIt is compatibility drug pair, calculates the probability matrix θ of " the p- effect of medicine "：
Wherein, W represents the sum of Chinese medicine,Represent Chinese medicine hiThe number of times of effect k is distributed to, not including current distribution；Represent
The Chinese medicine total degree of effect k is distributed to, not including Chinese medicine hiDistribute to the number of times of effect k；Representative distributes to effect k's
Chinese medicine total degree, not including Chinese medicine hi, hjDistribute to the number of times of effect k.
4. the prescription function prediction method based on probability topic model and Chinese medicine base attribute according to claim 3, its
Be characterised by the step 3 to implement process as follows：
3-1. is directed to every width prescription p, it is assumed that taste of traditional Chinese medicine number is Np, calculate Chinese medicine hiFrequency F (h in prescriptioni), take the frequency most
Two taste Chinese medicines high are used as monarch drug in a prescription and ministerial drug；
3-2. calculates Chinese medicine h using TFIDF modelsiTo the significance level of prescription, according to TFIDF value of every taste Chinese medicine in prescription
The weight vectors of construction prescription pUnique Chinese medicine during m is represented from prescription database is total；
Wherein, if prescription p includes Chinese medicine hi, then ti=TFIDF (hi), otherwise ti=0.
5. the prescription function prediction method based on probability topic model and Chinese medicine base attribute according to claim 4, its
Be characterised by the step 5 to implement process as follows：
5-1. user inputs prescription to be predictedhiChinese medicine is represented, the prescription is calculated using Bayesian formula
It is under the jurisdiction of the probability of effect k：
Wherein, xi=1 represents Chinese medicine hiThere is compatibility drug pair, otherwise xi=0；
5-2. is directed to prescription H(p), effect k for meeting following formula is returned, threshold value T=1e-8 is taken, obtain the unification of effect collection：
p(k|H(p)) ＞ T.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611244641.7A CN106803012B (en) | 2016-12-29 | 2016-12-29 | Prescription function prediction method based on probability topic model and Chinese medicine essential attribute |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611244641.7A CN106803012B (en) | 2016-12-29 | 2016-12-29 | Prescription function prediction method based on probability topic model and Chinese medicine essential attribute |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106803012A true CN106803012A (en) | 2017-06-06 |
| CN106803012B CN106803012B (en) | 2019-03-22 |
Family
ID=58985228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611244641.7A Active CN106803012B (en) | 2016-12-29 | 2016-12-29 | Prescription function prediction method based on probability topic model and Chinese medicine essential attribute |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106803012B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109346180A (en) * | 2018-08-03 | 2019-02-15 | 电子科技大学 | The training recognition methods of tcm prescription monarch and system |
| CN109378080A (en) * | 2018-09-14 | 2019-02-22 | 浙江大学 | A kind of similar Chinese medicine search method based on feature bag of words |
| CN109801697A (en) * | 2019-01-16 | 2019-05-24 | 中国中医科学院中医药信息研究所 | A kind of evaluation method of medicine materical crude slice significance level in Chinese medicinal formulae |
| CN109947901A (en) * | 2019-02-20 | 2019-06-28 | 杭州师范大学 | Prescription Effect prediction technique based on multi-layer perception (MLP) and natural language processing technique |
| CN110289106A (en) * | 2019-06-28 | 2019-09-27 | 淮阴工学院 | A method of effect, which is analyzed, from Chinese medicine compound prescription corresponds to Chinese medicine and its pharmacological property compatibility relationship |
| CN110335684A (en) * | 2019-06-14 | 2019-10-15 | 电子科技大学 | The intelligent dialectical aid decision-making method of Chinese medicine based on topic model technology |
| CN110619960A (en) * | 2019-09-10 | 2019-12-27 | 电子科技大学 | Traditional Chinese medicine incompatibility prediction method based on supervised learning framework |
| CN111180045A (en) * | 2019-11-25 | 2020-05-19 | 浙江大学 | Method for mining relation between medicine pairs and efficacy from prescription information |
| CN111883263A (en) * | 2020-07-29 | 2020-11-03 | 济南浪潮高新科技投资发展有限公司 | Method, device, equipment and storage medium for assisting in judging drug effect of traditional Chinese medicine prescription |
| CN112151140A (en) * | 2020-11-25 | 2020-12-29 | 西藏自治区人民政府驻成都办事处医院 | Antibacterial drug clinical application system, electronic device and computer readable storage medium |
| CN115050481A (en) * | 2022-06-17 | 2022-09-13 | 湖南中医药大学 | Traditional Chinese medicine prescription efficacy prediction method based on graph convolution neural network |
| CN117174245A (en) * | 2023-09-19 | 2023-12-05 | 兰州大学 | Chinese medicinal prescription repositioning method based on herbal medicine attributes and efficacy |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101118562A (en) * | 2006-08-21 | 2008-02-06 | 凌强 | Herbalist doctor clinical reference system |
| CN102122325A (en) * | 2011-04-20 | 2011-07-13 | 天津师范大学 | Method for automatically analyzing efficacy of Chinese medicine formula |
| CN103823848A (en) * | 2014-02-11 | 2014-05-28 | 浙江大学 | LDA (latent dirichlet allocation) and VSM (vector space model) based similar Chinese herb literature recommendation method |
-
2016
- 2016-12-29 CN CN201611244641.7A patent/CN106803012B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101118562A (en) * | 2006-08-21 | 2008-02-06 | 凌强 | Herbalist doctor clinical reference system |
| CN102122325A (en) * | 2011-04-20 | 2011-07-13 | 天津师范大学 | Method for automatically analyzing efficacy of Chinese medicine formula |
| CN103823848A (en) * | 2014-02-11 | 2014-05-28 | 浙江大学 | LDA (latent dirichlet allocation) and VSM (vector space model) based similar Chinese herb literature recommendation method |
Non-Patent Citations (2)
| Title |
|---|
| QIAN TAN 等: "LDA-Based Model for Traditional Chinese Medicine Diagnosis", 《3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY》 * |
| 基于BP神经网络中药复方功效的预测研究: "李味味，章新友，仵倚，周小玲", 《中医药导报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109346180A (en) * | 2018-08-03 | 2019-02-15 | 电子科技大学 | The training recognition methods of tcm prescription monarch and system |
| CN109378080A (en) * | 2018-09-14 | 2019-02-22 | 浙江大学 | A kind of similar Chinese medicine search method based on feature bag of words |
| CN109801697A (en) * | 2019-01-16 | 2019-05-24 | 中国中医科学院中医药信息研究所 | A kind of evaluation method of medicine materical crude slice significance level in Chinese medicinal formulae |
| CN109947901B (en) * | 2019-02-20 | 2020-10-20 | 杭州师范大学 | Prescription efficacy prediction method based on multilayer perceptron and natural language processing technology |
| CN109947901A (en) * | 2019-02-20 | 2019-06-28 | 杭州师范大学 | Prescription Effect prediction technique based on multi-layer perception (MLP) and natural language processing technique |
| CN110335684A (en) * | 2019-06-14 | 2019-10-15 | 电子科技大学 | The intelligent dialectical aid decision-making method of Chinese medicine based on topic model technology |
| CN110289106A (en) * | 2019-06-28 | 2019-09-27 | 淮阴工学院 | A method of effect, which is analyzed, from Chinese medicine compound prescription corresponds to Chinese medicine and its pharmacological property compatibility relationship |
| CN110289106B (en) * | 2019-06-28 | 2023-06-16 | 淮阴工学院 | Method for analyzing compatibility relation of traditional Chinese medicines with corresponding efficacy and drug properties in traditional Chinese medicine compound |
| CN110619960A (en) * | 2019-09-10 | 2019-12-27 | 电子科技大学 | Traditional Chinese medicine incompatibility prediction method based on supervised learning framework |
| CN110619960B (en) * | 2019-09-10 | 2022-04-22 | 电子科技大学 | Traditional Chinese medicine incompatibility prediction method based on supervised learning framework |
| CN111180045A (en) * | 2019-11-25 | 2020-05-19 | 浙江大学 | Method for mining relation between medicine pairs and efficacy from prescription information |
| CN111180045B (en) * | 2019-11-25 | 2023-05-12 | 浙江大学 | Method for mining relation between drug pairs and efficacy from prescription information |
| CN111883263A (en) * | 2020-07-29 | 2020-11-03 | 济南浪潮高新科技投资发展有限公司 | Method, device, equipment and storage medium for assisting in judging drug effect of traditional Chinese medicine prescription |
| CN112151140A (en) * | 2020-11-25 | 2020-12-29 | 西藏自治区人民政府驻成都办事处医院 | Antibacterial drug clinical application system, electronic device and computer readable storage medium |
| CN115050481A (en) * | 2022-06-17 | 2022-09-13 | 湖南中医药大学 | Traditional Chinese medicine prescription efficacy prediction method based on graph convolution neural network |
| CN115050481B (en) * | 2022-06-17 | 2023-10-31 | 湖南中医药大学 | Traditional Chinese medicine prescription efficacy prediction method based on graph convolution neural network |
| CN117174245A (en) * | 2023-09-19 | 2023-12-05 | 兰州大学 | Chinese medicinal prescription repositioning method based on herbal medicine attributes and efficacy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106803012B (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106803012A (en) | Prescription function prediction method based on probability topic model and Chinese medicine base attribute | |
| CN107169078A (en) | Knowledge of TCM collection of illustrative plates and its method for building up and computer system | |
| Feng et al. | Knowledge discovery in traditional Chinese medicine: state of the art and perspectives | |
| Xia et al. | Data Mining‐Based Analysis of Chinese Medicinal Herb Formulae in Chronic Kidney Disease Treatment | |
| Yang et al. | Association rule mining and network analysis in oriental medicine | |
| Jin et al. | An improved association-mining research for exploring Chinese herbal property theory: based on data of the Shennong's Classic of Materia Medica | |
| CN110289106B (en) | Method for analyzing compatibility relation of traditional Chinese medicines with corresponding efficacy and drug properties in traditional Chinese medicine compound | |
| CN109326350A (en) | Cerebral infarction clinic diagnosis system | |
| CN108986911A (en) | A kind of differential diagnosis in tcm opinion controls data processing method | |
| Hu et al. | An analysis model of diagnosis and treatment for COVID-19 pandemic based on medical information fusion | |
| CN108460132B (en) | Chinese medicinal material attribute feature coding and searching system based on Chinese pharmacology theory | |
| Liu et al. | Application of the data mining algorithm in the clinical guide medical records | |
| Bahri et al. | Science mapping for nutrition education in sports recovery research: A bibliometric analysis | |
| CN110619960B (en) | Traditional Chinese medicine incompatibility prediction method based on supervised learning framework | |
| Zhang et al. | [Retracted] Analysis of Prescription Medication Rules of Traditional Chinese Medicine for Diabetes Treatment Based on Data Mining | |
| Qin et al. | A traditional Chinese medicine prescription recommendation method based on mutual information clustering | |
| Wang et al. | Research methods about data mining technology in the study medication Rule on Famous Veteran Teran Doctors of TCM | |
| Xin-Di et al. | Research on herb pairs of classical formulae of ZHANG Zhong-Jing using big data technology | |
| CN111383740A (en) | Traditional Chinese medicine efficacy prediction method based on multitask deep neural network | |
| Sun et al. | An approach to co-medication mechanism mining of Chinese Materia Medica and western medicines based on complex networks with the multi-source heterogeneous information | |
| Zhu et al. | An approach to calculation and visualization of efficacies of Traditional Chinese Medical formulae based on a semantic network | |
| Yang et al. | Construction of Chinese Medicine Prescription Data Mining Based on Association Rules of the System | |
| Ramadhanti et al. | Development of Jamu formula prediction system module of Ijah analytics based on pharmacology activity and particular efficacy target | |
| CN104268656A (en) | Method for assessing cooperativity and effect degree of various kinds of traditional Chinese medicine with same biological function on biological function and traditional Chinese medicine compound optimizing method | |
| Li et al. | Data Exploration and Mining on Traditional Chinese Medicine |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201231 Address after: No.1 xc1001-2, Nanmen Gongnong Road, Chongfu Town, Tongxiang City, Jiaxing City, Zhejiang Province Patentee after: JIAXING JINJING E-COMMERCE Co.,Ltd. Address before: Hangzhou City, Zhejiang province 310036 Xiasha Higher Education Park forest Street No. 16 Patentee before: HANGZHOU NORMAL UNIVERSITY QIANJIANG College |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20211117 Address after: 257091 room 419, building a, Dongying Economic and Technological Development Zone Management Committee, No. 59, Fuqian street, Dongying District, Dongying City, Shandong Province Patentee after: Dongying dongkai New Material Industrial Park Co.,Ltd. Address before: No.1 xc1001-2, Nanmen Gongnong Road, Chongfu Town, Tongxiang City, Jiaxing City, Zhejiang Province Patentee before: JIAXING JINJING E-COMMERCE Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221229 Address after: 257091 Room 101, Building 5, Science and Technology Enterprise Accelerator, No. 17, Xinghuahe Road, Dongying Development Zone, Shandong Province Patentee after: Dongying Dongkai New Material Technology Research and Development Co.,Ltd. Address before: 257091 room 419, building a, Dongying Economic and Technological Development Zone Management Committee, No. 59, Fuqian street, Dongying District, Dongying City, Shandong Province Patentee before: Dongying dongkai New Material Industrial Park Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240126 Address after: Room 405, Building A, Technology Enterprise Accelerator, No. 17 Xinghuahe Road, Development Zone, Dongying City, Shandong Province, 257091 Patentee after: Dongying Dongkai Industrial Park Operation Management Co.,Ltd. Country or region after: China Address before: 257091 Room 101, Building 5, Science and Technology Enterprise Accelerator, No. 17, Xinghuahe Road, Dongying Development Zone, Shandong Province Patentee before: Dongying Dongkai New Material Technology Research and Development Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |