CN109817333A - A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis - Google Patents
A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis Download PDFInfo
- Publication number
- CN109817333A CN109817333A CN201910217862.2A CN201910217862A CN109817333A CN 109817333 A CN109817333 A CN 109817333A CN 201910217862 A CN201910217862 A CN 201910217862A CN 109817333 A CN109817333 A CN 109817333A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- information
- module
- methods
- data
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims abstract description 108
- 239000003814 drug Substances 0.000 title claims abstract description 33
- 229940079593 drug Drugs 0.000 title claims abstract description 24
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 208000011580 syndromic disease Diseases 0.000 title claims abstract description 20
- 230000004069 differentiation Effects 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 210000001367 artery Anatomy 0.000 claims description 14
- 210000003462 vein Anatomy 0.000 claims description 14
- 208000024891 symptom Diseases 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 4
- 201000010099 disease Diseases 0.000 claims description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000002360 preparation method Methods 0.000 claims description 2
- 238000011282 treatment Methods 0.000 abstract description 12
- 230000008569 process Effects 0.000 abstract description 9
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000003759 clinical diagnosis Methods 0.000 abstract description 6
- 210000002105 tongue Anatomy 0.000 description 24
- 230000036541 health Effects 0.000 description 16
- 238000003066 decision tree Methods 0.000 description 10
- 101100276976 Drosophila melanogaster Drak gene Proteins 0.000 description 8
- 210000002700 urine Anatomy 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 208000030090 Acute Disease Diseases 0.000 description 1
- 206010019233 Headaches Diseases 0.000 description 1
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 231100000869 headache Toxicity 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
Present patent application belongs to Diagnostics of Chinese Medicine and artificial intelligence combination field, the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis is specifically disclosed, including the information acquisition device for acquiring patient information；For receiving the information data of information acquisition device and carrying out the message handler of data processing；Weight judgement is carried out for the data after message handler processing and obtains the logic judgment unit of diagnosis；This programme can solve in tcm diagnosis automation process, can not judge automatically four methods of diagnosis information to the contribution weight of diagnosis, cause to acquire largely smaller to diagnosis contribution or do not have contributive data, medical treatment cost is higher；And there is no the problem of directive function to the raising of traditional Chinese physician's clinical diagnosis level during realizing intelligent tcm diagnosis (dialectical).
Description
Technical field
The present patent application belongs to Diagnostics of Chinese Medicine and artificial intelligence combination field, specifically discloses a kind of four methods of diagnosis information weight
The syndrome Differentiation System of Traditional Chinese Medicine and its method of analysis.
Background technique
It is counted according to the national health health committee, the 1-11 month in 2018, the national total diagnosis and treatment person-time of medical and health organization reach
75.4 hundred million person-times, wherein 40.2 hundred million person-times of Basic medical and health institutions, account for 53.3%.As the first line of defence of citizen's health,
Basic medical and health institutions carry diagnosis and treatment, and sick minor illness, acute disease of changing the place of examination serious disease alleviate the important work of higher level's hospital admissions pressure slowly
With.However for a long time, China's Basic medical and health institutions are but faced with Medical Devices and fall behind, and hygienic mo del lacks problem, difficult
To meet the healthy needs of resident.Therefore, although China has carried out a series of activities for promoting basic health service in recent years,
How to improve the treatment level of Basic medical and health institutions and be still one and cannot be neglected public health problem.
The Chinese medicine disease treatment mode traditional as China is not required to by high-grade, precision and advanced diagnostic equipment, easy honest and clean effect
Feature is more suitable for undertaking the daily diagnosis and treatment work of basic health mechanism compared with western medicine.But Chinese medicine diagnosis and treatment are with macroscopical whole
Based on, it emphasizes experience, is not easy to quantify；The culture of Chinese Medicine Talents also needs at least time of 5-7, and usually requires the longer time
Clinical practice medical technology could be increased to one substantially conform to residents ' health needs level, be unable to satisfy in the short time
Residents ' health requirement.Basic health mechanism Chinese Medicine Talents notch and auxiliary raising traditional Chinese physician can be effectively relieved therefore, it is necessary to a kind of
The system and method for Clinics.
The four methods of diagnosis, diagnosis and treatment, the tcm diagnosis organic component most crucial as traditional Chinese medicine are tcm clinical practice realities
It is most difficult to grasp most important content in trampling.Therefore, the clinic diagnosis level of a traditional Chinese physician is often also diagnosed the illness by it, is distinguished
The technical level of syndrome is determined.On the basis of Chinese medicine four methods of diagnosis information automation standardized acquisition, if it is possible to realize Chinese medicine
The problem of Chinese Medicine Talents lack will be effectively relieved in the automation of diagnosis.Patient comes after basic health medical institutions, only need to be by
Medical worker by certain simple training guides the work for carrying out four methods of diagnosis information collection and inputting computer, can grasp substantially
Its syndrome, and relevant treatment and health information can be obtained.Therefore, it is necessary to one kind, and traditional Chinese physician can be assisted to carry out clinical diagnosis and oneself
The system and method for dynamicization diagnosis.
As AlphaGo defeats the top player of the mankind on go competition field, artificial intelligence technology can be automatic by feat of it
The advantage for dissolving certain challenges of determining, has penetrated into each industry of 21 century.Accurate advertisement is launched, recognition of face, nothing
People's driving, the identification of automedica image is all its more mature application field.And tcm diagnosis information higher-dimension, it is non-thread
The characteristics of property, there is natural compatibility with artificial intelligence technology, therefore can realize that one kind can be assisted using this technology
The system and method for traditional Chinese physician progress clinical diagnosis and automated diagnostic.
In previous tcm diagnosis and the connected applications of artificial intelligence, as China Patent No. be CN104200120A and
Two patents of CN107145736A, are all difficult to be widely applied in a short time.On the one hand existing four methods of diagnosis information examines mode
Tongue diagnosing instrument is such as automated, pulse-taking instrument all also fails to all information for extracting the needs that diagnose the illness of complete specifications, on the other hand
The technology of these patents in four methods of diagnosis infonnation collection process, can not automatization judgement symptom to disease, the contribution degree of symptomatic diagnosis,
It is unable to specific aim personalization examination information.All these patented technologies in order to guarantee diagnosis accuracy, the information of required acquisition
It is excessively complicated, tcm clinical practice at this stage is diagnosed also without directive function.Therefore a kind of four based on artificial intelligence technology are needed
Examine information weight analysis and syndrome Differentiation System of Traditional Chinese Medicine and its method.
Summary of the invention
In view of the above deficiencies, the purpose of the present invention is to provide a kind of syndrome Differentiation System of Traditional Chinese Medicine of four methods of diagnosis information weight analysis and
Its method can not judge automatically four methods of diagnosis information to the contribution weight of diagnosis to solve in tcm diagnosis automation process, cause to need
Acquisition is largely smaller to diagnosis contribution or does not have contributive data, and medical treatment cost is higher；And it (is distinguished in the intelligent tcm diagnosis of realization
Card) there is no the problem of directive function to the raising of traditional Chinese physician's clinical diagnosis level in the process.
In order to achieve the above object, base case of the invention are as follows:
A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis, including the information for acquiring patient information
Collector；For receiving the information data of information acquisition device and carrying out the message handler of data processing；For message handler
Data after processing carry out weight judgement and obtain the logic judgment unit of diagnosis.
Further, the information acquisition device includes the pulse condition that can acquire arteries and veins position, arteries and veins length, pulsewidth, arteries and veins power, pulse frequency information
Acquisition device；Tongue color, the digitlization tongue picture collecting apparatus for diagnostic of the information such as ligulate can be acquired；The amount of multinomial symptom and sign can be acquired
Table interrogation instrument；By display, interactive interface, the human-computer interaction device of the compositions such as input equipment, the human-computer interaction device can be real
When show and need to acquire four methods of diagnosis information category, the contribution weight of information and diagnostic result, and can be by algorithm model, result of correcting errors etc.
Data afferent message processor.
Further, the message handler includes data module, four methods of diagnosis information acquisition module, input/output module, feedback
Module, authentication module, management module；The input/output module is connected with data module, can be according to four methods of diagnosis information collection
The information of input is simultaneously stored into data module by the needs of module, control information acquisition device input four methods of diagnosis information；Described four
Examine information acquisition module, can real-time operation go out the four methods of diagnosis item of information mesh number that need to acquire and its content and be stored in data module
In.After patient's one state of an illness information of every input, the four methods of diagnosis item of information mesh number and its content that need to be acquired can all change a lot, most
Substantially need to comprehensively acquire four methods of diagnosis information includes that can be acquired by tongue diagnosing instrument, pulse-taking instrument and the dedicated scale of this seminar establishment etc.
: tongue color, ligulate, color local feature, coating colour, coating nature；Arteries and veins position, arteries and veins is long, pulsewidth, arteries and veins power, arteries and veins shape；Body characteristics, psychological characteristics,
Morbidity tendency, complexion, the colour of skin, two just, uncomfortable position and property；Gender, age etc..It both include mainly being acquired by electronic instrument
Continuity numerical value graphic data such as body temperature, also include qualitative data if any no headache etc..This module can handle these two types of numbers simultaneously
According to mainly by one according to the data creation being stored in data module, decision tree is constituted made of trimming.Decision tree is a kind of
The most basic algorithm model for being widely used in classification task is the basic Component units of the excellent algorithm model of multiple performance.This
Although the lower realization for being seldom individually used for classification task of algorithm accuracy rate, its various dimensions weight analysis performance are very excellent
It is different.Each node of decision tree is made of a state of an illness data, is all a possible diagnostic result per a piece of final leaf.On
The selection of position node is determined according to making the confusion degree of sample diagnostic result minimum after division.Confusion degree is usually by base
Buddhist nun's coefficient or comentropy determine.The data set given for one, number of tags K-1, number of nodes m, the region after division are
Rm, the sample number inside region is Nm, then for a sample in Rm, the probability that label is K is Pmk, then
Gini coefficient is
Comentropy is
If patient acquires information without particularly pertinent four methods of diagnosis information, according to the path of script decision tree, Chinese medicine is simulated
Teacher's purposefully interrogation process；If patient has particularly pertinent symptom or sign, using this feature as the first partitioning site, weight
It calculates the comentropy of remaining feature newly to construct a new decision tree, continues targetedly to acquire according to the path of decision tree
Information.Such as there are tongues red, yellow tongue fur, scanty drak urine these three correlated characteristic information, weight is roughly the same, but scanty drak urine is opposite
Higher, therefore this module can select scanty drak urine as node diagnostic, after scanty drak urine is selected, tongue is red, yellow tongue fur different degree
Can then be lower because they can the impurity level of reduction removed by the feature of scanty drak urine, i.e., tongue is red, yellow tongue fur can be drawn
The fever and chills classification divided is separated by scanty drak urine, therefore this module will continue to the identification label selected under " heat symptom-complex "；But
If patient emphasizes that tongue is red, that is, set that tongue is red as first node, this module can still choose scanty drak urine as the second section
Point, because of the red judgement that can not support " heat symptom-complex " of tongue, and it is bigger compared with yellow tongue fur weight for diagnosis " heat symptom-complex " scanty drak urine.It is worth
It is noted that on the one hand this decision tree is that the algorithm of this module automatically generates and automatically updated according to the data in data module
, higher-dimension challenge can not be solved the problems, such as by avoiding artificial assignment weighting building this method of decision tree；On the other hand, originally
Module is as four methods of diagnosis information acquisition module, those information need to be acquired by being only used for judgement, without doing last diagnostic.
Further, data module and other all modules have connection；Data module by existing case data and its can examine
Disconnected and feedback result is stored with the identifiable data format of the computer of matroid, and data module can restore data to locally
Reservoir or cloud reservoir, can be by existing case data and its diagnosis and feedback result with the format similar to matrix
It is stored.Various four methods of diagnosis information determine that the data such as result are all stored in data module with identical data essence, but calculate
Machine can identify differentiation；Its another important function is exactly to back up, and restores data to locally-stored device or cloud reservoir.It is stored up
Deposit structure such as:
[[' name ' ' gender ' ' age ' ' tongue color ' ' arteries and veins position ' ...]
[' Zhang San ' ' female ' ' 21 ' ' tongue is red ' ' normal ' ...]
[' Li Si ' ' male ' ' 23 ' ' pale tongue ' ' deeptensepulse ' ...]
……
[' king's pockmarks ' ' female ' ' 25 ' ' tongue is red ' ' floating pulse ' ...]
[' wantonly six ' ' male ' ' 29 ' ' tongue is purple dark ' ' deeptensepulses ' ...]].
Further, logic judgment unit includes: tcm diagnosis module, weight judgment module；The tcm diagnosis module
The diagnostic result that the case can be gone out using the four methods of diagnosis data operation being stored in data module, is then stored into data mould for result
In block；Initial algorithm model built in the tcm diagnosis module is neural network.It can be verified module in the process of running
The middle higher algorithm replacement of accuracy rate.
Further, weight judgment module can utilize the four methods of diagnosis information data and corresponding diagnosis being stored in data module
Data operation goes out each four methods of diagnosis information to the contribution degree weight of the diagnosis, and is stored in data module；The weight judgement
The initial algorithm model of module is Random Forest, and working principle is to be concentrated with to put back to ground grab sample formation one from data
The decision tree of fixed number amount, a new sample diagnostic result are voted by all decision trees in random forest and are determined, each certainly
The principle of plan tree, being related to parameter has:
N_estimators, criterion, max_depth, min_samples_split, min_samples_leaf,
Min_weight_fraction_leaf, max_features, max_leaf_nodes, min_impurity_decrease,
Min_impurity_split, bootstrap, oob_score, n_jobs, random_state, verbose, warm_
Start, class_weight.
Further, feedback module is connected with data module, and the diagnosis knot of the computer case can be fed back to by traditional Chinese physician
Whether fruit is correct, and is stored in data module.
Further, authentication module can be imported and be adjusted various algorithm models, and benefit by information acquisition device by operator
Diagnosis is made with the data being stored in data module, as system is continued on, the case being stored in data module is believed
, also can be automatically after predetermined time interval or other activation threshold value conditions after the quantity and data content of breath change, it will
The accuracy of algorithm model in various authentication modules is higher by accuracy compared with the algorithm model in tcm diagnosis module
Algorithm model replace into tcm diagnosis module.
Further, management module is to integrate the system framework and energy batch input, modification case information of major module, is adjusted
Each module parameter and initialization system.
The Chinese medical discrimination method and step of this four methods of diagnosis information weight analysis is as follows:
(1) essential information acquires: acquiring patient information such as: such as age, gender, name etc.；
(2) information stores: the information acquired in step (1) being carried out data preparation and storage, is stored up in the form of new entry
There are in floating storage region；
(3) diagnostic message acquires: one patient of acquisition is most prominent or the higher information of diagnostic value of system recommendation；Such as master
Tell symptom, information of pulse examination, tongue inspection information etc. adds it in step (2) entry generated；
(4) analyze: judgement, analysis continue to acquire which four methods of diagnosis information facilitates diagnosis or contributes highest to diagnosis；
(5) continued to acquire the corresponding four methods of diagnosis information of patient according to the conclusion that step (4) obtains；And the freshly harvested four methods of diagnosis are believed
Breath is added into step (2) entry generated；
(6) (1)-(5) step is repeated, is diagnosed using neural network model algorithm, diagnostic result is stored, while is right
Judge diagnostic result and four methods of diagnosis information to the contribution weighted value of the diagnosis.
The working principle and beneficial effect of this base case are:
This programme solves in tcm diagnosis automation process, can not judge automatically four methods of diagnosis information to the contribution weight of diagnosis,
Cause to acquire largely smaller to diagnosis contribution or do not have contributive data, medical treatment cost is higher；And it is examined in the intelligent Chinese medicine of realization
There is no the problem of directive function to the raising of traditional Chinese physician's clinical diagnosis level during disconnected (dialectical).
This system and method dynamic real-time judge, update need to acquire those four methods of diagnosis information, before maintaining accuracy
Put, solve the problems, such as other methods must each case of comprehensive collection as far as possible all state of an illness data, reduce
Medical treatment cost, improves the compliance of patient.
The contribution weight that this system and method can differentiate, show four methods of diagnosis information to diagnostic result, auxiliary improve in youth
The clinical diagnosis of doctor is horizontal, and basic health medical institutions maturation Chinese Medicine Talents gap problem is effectively relieved.
Detailed description of the invention
Fig. 1 is schematic structural view of the invention；
Fig. 2 is middle four methods of diagnosis information acquisition module working principle diagram of the invention；
Fig. 3 is tcm diagnosis module working principle diagram of the invention；
Fig. 4 is the basic Component units working principle diagram of weight judgment module of the invention.
Specific embodiment
It is further described below by specific embodiment:
Embodiment is basic as shown in attached drawing 1-4:
A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis, including the information for acquiring patient information
Collector；For receiving the information data of information acquisition device and carrying out the message handler of data processing；For message handler
Data after processing carry out weight judgement and obtain the logic judgment unit of diagnosis.
The information acquisition device includes the pulse-tracing collection dress that can acquire arteries and veins position, arteries and veins length, pulsewidth, arteries and veins power, pulse frequency information
It sets；Tongue color, the digitlization tongue picture collecting apparatus for diagnostic of the information such as ligulate can be acquired；The scale interrogation of multinomial symptom and sign can be acquired
Instrument；By display, interactive interface, the human-computer interaction device of the compositions such as input equipment, the human-computer interaction device be can display real-time
Four methods of diagnosis information category, the contribution weight of information and diagnostic result need to be acquired out, and can be by algorithm model, the data such as result of correcting errors pass
Enter message handler.
The message handler includes data module, four methods of diagnosis information acquisition module, input/output module, feedback module, tests
Demonstrate,prove module, management module；The input/output module is connected with data module, can be according to the need of four methods of diagnosis information acquisition module
It wants, the information of input is simultaneously stored into data module by control information acquisition device input four methods of diagnosis information；The four methods of diagnosis information is adopted
Collect module, can real-time operation go out the four methods of diagnosis item of information mesh number that need to acquire and its content and be stored in data module.
The data module and other all modules has connection；Data module can be by existing case data and its diagnosis
It is stored with feedback result with the identifiable data format of the computer of matroid, data module can restore data and store up to local
Storage or cloud reservoir.
The logic judgment unit includes: tcm diagnosis module, weight judgment module；The tcm diagnosis module can benefit
The diagnostic result for going out the case with the four methods of diagnosis data operation being stored in data module, is then stored into data module for result
In；Initial algorithm model built in the tcm diagnosis module is neural network.
The weight judgment module can utilize the four methods of diagnosis information data and corresponding diagnosis being stored in data module
Data operation goes out each four methods of diagnosis information to the contribution degree weight of the diagnosis, and is stored in data module；The weight judgement
The initial algorithm model of module is Random Forest.
The feedback module is connected with data module, and the diagnostic result of the computer case can be fed back to by traditional Chinese physician
It is whether correct, and be stored in data module.
The authentication module can be imported by information acquisition device by operator and adjust various algorithm models, and be utilized
The data being stored in data module make diagnosis, and the quantity and data content for being stored in the case information in data module occur
It, also can be automatically after predetermined time interval or other activation threshold value conditions, by the algorithm mould in various authentication modules after change
The accuracy of type is examined compared with the algorithm model in tcm diagnosis module, by the higher algorithm model displacement of accuracy to Chinese medicine
In disconnected module.
The management module is to integrate the system framework and energy batch input, modification case information of major module, is adjusted
Each module parameter and initialization system.
It specific implementation process and has the beneficial effect that:
The essential information such as age of patient, gender, name etc., through information acquisition device input system are acquired and inputted first
Afterwards, specific format is organized by data module and is stored in floating storage region in the form of new entry；Then one is acquired
Patient is most prominent or the higher information of diagnostic value of system recommendation, such as chief complaint, information of pulse examination, tongue inspection information etc., equally
Through information acquisition device input system and it is added in the entry generated；Four methods of diagnosis information acquisition module can read entry information,
And judges, analyzes and continue to acquire those state of an illness data to diagnosis contribution highest, and analysis result is existed via input/output module
It is shown in human-computer interaction device, finally continues to acquire state of an illness data according to display result by operator, and will newly acquire
Four methods of diagnosis information be added in entry；Above-mentioned process is repeated, until the state of an illness data of acquisition can be such that four methods of diagnosis information acquisition module does
All collected four methods of diagnosis information are stored into data module by tentative diagnosis out；Tcm diagnosis module reads entry information, does
It diagnoses out, diagnostic result is stored into data module, and shown and paid a home visit in human-computer interaction device by input/output module
Disconnected result and each four methods of diagnosis information are obtaining except diagnostic result, traditional Chinese physician is also using symptom the contribution weight of the diagnosis
Contribution weight promote that examination is horizontal, feedback module can also be passed through and feed back the just no as a result, with lifting system of computer diagnosis
Applicability.
What has been described above is only an embodiment of the present invention, and the common sense such as well known specific structure and characteristic are not made herein in scheme
Excessive description.It, without departing from the structure of the invention, can be with it should be pointed out that for those skilled in the art
Several modifications and improvements are made, these also should be considered as protection scope of the present invention, these all will not influence what the present invention was implemented
Effect and patent practicability.
Claims (10)
1. a kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis, which is characterized in that including for acquiring patient
The information acquisition device of information；For receiving the information data of information acquisition device and carrying out the message handler of data processing；For
Data after message handler processing carry out weight judgement and obtain the logic judgment unit of diagnosis.
2. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 1, feature exist
In the information acquisition device includes the pulse condition collecting device that can acquire arteries and veins position, arteries and veins length, pulsewidth, arteries and veins power, pulse frequency information；It can
To acquire tongue color, the digitlization tongue picture collecting apparatus for diagnostic of the information such as ligulate；The scale interrogation instrument of multinomial symptom and sign can be acquired；By
Display, interactive interface, the human-computer interaction device of the compositions such as input equipment, the human-computer interaction device, which can display real-time out, to be adopted
Collect the contribution weight and diagnostic result of four methods of diagnosis information category, information, and can be by algorithm model, the data afferent message such as result of correcting errors
Processor.
3. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 2, feature exist
In the message handler includes data module, four methods of diagnosis information acquisition module, input/output module, feedback module, verifying mould
Block, management module；The input/output module is connected with data module, can according to the needs of four methods of diagnosis information acquisition module,
The information of input is simultaneously stored into data module by control information acquisition device input four methods of diagnosis information；The four methods of diagnosis information collection mould
Block, can real-time operation go out the four methods of diagnosis item of information mesh number that need to acquire and its content and be stored in data module.
4. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 3, feature exist
In the data module and other all modules have connection；Data module can be by existing case data and its diagnosis and anti-
Feedback result is stored with the identifiable data format of the computer of matroid, and data module can restore data to locally-stored device
Or cloud reservoir.
5. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 3, feature exist
In the logic judgment unit includes: tcm diagnosis module, weight judgment module；The tcm diagnosis module can utilize storage
There are the diagnostic results that the four methods of diagnosis data operation in data module goes out the case, and then result is stored into data module；Institute
The initial algorithm model built in tcm diagnosis module stated is neural network.
6. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 5, feature exist
In the weight judgment module can be transported using the four methods of diagnosis information data and corresponding diagnostic data being stored in data module
Each four methods of diagnosis information is calculated to the contribution degree weight of the diagnosis, and is stored in data module；At the beginning of the weight judgment module
The algorithm model of beginning is Random Forest.
7. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 3, feature exist
In, the feedback module is connected with data module, can be fed back to by traditional Chinese physician the computer case diagnostic result whether
Correctly, it and is stored in data module.
8. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 3, feature exist
In the authentication module can be imported and be adjusted various algorithm models by information acquisition device by operator, and utilize storage
Data in data module make diagnosis, and the quantity and data content for the case information being stored in data module change
It afterwards, also can be automatically after predetermined time interval or other activation threshold value conditions, by the algorithm model in various authentication modules
Accuracy is compared with the algorithm model in tcm diagnosis module, by the higher algorithm model displacement of accuracy to tcm diagnosis mould
In block.
9. the syndrome Differentiation System of Traditional Chinese Medicine and its method of a kind of four methods of diagnosis information weight analysis according to claim 3, feature exist
In the management module is to integrate the system framework and energy batch input, modification case information of major module, adjusts each module
Parameter and initialization system.
10. a kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis, which is characterized in that method and step is as follows:
(1) essential information acquires: acquiring patient information such as: such as age, gender, name etc.；
(2) information stores: the information acquired in step (1) being carried out data preparation and storage, is stored in the form of new entry
In floating storage region；
(3) diagnostic message acquires: one patient of acquisition is most prominent or the higher information of diagnostic value of system recommendation；Such as main suit's disease
Shape, information of pulse examination, tongue inspection information etc. add it in step (2) entry generated；
(4) analyze: judgement, analysis continue to acquire which four methods of diagnosis information facilitates diagnosis or contributes highest to diagnosis；
(5) continued to acquire the corresponding four methods of diagnosis information of patient according to the conclusion that step (4) obtains；And freshly harvested four methods of diagnosis information is added
It is added into step (2) entry generated；
(6) (1)-(5) step is repeated, is diagnosed using neural network model algorithm, diagnostic result is stored, while to judgement
The contribution weighted value of diagnostic result and four methods of diagnosis information to the diagnosis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910217862.2A CN109817333A (en) | 2019-03-21 | 2019-03-21 | A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910217862.2A CN109817333A (en) | 2019-03-21 | 2019-03-21 | A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109817333A true CN109817333A (en) | 2019-05-28 |
Family
ID=66609936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910217862.2A Pending CN109817333A (en) | 2019-03-21 | 2019-03-21 | A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109817333A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223749A (en) * | 2019-06-14 | 2019-09-10 | 电子科技大学 | Chinese medical discrimination aid decision-making method based on PCNN network and attention mechanism |
| CN110432864A (en) * | 2019-07-19 | 2019-11-12 | 成都中医药大学 | A kind of tcm constitution dynamic change discrimination method and system |
| CN111261290A (en) * | 2020-01-08 | 2020-06-09 | 来康科技有限责任公司 | Method and system for determining characteristic information of target object |
| CN112509672A (en) * | 2020-12-14 | 2021-03-16 | 河南经方云科技有限公司 | Traditional Chinese medicine dialectical treatment auxiliary system and method based on artificial intelligence |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1759804A (en) * | 2005-11-02 | 2006-04-19 | 浙江大学 | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis |
| 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 |
-
2019
- 2019-03-21 CN CN201910217862.2A patent/CN109817333A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1759804A (en) * | 2005-11-02 | 2006-04-19 | 浙江大学 | Intelligent analyzing and differentiating method of herbalist doctor through integrated references form four parts of diagnosis |
| 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 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110223749A (en) * | 2019-06-14 | 2019-09-10 | 电子科技大学 | Chinese medical discrimination aid decision-making method based on PCNN network and attention mechanism |
| CN110432864A (en) * | 2019-07-19 | 2019-11-12 | 成都中医药大学 | A kind of tcm constitution dynamic change discrimination method and system |
| CN111261290A (en) * | 2020-01-08 | 2020-06-09 | 来康科技有限责任公司 | Method and system for determining characteristic information of target object |
| CN112509672A (en) * | 2020-12-14 | 2021-03-16 | 河南经方云科技有限公司 | Traditional Chinese medicine dialectical treatment auxiliary system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109817333A (en) | A kind of syndrome Differentiation System of Traditional Chinese Medicine and its method of four methods of diagnosis information weight analysis | |
| CN108198620B (en) | Skin disease intelligent auxiliary diagnosis system based on deep learning | |
| CN109509551A (en) | A kind of common disease intelligent diagnosing method and system | |
| CN109920508A (en) | prescription auditing method and system | |
| CN107066814A (en) | A kind of traditional Chinese medical science intelligent auxiliary diagnosis system cooperateed with based on the four methods of diagnosis | |
| CN107369151A (en) | System and method are supported in GISTs pathological diagnosis based on big data deep learning | |
| CN104382570B (en) | Digital full-automatic health status detection device | |
| WO2019041711A1 (en) | Chronic disease follow-up monitoring system and method based on health examination all-in-one machine | |
| CN105054897A (en) | Multi-combined-type traditional Chinese medicine electronic diagnosis and treatment method and system | |
| CN104766259A (en) | Medical clinical quality monitoring and evaluation system based on single-disease model | |
| CN108877921A (en) | Medical intelligent diagnosis method and medical intelligent diagnosis system | |
| CN106777873A (en) | Community's smart cloud health services system | |
| CN101647696A (en) | Intelligent system for health diagnosis and treatment | |
| CN109948719A (en) | A kind of eye fundus image quality automatic classification method based on the intensive module network structure of residual error | |
| CN108109692A (en) | The selection method and system of a kind of therapeutic scheme | |
| CN106919804A (en) | Medicine based on clinical data recommends method, recommendation apparatus and server | |
| Bradley et al. | Handover: Faster and safer? | |
| CN107430645A (en) | The system notified for the laboratory evaluation automated analysis in CICU and risk | |
| CN107895518A (en) | Information-based nurse training method | |
| CN107799180A (en) | Mental Capital training for promotion method and system based on cognitive-behavioral therapy | |
| CN109978873A (en) | A kind of intelligent physical examination system and method based on Chinese medicine image big data | |
| CN106650253A (en) | Dialectical system of traditional Chinese medicine | |
| CN106951710A (en) | CAP data systems and method based on privilege information Learning support vector machine | |
| CN110136113A (en) | A kind of vagina pathology image classification method based on convolutional neural networks | |
| CN204813807U (en) | Box -like traditional chinese medical science electron equipment of diagnosing of multiunit |
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 |
Application publication date: 20190528 |
|
| RJ01 | Rejection of invention patent application after publication |