CN109637618A - A kind of Chinese medicinal formulae diversity recommended method based on label - Google Patents
A kind of Chinese medicinal formulae diversity recommended method based on label Download PDFInfo
- Publication number
- CN109637618A CN109637618A CN201811437469.6A CN201811437469A CN109637618A CN 109637618 A CN109637618 A CN 109637618A CN 201811437469 A CN201811437469 A CN 201811437469A CN 109637618 A CN109637618 A CN 109637618A
- Authority
- CN
- China
- Prior art keywords
- symptom
- prescription
- sublist
- diversity
- label
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 208000024891 symptom Diseases 0.000 claims abstract description 110
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 55
- 201000010099 disease Diseases 0.000 claims abstract description 41
- 230000005484 gravity Effects 0.000 claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 208000011580 syndromic disease Diseases 0.000 claims abstract description 20
- 239000003814 drug Substances 0.000 claims abstract description 18
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 2
- 230000009089 cytolysis Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000008707 rearrangement Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H20/13—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered from dispensers
-
- 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)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The Chinese medicinal formulae diversity recommended method based on label that the invention discloses a kind of constructs symptom syndrome label weight matrix using Chinese medicine case;The different types of prescription of disease, which is generated, using symptom syndrome label weight matrix recommends sublist;Utilize the weight and user's symptom model of symptom syndrome label and the similarity calculation sublist sequence specific gravity of prescription symptom model;According to sublist sequence specific gravity, calculate the prescription quantity that each sublist is subordinate to diversity recommendation list, the sequence specific gravity of sublist is subordinate to according to prescription for the diversity recommendation list of generation and prescription symptom reorders with user's symptom characteristic similarity, obtains final diversity recommendation list.Recommend to consider deficiency for diversity of the prior art to traditional Chinese medical prescription, prescription list and method for reordering of this method by the multiple and different syndromes of generation, generating has multifarious tcm prescription recommendation list.
Description
Technical field
The present invention relates to computer processing technical field more particularly to a kind of Chinese medicinal formulae diversity recommendations based on label
Method.
Background technique
Traditional Chinese medicine is a part of Chinese national characteristic culture originating from China, from the perspective of medicine and medicine
One important branch on boundary.It enters after 21 century, traditional Chinese medicine is gradually increased by social recognition degree, and traditional Chinese medicine is debated due to it
Card, dynamic, whole treatment method suffers from very good therapeutic effect to a variety of psychosomatics, therefore by more
Carry out the concern of more people.
Traditional traditional Chinese medicine has used thousands of years greatly China is ancient on the ground, has formd more complete knowledge body
System, it is the important component of Chinese traditional culture." side " in prescription refers to hospital, " agent ", and ancient times makees " neat ", refers to tune
Agent, prescription are exactly the prescription cured the disease.Tcm prescription of the Chinese nation Jing Guo clinical practice in thousands of years can be described as knowledge of TCM
The essence of resource is one of main inheritance of traditional Chinese medicine and pharmacy the A to Z of.
In traditional Chinese medical science field, card is that the pathology of a certain stage or a certain type is summarized in lysis, generally opposite by one group
It is fixed, have inner link, the disease a certain stage can be disclosed or the sings and symptoms of the lesion essence of a certain type composition;Disease,
That is the general name of sings and symptoms, be shown in lysis it is individual, encourage the phenomenon that.Syndrome is Chinese medicine from treatment angle pair
The summary of body state and description, symptom are then the external manifestations of body state, are the relationship of judgement and argument between the two.
Existing recommended method be applied to Chinese medicinal formulae recommendation often single emphasis user symptom and prescription cure mainly symptom
Similarity, have ignored the information that user's symptom is subordinate to disease, so cause recommend Chinese medicinal formulae lack diversity.So
During Chinese medicinal formulae is recommended, the multiple diseases that may be subordinate to of user's symptom are considered, recommend corresponding prescription for each disease, it can be with
The reference of multiple angles is provided for doctor, the specific requirements situation that doctor fully considers drug is more advantageous to, outputs and be more in line with
The drug of demand.
Summary of the invention
For the prior art diversity of traditional Chinese medical prescription is recommended to consider insufficient, the present invention proposes a kind of based on label
Tcm prescription diversity recommended method is generated by generating prescription list and the method for reordering of multiple and different syndromes with more
The tcm prescription recommendation list of sample.
To achieve the above object, the present invention adopts the following technical scheme that:
A kind of tcm prescription diversity recommended method based on label, the method includes the steps of:
Step S1: symptom syndrome label weight matrix is constructed using Chinese medicine case;
Step S2: the different types of prescription of disease is generated using symptom syndrome label weight matrix and recommends sublist;
Step S3: the weight and user's symptom model of symptom syndrome label and the similarity meter of prescription symptom model are utilized
Operator list ordering specific gravity;
Step S4: according to sublist sequence specific gravity, calculating the prescription quantity that each sublist is subordinate to diversity recommendation list, right
It is subordinate to according to prescription the sequence specific gravity and prescription symptom and user's symptom characteristic phase of sublist in the diversity recommendation list of generation
It reorders like degree, obtains final diversity recommendation list.
Further, step S1, which constructs the specific method of symptom disease label weight matrix, is, according to existing Chinese medicine case, benefit
The related coefficient between symptom and disease is calculated with mutual information, which is referred to as the symptom and sign contribution degree of disease, is utilized
The symptom and sign contribution degree of disease constructs symptom disease label weight matrix.Wherein, the calculation formula of mutual information I is as follows:
Wherein, X, Y respectively represent two stochastic variables, and Joint Distribution probability is p (x, y), and p (x) and p (y) indicate this
The limit distribution of two stochastic variables.
Further, step S2 generates the recommendation sublist of different syndrome type prescription using symptom disease label matrix, recommends son
List generate method include:
Symptom is inputted according to user and symptom disease label weight matrix calculates user and inputs the corresponding institute of symptom set S
There is disease tag set T, be directed to each of disease tag set T label, generate prescription and recommend sublist, in sublist
The sequence of prescription according to prescription symptom characteristic and user's input feature vector S sequencing of similarity.
Further, the step S3 calculating sublist sequence specific gravity includes:
The hybrid weight value syn of S3.1 calculating sublist j symptom disease labelweight, calculation formula is as follows:
synweight(j)=δ × syndromemean(j)+γ×syndromemax(j)(2)
Syndrome in formula (2)mean(j) average sign contribution degree of the input symptom for disease j of user is indicated,
syndromemax(j)Indicate maximum sign contribution degree of the input symptom for disease j of user.Use synijIndicate user's input
Symptom i corresponds to the weight of card type j, then syndrome in formula (2)mean(j)、syndromemax(j) calculation formula such as (3), (4)
It is shown:
syndromemax(j)=max (synij) (4)
The hybrid similarity value sim of S3.2 calculating user's symptom model and sublist j prescription symptom modelsymptom(j),
Calculation formula is as follows:
simsymptom(j)=σ × simSymmean(j)+τ×simSymmax(j) (5)
In formula (5), simSymmean(j) average similarity of prescription symptom in user's symptom and sublist is indicated,
simSymmax(j) similar value of prescription symptom most like with user's symptom in sublist is indicated.Use SinputIndicate user's disease
Shape model, Sref(i, j) indicates i-th of prescription symptom model in the recommendation sublist of corresponding disease J, then in formula (5),
simSymmean(j) and simSymmax(j) calculation formula is as follows:
simSymmax=max (sim (Sinput, Sref(i, j))) (7)
Further, the calculating of symptom similarity is calculated by Jaccard coefficient in the S3.2, and Jaccard coefficient is used for
Compare the otherness between finite sample collection, Jaccard coefficient is bigger, and Sample Similarity is higher.
The sequence specific gravity subList of S3.3 calculating sublistweight, calculation formula is as follows:
subListweight=α × synweight+β×simsymptom (8)
Wherein, synweight, simsymptomCalculating as described in S3.1 and S3.2, α and β indicate its coefficient.
Further, step S4 generates final diversity recommendation list, comprising:
S4.1 calculates diversity recommendation list by the structure of sublist according to the sublist sequence specific gravity calculated in step S3
Proportional proportioni, calculation formula is as follows:
Wherein, subListweight(i) it is obtained by step S3, indicates that the sequence rate of specific gravity of i-th of sublist, N represent multiplicity
The quantity of property recommendation list, proportioniEnd value by the way of being rounded downwards.
S4.2 is according to proportioniValue, extract proportion in i-th of sublistiA prescription is added to more
In sample recommendation list.
S4.3 calculates prescription according to the sequence specific gravity that the similarity and prescription of user's symptom and prescription symptom are subordinate to sublist
Sequence index, sorted again to diversity recommendation list, the calculation formula for the index that sorts is as follows:
presindex(i)=sim (Sinput, Spres(i))+ω×subListweight(j, i ∈ j) (10)
Wherein, Sref(i) indicate that the symptom characteristic of i-th of prescription, ω indicate the number of sublist sequence specific gravity,
subListweightThe sequence rate of specific gravity of (j, where i in j) expression prescription i sublist j subjected.
Detailed description of the invention
The present invention is further described in conjunction with the accompanying drawings and embodiments.
Fig. 1 shows the diversity recommended method flow charts based on label;
Fig. 2 indicates symptom and sign contribution degree calculation flow chart;
Fig. 3 indicates symptom-disease label weight matrix schematic diagram;
The rearrangement program flow diagram of Fig. 4 expression diversity recommendation list.
Specific embodiment
In conjunction with the accompanying drawings, the present invention is further explained in detail, as shown in Figure 1, present embodiments providing a kind of base
In the tcm prescription diversity recommended method of label, comprise the following steps:
Step S1 constructs symptom disease label weight matrix using Chinese medicine case.According to " tcm clinical practice diagnosis and treatment term country
Standard (disease part) ", it can learn the specific symptom of a certain card type, but these symptoms can not be learnt for the weight of the card type
Degree is wanted, the related coefficient between symptom and disease is indicated by mutual information, is called disease symptom and sign contribution degree, is utilized
Disease symptom contribution degree constructs symptom disease label weight matrix, and building flow chart is as shown in Figure 2.
S1.1 for collection Chinese medicine case, with reference to " tcm clinical practice diagnosis and treatment term national standard " in case symptom and
Card type is standardized.
S1.2 calculates disease symptom contribution degree in Chinese medicine case using formula (1), and formula is as follows:
Wherein, X, Y respectively represent two stochastic variables of symptom and disease, and Joint Distribution probability is p (x, y), p (x) and p
(y) the limit distribution of the two stochastic variables is indicated.
S1.3 constructs symptom disease label weight matrix according to disease symptom contribution degree, and matrix constructs schematic diagram such as Fig. 3 institute
Show.
Step S2 recommends sublist using the prescription that symptom disease label weight matrix generates different disease types;
S2.1. it is corresponding to generate disease for each disease type for the corresponding all disease information of counting user input symptom
Prescription sublist.
S2.2. the similarity that prescription symptom characteristic and user in the list of each side's jizi for making dumplings input symptom characteristic, antithetical phrase column are calculated
Prescription in table is ranked up by symptom characteristic similarity.Similarity is calculated by Jaccard coefficient, Jaccard coefficient
Calculation formula is such as shown in (2).
Wherein, X indicates that user inputs symptom characteristic vector, and Y indicates prescription symptom characteristic vector.It is arranged for classical symptom
Table indicates that user inputs sympotomatic set feature vector and prescription symptom characteristic vector using one-hot.
Step S3, according to symptom similarity and disease label weight calculation sublist sequence specific gravity;
S3.1 disease j corresponding for sublist calculates the disease label hybrid weight value that user inputs symptom, mixing power
The calculation formula (3) of weight is as follows:
synweight(j)=δ × syndromemean(j)+γ×syndromemax(j) (3)
Wherein, δ, γ indicate coefficient, syndromemean(j), syndromemax(j) it is obtained by formula (4), (5), it is as follows
It is shown:
syndromemax(j)=max (synij) (5)
Wherein, synijIndicate that user inputs symptom i for the weight of sublist syndrome j, by symptom syndrome label weight square
Battle array obtains.
S3.2 calculates the hybrid similarity value of prescription symptom characteristic in user's symptom characteristic and sublist, calculation formula
(6) as follows:
simsymptom(j)=σ × simSymmean(j)+T×simSymmax(j) (6)
Wherein, σ, τ indicate coefficient, simSymmean(j), simSymmax(j) it is obtained by formula (7), (8), as follows:
simSymmax=max (sim (Sinput, Sref(i, j))) (8)
Wherein, sim () indicates similarity calculation, herein refers to the calculating of Jaccard coefficient, SinputIndicate that user inputs symptom
Feature vector, Sref(i, j) indicates prescription symptom characteristic vector.
S3.3 calculates sublist sequence rate of specific gravity, and calculation formula is as follows:
subListweight=α × synweight+β×simsymptom (9)
Wherein, α, β indicate coefficient, SynweightAnd simsymptomCalculating obtained by formula (3), (6).
S3.4 repeats the process of S3.1-S3.3, the sequence rate of specific gravity until obtaining all sublist.
Step S4 generates diversity recommendation list according to sublist sequence specific gravity in proportion, and to the prescription in list into
Rearrangement sequence, flow chart are as shown in Figure 4.
S4.1 calculates each sublist in prescription diversity recommendation list according to the sublist sequence specific gravity obtained in step S3
In prescription quantity, calculation formula is as follows:
Wherein, N refers to the prescription quantity in consequently recommended list, and final prescription number is obtained by the way of being rounded downwards
Amount.
S4.2 is according to the proportion calculated in S4.1i, it is more that the prescription of respective numbers in sublist is added to prescription
In sample recommendation list, initial diversity recommendation list is obtained.
S4.3 is subordinate to the sequence densimeter of sublist to the similarity and prescription according to user's symptom characteristic and prescription feature
The sequence index for calculating diversity recommendation list prescription, reorders to it, the calculation formula for the index that sorts is as follows:
presindex(i)=sim (Sinput, Spres(i))+ω×subListweight(j, i ∈ j)
Taking the above-mentioned ideal embodiment according to the present invention as inspiration, through the above description, relevant staff is complete
Multifarious change and modification can be carried out without departing from the scope of the technological thought of the present invention' entirely.The skill of this invention
Art range is not limited to the contents of the specification, it is necessary to determine its technical scope according to scope of the claims.
Claims (7)
1. a kind of tcm prescription diversity recommended method based on label, it is characterised in that: the method includes the steps of,
Step S1: symptom syndrome label weight matrix is constructed using Chinese medicine case;
Step S2: the different types of prescription of disease is generated using symptom syndrome label weight matrix and recommends sublist;
Step S3: the weight and user's symptom model of symptom syndrome label and similarity calculation of prescription symptom model are utilized
List ordering specific gravity;
Step S4: according to sublist sequence specific gravity, the prescription quantity that each sublist is subordinate to diversity recommendation list is calculated, for life
At diversity recommendation list be subordinate to according to prescription the sequence specific gravity and prescription symptom and user's symptom characteristic similarity of sublist
It reorders, obtains final diversity recommendation list.
2. a kind of tcm prescription diversity recommended method based on label according to claim 1, it is characterised in that: step
The specific method of S1 building symptom disease label weight matrix is, according to existing Chinese medicine case, using mutual information calculate symptom and
Related coefficient between disease, the related coefficient are referred to as the symptom and sign contribution degree of disease, are contributed using the symptom and sign of disease
Degree building symptom disease label weight matrix;Wherein, the calculation formula of mutual information I is as follows:
Wherein, X, Y respectively represent two stochastic variables, and Joint Distribution probability is p (x, y), and p (x) and p (y) indicate the two
The limit distribution of stochastic variable.
3. a kind of tcm prescription diversity recommended method based on label according to claim 1, it is characterised in that: step
S2 generates the recommendation sublist of different syndrome type prescription using symptom disease label matrix, and the method for recommending sublist to generate includes:
Symptom is inputted according to user and symptom disease label weight matrix calculates user and inputs the corresponding all diseases of symptom set S
Tag set T is waited, each of disease tag set T label is directed to, prescription is generated and recommends sublist, prescription in sublist
Sequence according to prescription symptom characteristic and user's input feature vector S sequencing of similarity.
4. a kind of tcm prescription diversity recommended method based on label according to claim 1, it is characterised in that: described
Step S3 calculates sublist sequence specific gravity
The hybrid weight value syn of S3.1 calculating sublist j symptom disease labelweight, calculation formula is as follows:
synweight(j)=δ × syndromemean(j)+γ×syndromemax(j) (2)
Syndrome in formula (2)mean(j) average sign contribution degree of the input symptom for disease j of user is indicated,
syndromemax(j)Indicate maximum sign contribution degree of the input symptom for disease j of user;Use synijIndicate user's input
Symptom i corresponds to the weight of card type j, then syndrome in formula (2)mean(j)、syndromemax(j) calculation formula such as (3), (4)
It is shown:
syndromemax(j)=max (synij) (4)
The hybrid similarity value sim of S3.2 calculating user's symptom model and sublist j prescription symptom modelsymptom(j), it calculates
Formula is as follows:
simsymptom(j)=σ × simSymmean(j)+τ×simSymmax(j) (5)
In formula (5), simSymmean(j) average similarity of prescription symptom in user's symptom and sublist, simSym are indicatedmax(j)
Indicate the similar value of prescription symptom most like with user's symptom in sublist;Use SinputIndicate user's symptom model, Sref
(i, j) indicates i-th of prescription symptom model in the recommendation sublist of corresponding disease J, then in formula (5), simSymmean(j) and
simSymmax(j) calculation formula is as follows:
simSymmax=max (sim (Sinput, Sref(i, j))) (7).
5. a kind of tcm prescription diversity recommended method based on label according to claim 4, it is characterised in that: described
The calculating of symptom similarity is calculated by Jaccard coefficient in S3.2, and Jaccard coefficient is for comparing between finite sample collection
Otherness, Jaccard coefficient is bigger, and Sample Similarity is higher.
6. a kind of tcm prescription diversity recommended method based on label stated according to claim 4, it is characterised in that: S3.3 meter
The sequence specific gravity subList of operator listweight, calculation formula is as follows:
subListweight=α × synweight+β×simsymptom (8)
Wherein, synweight, simsymptomCalculating as described in S3.1 and S3.2, α and β indicate synweight, slmsymptomPower
Weight coefficient.
7. a kind of tcm prescription diversity recommended method based on label according to claim 1, it is characterised in that: step
S4 generates final diversity recommendation list, comprising:
S4.1 calculates diversity recommendation list by the composition ratio of sublist according to the sublist sequence specific gravity calculated in step S3
Example proportioni, calculation formula is as follows:
Wherein, subListweight(i) it is obtained by step S3, indicates that the sequence rate of specific gravity of i-th of sublist, N represent diversity and push away
Recommend the quantity of list, proportioniEnd value by the way of being rounded downwards;
S4.2 is according to proportioniValue, extract proportion in i-th of sublistiA prescription, is added to diversity
In recommendation list;
S4.3 calculates the row of prescription according to the sequence specific gravity that the similarity and prescription of user's symptom and prescription symptom are subordinate to sublist
Sequence index sorts again to diversity recommendation list, and the calculation formula for the index that sorts is as follows:
presindex(i)=sim (Sinput, Spres(i))+ω×subListweight(j, i ∈ j) (10)
Wherein, Sref(i) indicate that the symptom characteristic of i-th of prescription, ω indicate the number of sublist sequence specific gravity, subListweight
The sequence rate of specific gravity of (j, whereiinj) expression prescription i sublist j subjected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811437469.6A CN109637618A (en) | 2018-11-28 | 2018-11-28 | A kind of Chinese medicinal formulae diversity recommended method based on label |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811437469.6A CN109637618A (en) | 2018-11-28 | 2018-11-28 | A kind of Chinese medicinal formulae diversity recommended method based on label |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109637618A true CN109637618A (en) | 2019-04-16 |
Family
ID=66069410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811437469.6A Pending CN109637618A (en) | 2018-11-28 | 2018-11-28 | A kind of Chinese medicinal formulae diversity recommended method based on label |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109637618A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112992378A (en) * | 2021-04-25 | 2021-06-18 | 南京大经中医药信息技术有限公司 | Multi-dimensional traditional Chinese medicine prescription recommendation method and recommendation system |
CN113409911A (en) * | 2021-07-14 | 2021-09-17 | 浙江大学 | Traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200069A (en) * | 2014-08-13 | 2014-12-10 | 周晋 | Drug use recommendation system and method based on symptom analysis and machine learning |
CN105373706A (en) * | 2015-12-04 | 2016-03-02 | 上海斐讯数据通信技术有限公司 | Drug pushing method and system |
CN106095616A (en) * | 2016-06-01 | 2016-11-09 | 哈尔滨工业大学 | Condition Monitoring Data restoration methods based on mutual information Yu multiple linear regression |
CN106933994A (en) * | 2017-02-27 | 2017-07-07 | 广东省中医院 | A kind of core disease card relation construction method based on knowledge of TCM collection of illustrative plates |
CN108062556A (en) * | 2017-11-10 | 2018-05-22 | 广东药科大学 | A kind of drug-disease relationship recognition methods, system and device |
CN108231153A (en) * | 2018-02-08 | 2018-06-29 | 康美药业股份有限公司 | A kind of drug recommends method, electronic equipment and storage medium |
CN108899072A (en) * | 2018-05-31 | 2018-11-27 | 平安医疗科技有限公司 | Traditional Chinese medicinal prescription recommended method, device, computer equipment and storage medium |
-
2018
- 2018-11-28 CN CN201811437469.6A patent/CN109637618A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104200069A (en) * | 2014-08-13 | 2014-12-10 | 周晋 | Drug use recommendation system and method based on symptom analysis and machine learning |
CN105373706A (en) * | 2015-12-04 | 2016-03-02 | 上海斐讯数据通信技术有限公司 | Drug pushing method and system |
CN106095616A (en) * | 2016-06-01 | 2016-11-09 | 哈尔滨工业大学 | Condition Monitoring Data restoration methods based on mutual information Yu multiple linear regression |
CN106933994A (en) * | 2017-02-27 | 2017-07-07 | 广东省中医院 | A kind of core disease card relation construction method based on knowledge of TCM collection of illustrative plates |
CN108062556A (en) * | 2017-11-10 | 2018-05-22 | 广东药科大学 | A kind of drug-disease relationship recognition methods, system and device |
CN108231153A (en) * | 2018-02-08 | 2018-06-29 | 康美药业股份有限公司 | A kind of drug recommends method, electronic equipment and storage medium |
CN108899072A (en) * | 2018-05-31 | 2018-11-27 | 平安医疗科技有限公司 | Traditional Chinese medicinal prescription recommended method, device, computer equipment and storage medium |
Non-Patent Citations (3)
Title |
---|
孟庆波等: "基于数据包络分析法的中医证候量化辨证分型研究", 《中国中药杂志》 * |
杨铭等: "应用复杂***熵网络方法发现中医方剂中的药对", 《药学服务与研究》 * |
王文杰等: "基因组学数据的网络构建与分析方法", 《中国卫生统计》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112992378A (en) * | 2021-04-25 | 2021-06-18 | 南京大经中医药信息技术有限公司 | Multi-dimensional traditional Chinese medicine prescription recommendation method and recommendation system |
CN113409911A (en) * | 2021-07-14 | 2021-09-17 | 浙江大学 | Traditional Chinese medicine formula recommendation method and system based on case clinical phenotype association degree |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kołomańska-Bogucka et al. | Physical activity and the occurrence of postnatal depression—a systematic review | |
Crawford et al. | Are changes in physical work capacity induced by high-intensity functional training related to changes in associated physiologic measures? | |
Bycura et al. | Impact of different exercise modalities on the human gut microbiome | |
WO2021032220A2 (en) | Traditional chinese medicine supplementary diagnosis system based on syndrome factors | |
CN104881463B (en) | Reference case history search method and device based on structured patient record database | |
Del Coso et al. | ACTN3 R577X genotype and exercise phenotypes in recreational marathon runners | |
Lim et al. | The impacts of pilates and yoga on health-promoting behaviors and subjective health status | |
Owlia et al. | Normalized impact factor (NIF): an adjusted method for calculating the citation rate of biomedical journals | |
Martinez-Martin et al. | PHAROS 2.0—A PHysical assistant RObot system improved | |
CN109637618A (en) | A kind of Chinese medicinal formulae diversity recommended method based on label | |
Steele et al. | Slow and steady, or hard and fast? A systematic review and meta-analysis of studies comparing body composition changes between interval training and moderate intensity continuous training | |
CN109817302B (en) | Expert system for fitness | |
Mages et al. | Exercise effects on bone mineral density in men | |
CN107491992A (en) | A kind of intelligent Service proposed algorithm based on cloud computing | |
Sawyer et al. | Supra-versus submaximal cycle ergometer verification of VO2max in males and females | |
TW202015069A (en) | Herbal medicine prescription information processing system, information processing method, and program | |
Bacanoiu et al. | New strategies to improve the quality of life for normal aging versus pathological aging | |
Chiu et al. | Multidisciplinary care after acute care for stroke: a prospective comparison between a multidisciplinary post-acute care group and a standard group matched by propensity score | |
Mugueta-Aguinaga et al. | Frailty level monitoring and analysis after a pilot six-week randomized controlled clinical trial using the FRED exergame including biofeedback supervision in an elderly day care centre | |
Wang et al. | Differential Impact of exercises on Quality-of-life improvement in breast Cancer survivors: A Network Meta-Analysis of Randomized controlled trials | |
Schweda et al. | Proof of concept of a 6-month person-oriented exercise intervention ‘MultiPill-Exercise’among patients at risk of or with multiple chronic diseases: Results of a one-group pilot trial | |
CN108053870A (en) | A kind of accurate nutrition intelligent platform | |
CN107516013A (en) | It is a kind of that the preferable method and system of medicine are carried out by curative effect triangle | |
Papadakis et al. | Cardiorespiratory coordination in collegiate rowing: A network approach to cardiorespiratory exercise testing | |
Monteiro et al. | Bodyweight and combined training reduce chronic low-grade inflammation and improve functional fitness of postmenopausal women |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |