CN109326351A - A kind of aided diagnosis of traditional Chinese medicine method and device of combination artificial intelligence - Google Patents
A kind of aided diagnosis of traditional Chinese medicine method and device of combination artificial intelligence Download PDFInfo
- Publication number
- CN109326351A CN109326351A CN201811187190.7A CN201811187190A CN109326351A CN 109326351 A CN109326351 A CN 109326351A CN 201811187190 A CN201811187190 A CN 201811187190A CN 109326351 A CN109326351 A CN 109326351A
- Authority
- CN
- China
- Prior art keywords
- information
- illness
- default
- primary symptom
- tcm
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention provides a kind of aided diagnosis of traditional Chinese medicine method and devices of combination artificial intelligence, it is user being inputted, semantics recognition and judgement are carried out with the state of an illness of natural language statement, it simultaneously can also be in conjunction with information such as tongue picture, the pulse conditions of patient, Chinese medicine identification is carried out to the illness of patient, four rash processes of the four methods of diagnosis during simulation doctor practises medicine, to realize automatic tcm diagnosis, so that patient or doctor refer to.
Description
Technical field
The present invention relates to natural language processing field, in particular to a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence
And device.
Background technique
With the development of information technology, more and more things can be completed in the case where people stay indoors, network
The new mode of seeing a doctor such as interrogation, remote interrogation starts the sight for gradually entering people.For the mode of such remote interrogation, by
Yu doctor can not be sitting in anywhere or anytime with the enquirement of response patient before computer, therefore in order to guarantee that some of patient ask substantially
Inscribe it is available quickly return to, need to set up automatic diagnosis mechanism.
Existing automatic diagnosis mechanism, the clinical manifestation mostly based on patient's input carry out the screening and matching of illness;So
And for Chinese medicine, it only is unable to complete tcm diagnosis by the statement of patient, Chinese medicine also needs to cooperate the four methods of diagnosis, that is, hopes to hear and ask
It cuts, patient's system is judged and be assessed, to form accurate tcm diagnosis;This proposes the automatic diagnosis mechanism of Chinese medicine
Higher requirement is gone out.
Summary of the invention
It is an object of the invention to overcome the shortage of prior art, a kind of aided diagnosis of traditional Chinese medicine of combination artificial intelligence is provided
Method and device, it is user being inputted, semantics recognition and judgement are carried out with the state of an illness of natural language statement, while can also combine
The information such as tongue picture, the pulse condition of patient carry out Chinese medicine identification to the illness of patient, so that automatic tcm diagnosis is realized, for patient
Or doctor refers to.
The following technical solution is employed to achieve the above object by the present invention:
In a first aspect, the present invention provides a kind of aided diagnosis of traditional Chinese medicine methods of combination artificial intelligence, comprising:
Obtain clinical manifestation information, Tongue Information, pulse condition information and the personal information of patient;
TCM syndrome sequence is generated according to acquired clinical manifestation information, wherein the TCM syndrome sequence includes at least
One TCM syndrome language;
Tongue picture diagnostic message is generated according to the Tongue Information;
Pulse condition diagnostic message is generated according to the pulse condition information;
Obtain default tcm diagnosis table, wherein including at least one illness information, and at least one in the tcm diagnosis table
A tcm diagnosis letter with the clinical manifestation information of the illness information matches and at least one and the illness information matches
Breath, wherein the diagnostic message includes default information of pulse examination and default tongue inspection information;
According to the TCM syndrome word order arrange, from the default tcm diagnosis table obtain clinical manifestation information and it is described in
The illness information that disease word order column matching degree is not less than preset value is cured, candidate illness information is denoted as;
Obtain the tcm diagnosis information of the candidate illness information;
Remember that default information of pulse examination in the tcm diagnosis information and the pulse condition diagnostic message are matched, and the Chinese medicine
Default tongue inspection information in diagnostic message matches illness information with the matched candidate illness of the tongue picture diagnostic message;
The matching illness information is sent to patient and/or doctor.
In an embodiment of the present invention, the personal information includes one of age of patient, occupation, constitution or more
Kind;
Then, described that tongue picture diagnostic message is generated according to the Tongue Information, it specifically includes:
Obtain default tongue picture correction chart, wherein the default tongue picture correction chart includes at least one characteristic information, and with institute
State the matched tongue picture amendment feature of characteristic information;
According to the personal information of acquired patient, characteristic information and described are obtained from the default tongue picture correction chart
The tongue picture of people's information matches corrects feature, is denoted as amendment benchmark Tongue Information;
Tongue picture diagnostic message is generated according to the Tongue Information of acquired patient and the amendment benchmark Tongue Information;
Then, described that pulse condition diagnostic message is generated according to the pulse condition information, it specifically includes:
Obtain default pulse condition correction chart, wherein the default pulse condition correction chart includes at least one characteristic information, and with institute
State the matched pulse condition amendment feature of characteristic information;
According to the personal information of acquired patient, characteristic information and described are obtained from the default pulse condition correction chart
The pulse condition of people's information matches corrects feature, is denoted as amendment benchmark pulse condition information;
Pulse condition diagnostic message is generated according to the pulse condition information of acquired patient and the amendment benchmark pulse condition information.
In an embodiment of the present invention, be not present when in acquired candidate illness, the default information of pulse examination with it is described
The matching of pulse condition diagnostic message, and when the default tongue inspection information and the matched tcm diagnosis information of the tongue picture diagnostic message;
Obtain default illness property list, wherein it include at least one illness information in the default illness property list, and with
The main characterization information of the illness information matches, wherein the main characterization information includes tongue picture or pulse condition;
According to the candidate illness information, matched main characterization information is obtained from the default illness property list;
When the main characterization information is pulse condition;
Remember the default information of pulse examination and the matched candidate illness of the pulse condition diagnostic message in the tcm diagnosis information
To match illness information;
When the main characterization information is tongue picture;
Remember that default tongue inspection information and the matched candidate illness of the tongue picture diagnostic message in the tcm diagnosis information are
Match illness information.
In an embodiment of the present invention, the clinical manifestation information according to acquired in generates TCM syndrome sequence, specifically
Include:
Extract at least one illness unit in order from acquired clinical manifestation information, and according to extracted illness
Unit and its sequence of extraction and generation illness sequence;
Obtain default primary symptom database, wherein the primary symptom database includes at least one primary symptom information;
According to the default primary symptom database, the illness unit in the illness sequence with the primary symptom information matches is remembered,
For primary symptom unit, remembers with the unmatched illness unit of the primary symptom information in the illness sequence, be non-primary symptom unit;
Obtain the non-primary symptom unit with the primary symptom units match;
According to the primary symptom unit and matched non-primary symptom unit, obtained in matched from default TCM syndrome database
Cure disease language;
TCM syndrome sequence is generated according to acquired TCM syndrome language.
Further, in an embodiment of the present invention, remember that i-th of primary symptom unit is the i-th primary symptom list in the illness sequence
Member, wherein i ∈ [1, n], n are the number of primary symptom unit in the illness sequence;
Then, the non-primary symptom unit of the acquisition and the primary symptom units match, specifically includes:
All non-primary symptom units between jth primary symptom unit and+1 primary symptom unit of jth are obtained, are denoted as and the jth primary symptom
The non-primary symptom unit of units match, wherein j ∈ [1, n).
Further, in an embodiment of the present invention, the non-primary symptom unit of the acquisition and the primary symptom units match, also
Include:
All non-primary symptom units after the n-th primary symptom unit are obtained, the non-primary symptom with the n-th primary symptom units match is denoted as
Unit.
In an embodiment of the present invention, the default TCM syndrome database includes Primary database and second databases,
Wherein, the Primary database includes at least one level-one TCM syndrome language, and each level-one TCM syndrome language matches respectively
There are unique second databases, includes at least one and the matched second level of level-one TCM syndrome language in the second databases
TCM syndrome language;
Then, described according to the primary symptom unit and matched non-primary symptom unit, it is obtained from default TCM syndrome database
Matched TCM syndrome language, specifically includes:
The level-one TCM syndrome language with the primary symptom units match is obtained from the Primary database;
It obtains and the matched second databases of level-one TCM syndrome language;
From acquired second databases, the second level TCM syndrome language with the non-primary symptom units match is obtained;
The acquired second level TCM syndrome language of note is matched TCM syndrome language.
Further, when the primary symptom unit does not have matched non-primary symptom unit,
Then, described according to the primary symptom unit and matched non-primary symptom unit, it is obtained from default TCM syndrome database
Matched TCM syndrome language, further includes:
The level-one TCM syndrome language with the primary symptom units match is obtained from the Primary database;
Remember that the level-one TCM syndrome language is matched TCM syndrome language.
Second aspect, the present invention also provides a kind of aided diagnosis of traditional Chinese medicine device of combination artificial intelligence, including memory,
And the executable code and at least one processor of storage in the memory;
Wherein, the memory is stored with executable code, default tcm diagnosis table, default tongue picture correction chart, default arteries and veins
As correction chart, default illness property list, default primary symptom database, default TCM syndrome database;
The processor is coupled to the memory, and is configured to execute the executable code, to realize the present invention
The aided diagnosis of traditional Chinese medicine method of artificial intelligence is combined provided by first aspect.
The third aspect, the present invention also provides a kind of aided diagnosis of traditional Chinese medicine devices of combination artificial intelligence, including patient to believe
Breath obtain module, TCM syndrome sequence generating module, tongue picture diagnostic module, pulse condition diagnostic module, tcm diagnosis table obtain module,
Candidate illness obtains module, matching illness obtains module and sending module;
The patient information obtains module, for obtaining the clinical manifestation information of patient, Tongue Information, pulse condition information and a
People's information;
The TCM syndrome sequence generating module, for generating TCM syndrome sequence according to acquired clinical manifestation information
Column, wherein the TCM syndrome sequence includes at least one TCM syndrome language;
The tongue picture diagnostic module, for generating tongue picture diagnostic message according to the Tongue Information;
The pulse condition diagnostic module, for generating pulse condition diagnostic message according to the pulse condition information;
The tcm diagnosis table obtains module, for obtaining default tcm diagnosis table, wherein wrap in the tcm diagnosis table
Include at least one illness information and at least one with the clinical manifestation information of the illness information matches and at least one and institute
State the tcm diagnosis information of illness information matches, wherein the diagnostic message includes default information of pulse examination and default tongue inspection information;
Candidate's illness obtains module, for being arranged according to the TCM syndrome word order, from the default tcm diagnosis table
It is middle to obtain the illness information of clinical manifestation information and the TCM syndrome word order column matching degree not less than preset value, it is denoted as candidate disease
Disease information;
The matching illness obtains module, for obtaining the tcm diagnosis information of the candidate illness information, and described in note
Default information of pulse examination and the pulse condition diagnostic message in tcm diagnosis information is matched and pre- in the tcm diagnosis information
If tongue inspection information is to match illness information with the matched candidate illness of the tongue picture diagnostic message;
The sending module, for the matching illness information to be sent to patient and/or doctor.
Beneficial effects of the present invention:
The present invention provides a kind of aided diagnosis of traditional Chinese medicine method and devices of combination artificial intelligence, can facing according to patient
The information such as bed performance, pulse condition, tongue picture are combined judgement, so that four rash processes of the four methods of diagnosis during doctor practises medicine are simulated,
And then obtain most suitable tcm diagnosis information.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the aided diagnosis of traditional Chinese medicine method of combination artificial intelligence in one embodiment of the invention;
Fig. 2 is a kind of structural schematic diagram of the aided diagnosis of traditional Chinese medicine device of combination artificial intelligence in one embodiment of the invention.
Specific embodiment
With reference to the accompanying drawing and specific embodiment the present invention will be further described, illustrative examples therein and
Illustrate only to be used to explain the present invention, but not as a limitation of the invention.
In a first aspect, as shown in Figure 1, being wrapped the present invention provides a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence
It includes:
S100: clinical manifestation information, Tongue Information, pulse condition information and the personal information of patient are obtained;
S200: TCM syndrome sequence is generated according to acquired clinical manifestation information, wherein the TCM syndrome sequence packet
Include at least one TCM syndrome language;
S300: tongue picture diagnostic message is generated according to the Tongue Information;
S400: pulse condition diagnostic message is generated according to the pulse condition information;
S500: default tcm diagnosis table is obtained, wherein it include at least one illness information in the tcm diagnosis table, and
At least one is with the clinical manifestation information of the illness information matches and the Chinese medicine of at least one and the illness information matches is examined
Disconnected information, wherein the diagnostic message includes default information of pulse examination and default tongue inspection information;
S600: according to the TCM syndrome word order arrange, from the default tcm diagnosis table obtain clinical manifestation information with
The TCM syndrome word order column matching degree is not less than the illness information of preset value, is denoted as candidate illness information;
S700: the tcm diagnosis information of the candidate illness information is obtained;
S800: remember that default information of pulse examination in the tcm diagnosis information and the pulse condition diagnostic message are matched, and institute
It is to match illness information that the default tongue inspection information in tcm diagnosis information, which is stated, with the matched candidate illness of the tongue picture diagnostic message;
S900: the matching illness information is sent to patient and/or doctor.
Specifically, combining artificial intelligence provided by first aspect present invention in a concrete application scene of the invention
Aided diagnosis of traditional Chinese medicine method is completed by the background server of hospital;
Patient passes through the self-aided terminal set up within the hospital and inputs the clinical manifestation information of oneself, tongue picture picture, pulse condition number
According to and personal information etc., self-aided terminal the information that patient inputs is sent to the background server of the hospital, hospital manages on backstage
The clinical manifestation that reason system is inputted according to user, such as " I started to occur yesterday uncomfortable in chest, and chest is felt as the sense that has thing pressing against
To feel, throat abundant expectoration, body feels heavy, is unwilling to move, and feels very tired, out of strength, it is very tired, it is unwilling to speak more, has a meal
When feel belly it is swollen, do not have appetite.", generate corresponding TCM syndrome sequence be " uncomfortable in chest such as stop up and pain, abundant expectoration, limbs are tired
Weight, spiritlessness and sparing of words, indigestion and loss of appetite abdominal distension ";Meanwhile background server carries out image procossing to the tongue picture picture of the patient received, from
And the tongue picture diagnostic message of patient is obtained, such as thin white fur of tongue;Meanwhile pulse profile data of the background server to the patient received,
Such as pulse condition waveform, analysis comparison is carried out, to obtain the pulse condition diagnostic message of patient, such as surface pulse which can be felt when touched only lightly;
For background server first according to TCM syndrome sequence, obtaining clinical manifestation from default tcm diagnosis table includes in described
The illness information of disease language is cured, and generates the matching degree of the illness information and patient according to the quantity of included TCM syndrome language,
Wherein matching degree is no less than preset value to note, such as 80%, illness information be candidate illness information;Later, background server obtains
With the tcm diagnosis information for being selected illness information matches, the tcm diagnosis information includes the common pulse condition and tongue of the illness
As, and remember that the candidate illness information that wherein pulse condition is surface pulse which can be felt when touched only lightly, tongue picture is thin white fur of tongue is matching illness information;Background server will
Acquired matching illness information is sent on the self-aided terminal that patient uses, while can also be sent to the doctor that patient is registered
On doctor terminal used in raw, doctor is helped to complete tentative diagnosis.
In an embodiment of the present invention, the personal information includes one of age of patient, occupation, constitution or more
Kind;
Then, step S300 is specifically included:
Obtain default tongue picture correction chart, wherein the default tongue picture correction chart includes at least one characteristic information, and with institute
State the matched tongue picture amendment feature of characteristic information;
According to the personal information of acquired patient, characteristic information and described are obtained from the default tongue picture correction chart
The tongue picture of people's information matches corrects feature, is denoted as amendment benchmark Tongue Information;
Tongue picture diagnostic message is generated according to the Tongue Information of acquired patient and the amendment benchmark Tongue Information;
Then, step S400 is specifically included:
Obtain default pulse condition correction chart, wherein the default pulse condition correction chart includes at least one characteristic information, and with institute
State the matched pulse condition amendment feature of characteristic information;
According to the personal information of acquired patient, characteristic information and described are obtained from the default pulse condition correction chart
The pulse condition of people's information matches corrects feature, is denoted as amendment benchmark pulse condition information;
Pulse condition diagnostic message is generated according to the pulse condition information of acquired patient and the amendment benchmark pulse condition information.
Specifically, since the constitution between patient is different, for the benchmark of some specific crowds its pulse condition and tongue picture
Performance may be with common people's different from, and therefore, the present invention also provides the modification methods that a kind of pulse condition, tongue picture diagnose;
It uses the example above, patient can also input some personal information in self-aided terminal, such as age, gender, occupation or root
The constitution information etc. learnt according to pervious diagnosis experience;
Background server to patient tongue picture carry out identifying and diagnosing before, can also according to patient input personal information from
Default tongue picture correction chart obtains matched characteristic information, if the age of patient is 70 years old, and in the default tongue picture correction chart
The characteristic information matched is the elderly, and obtains the matched tongue picture amendment feature of the characteristic information, such as thin lingual fur;I.e. for old age
For patient, thin lingual fur belongs to common phenomenon, and too big association may be had no by falling ill with it, therefore background server is made with thin lingual fur
For the basis for the comparison that the tongue picture of the patient diagnoses, if the result of tongue picture picture recognition that patient sends also is thin lingual fur, after
The tongue picture diagnostic message that platform server generates is that tongue picture is normal;
Meanwhile background server is before the pulse condition to patient identifies, it also can be according to the personal information of input from pre-
If pulse condition correction chart obtains matched characteristic information, the occupation inputted such as patient is sportsman, and the default pulse condition correction chart
In characteristic information also include sportsman, the pulse condition amendment that background server obtains sportsman in the default pulse condition correction chart is special
Sign, such as retarded pulse, the comparison basis of pulse condition diagnosis of the background server using retarded pulse as the patient, if the pulse condition sent according to patient
When data show that the pulse condition of patient is normal pulse, background server judges to have when the patient actually pulse velocity compares normal added
Fastly, therefore the pulse condition diagnostic message of background server generation is rapid pulse.
In an embodiment of the present invention, be not present when in acquired candidate illness, the default information of pulse examination with it is described
The matching of pulse condition diagnostic message, and when the default tongue inspection information and the matched tcm diagnosis information of the tongue picture diagnostic message;
Obtain default illness property list, wherein it include at least one illness information in the default illness property list, and with
The main characterization information of the illness information matches, wherein the main characterization information includes tongue picture or pulse condition;
According to the candidate illness information, matched main characterization information is obtained from the default illness property list;
When the main characterization information is pulse condition;
Remember the default information of pulse examination and the matched candidate illness of the pulse condition diagnostic message in the tcm diagnosis information
To match illness information;
When the main characterization information is tongue picture;
Remember that default tongue inspection information and the matched candidate illness of the tongue picture diagnostic message in the tcm diagnosis information are
Match illness information.
Specifically, carrying out diagnosis in Chinese medicine is, although being particular about the diagnosis of four methods of diagnosis unification, sometimes because of various originals
Cause, such as patient's system, medication, will cause that tongue picture is different from the main disease that pulse condition is reflected, doctor generally can be according to patient at this time
Practical illness accepted or rejected;
Therefore, the present invention also provides a kind of pulse condition, tongue pictures to diagnose the correcting method for the moment that can not unite;
It uses the example above, there is no pulse condition is surface pulse which can be felt when touched only lightly in the candidate illness acquired in the background server, tongue picture is thin lingual fur
When white candidate illness;There is inconsistent situation in pulse condition and tongue picture at this time for background server judgement, then background server root
The main characterization information of the illness is obtained from default illness property list according to candidate illness information, such as described candidate illness information category
In warm disease, background server acquisition warm disease is characterized primarily by tongue picture, i.e., for warm disease, meaning of the tongue picture for clinical syndrome differentiation
Justice is than pulse condition with important, therefore it is matching disease that background server, which remembers in candidate illness information that tongue picture is the candidate illness of thin white fur of tongue,
Disease, without going the performance with reference to its pulse condition.
In one embodiment of the invention, step S200 is specifically included:
Extract at least one illness unit in order from acquired clinical manifestation information, and according to extracted illness
Unit and its sequence of extraction and generation illness sequence;
Specifically, the illness unit is the keyword that user states itself patient's condition or body-feeling, such as dizzy, head
Dusk, headache, headache, tinnitus etc.;The illness sequence is the sequence formed with extracted illness unit, wherein illness in sequence
Word order sequence when the sequence of unit inputs clinical manifestation according to user is arranged;
Such as, the clinical manifestation of user's input is that " last night starts the case where dizzy, headache occur, has the sense of tinnitus once in a while
Feel ", it is " dizzy, headache, tinnitus " according to the illness sequence that above-mentioned clinical manifestation generates.
Obtain default primary symptom database, wherein the primary symptom database includes at least one primary symptom information;
Specifically, the primary symptom information is common keyword in the description state of an illness or physical condition for sufferer;It is such as, dizzy,
Headache, uncomfortable in chest, trick is out of strength, the common statement such as limbs fatigue.
According to the default primary symptom database, the illness unit in the illness sequence with the primary symptom information matches is remembered,
For primary symptom unit, remembers with the unmatched illness unit of the primary symptom information in the illness sequence, be non-primary symptom unit;
Specifically, the non-primary symptom unit is different from common evaluation, but strong to the breaking-out position of symptom, breaking-out
The statement that situation etc. has reference value to doctor's judgement is aggravated at degree, breaking-out interval;Such as, pain is more obvious when meeting cold, leads
Back of ining succession also aches, and the color of phlegm is partially white etc..
Obtain the non-primary symptom unit with the primary symptom units match;
According to the primary symptom unit and matched non-primary symptom unit, obtained in matched from default TCM syndrome database
Cure disease language;
TCM syndrome sequence is generated according to acquired TCM syndrome language.
Further, in an embodiment of the present invention, remember that i-th of primary symptom unit is the i-th primary symptom list in the illness sequence
Member, wherein i ∈ [1, n], n are the number of primary symptom unit in the illness sequence;
Then, the non-primary symptom unit of the acquisition and the primary symptom units match, specifically includes:
All non-primary symptom units between jth primary symptom unit and+1 primary symptom unit of jth are obtained, are denoted as and the jth primary symptom
The non-primary symptom unit of units match, wherein j ∈ [1, n).
Specifically, such as according to user input clinical manifestation information generate illness sequence be " it is uncomfortable in chest, as there is thing pressure
Feeling, abundant expectoration, body feels heavy, is unwilling to move, tired, out of strength, be unwilling speak, belly is swollen, has no appetite "
Wherein, the primary symptom unit of the illness sequential extraction procedures include " uncomfortable in chest, abundant expectoration, body feels heavy, tired, out of strength,
Belly is swollen ", i.e. the 1st primary symptom unit is " uncomfortable in chest ", and the 2nd primary symptom unit is " abundant expectoration ", and the 3rd primary symptom unit is that " body feels heavy
Weight ", and so on;
1st primary symptom unit is that " uncomfortable in chest " and the 2nd primary symptom unit include 1 non-primary symptom unit between " abundant expectoration " " as having
The feeling that thing is pressing against " is " as the sense for having thing pressing against with the matched non-primary symptom unit of the 1st primary symptom unit " uncomfortable in chest "
Feel ".
Further, in an embodiment of the present invention, the non-primary symptom unit of the acquisition and the primary symptom units match, also
Include:
All non-primary symptom units after the n-th primary symptom unit are obtained, the non-primary symptom with the n-th primary symptom units match is denoted as
Unit.
Specifically, using the example above, one shares 6 primary symptom units in the illness sequence, wherein the 6th primary symptom unit is " tripe
Son is swollen ", all non-primary symptom units after the 6th primary symptom unit " belly is swollen " are " having no appetite ", i.e., are " tripe with the 6th primary symptom unit
Son is swollen " matched non-primary symptom unit is " having no appetite ".
Further, in an embodiment of the present invention, the default TCM syndrome database includes Primary database and two
Grade database, wherein the Primary database includes at least one level-one TCM syndrome language, each level-one TCM syndrome language
It is matched with unique second databases respectively, includes at least one and the level-one TCM syndrome language in the second databases
The second level TCM syndrome language matched;
Then, described according to the primary symptom unit and matched non-primary symptom unit, it is obtained from default TCM syndrome database
Matched TCM syndrome language, specifically includes:
The level-one TCM syndrome language with the primary symptom units match is obtained from the Primary database;
It obtains and the matched second databases of level-one TCM syndrome language;
From acquired second databases, the second level TCM syndrome language with the non-primary symptom units match is obtained;
The acquired second level TCM syndrome language of note is matched TCM syndrome language.
Further, when the primary symptom unit does not have matched non-primary symptom unit, then, and step S600 further include:
The level-one TCM syndrome language with the primary symptom units match is obtained from the Primary database;
Remember that the level-one TCM syndrome language is matched TCM syndrome language.
Second aspect, the present invention also provides a kind of aided diagnosis of traditional Chinese medicine device of combination artificial intelligence, including memory,
And the executable code and at least one processor of storage in the memory;
Wherein, the memory is stored with executable code, default tcm diagnosis table, default tongue picture correction chart, default arteries and veins
As correction chart, default illness property list, default primary symptom database, default TCM syndrome database;
The processor is coupled to the memory, and is configured to execute the executable code, to realize the present invention
The aided diagnosis of traditional Chinese medicine method of artificial intelligence is combined provided by first aspect.
The third aspect, as shown in Fig. 2, the present invention also provides a kind of aided diagnosis of traditional Chinese medicine device of combination artificial intelligence,
Module 100, TCM syndrome sequence generating module 200, tongue picture diagnostic module 300, pulse condition diagnostic module are obtained including patient information
400, tcm diagnosis table obtains module 500, candidate illness obtains module 600, matching illness obtains module 700 and sending module
800;
The patient information obtains module 100, for obtaining clinical manifestation information, the Tongue Information, pulse condition information of patient
And personal information;
The TCM syndrome sequence generating module 200, for generating TCM syndrome according to acquired clinical manifestation information
Sequence, wherein the TCM syndrome sequence includes at least one TCM syndrome language;
The tongue picture diagnostic module 300, for generating tongue picture diagnostic message according to the Tongue Information;
The pulse condition diagnostic module 400, for generating pulse condition diagnostic message according to the pulse condition information;
The tcm diagnosis table obtains module 500, for obtaining default tcm diagnosis table, wherein the tcm diagnosis table
In include at least one illness information and at least one with the clinical manifestation information of the illness information matches and at least one
With the tcm diagnosis information of the illness information matches, wherein the diagnostic message includes default information of pulse examination and default lingual diagnosis
Information;
Candidate's illness obtains module 600, for being arranged according to the TCM syndrome word order, from the default tcm diagnosis
Clinical manifestation information is obtained in table and the TCM syndrome word order column matching degree is not less than the illness information of preset value, is denoted as candidate
Illness information;
The matching illness obtains module 700, for obtaining the tcm diagnosis information of the candidate illness information, and remembers institute
It states default information of pulse examination in tcm diagnosis information and the pulse condition diagnostic message is matched, and in the tcm diagnosis information
Default tongue inspection information is to match illness information with the matched candidate illness of the tongue picture diagnostic message;
The sending module 800, for the matching illness information to be sent to patient and/or doctor.
In a concrete application scene of the invention, device provided by third aspect present invention is integrated in the backstage clothes of hospital
It is engaged in device, to realize method provided by first aspect present invention;
Specifically, patient pass through the self-aided terminal for setting up within the hospital input oneself clinical manifestation information, tongue picture picture,
The information that patient inputs is sent to the background server of the hospital, hospital by pulse profile data and personal information etc., self-aided terminal
The clinical manifestation that background management system is inputted according to user, such as " I started to occur yesterday uncomfortable in chest, and chest is felt as there is thing pressure
Feeling, throat abundant expectoration, body feels heavy, is unwilling to move, and feels very tired, out of strength, very tired, be unwilling speak,
Feel that belly is swollen, does not have appetite when having a meal.", generate corresponding TCM syndrome sequence be " uncomfortable in chest such as stop up and pain, abundant expectoration,
The tired weight of limbs, spiritlessness and sparing of words, indigestion and loss of appetite abdominal distension ";Meanwhile background server carries out at image the tongue picture picture of the patient received
Reason, to obtain the tongue picture diagnostic message of patient, such as thin white fur of tongue;Meanwhile pulse condition of the background server to the patient received
Data carry out analysis comparison such as pulse condition waveform, to obtain the pulse condition diagnostic message of patient, such as surface pulse which can be felt when touched only lightly;
For background server first according to TCM syndrome sequence, obtaining clinical manifestation from default tcm diagnosis table includes in described
The illness information of disease language is cured, and generates the matching degree of the illness information and patient according to the quantity of included TCM syndrome language,
Wherein matching degree is no less than preset value to note, such as 80%, illness information be candidate illness information;Later, background server obtains
With the tcm diagnosis information for being selected illness information matches, the tcm diagnosis information includes the common pulse condition and tongue of the illness
As, and remember that the candidate illness information that wherein pulse condition is surface pulse which can be felt when touched only lightly, tongue picture is thin white fur of tongue is matching illness information;Background server will
Acquired matching illness information is sent on the self-aided terminal that patient uses, while can also be sent to the doctor that patient is registered
On doctor terminal used in raw, doctor is helped to complete tentative diagnosis.
Obviously, above-described embodiment is used for the purpose of clearer expression technical solution of the present invention example, rather than right
The restriction of embodiment of the present invention.To those skilled in the art, it can also make on the basis of the above description other
Various forms of variations or variation, without departing from the inventive concept of the premise, these are all within the scope of protection of the present invention.Cause
The scope of protection of the patent of the invention shall be subject to the appended claims for this.
Claims (10)
1. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence characterized by comprising
Obtain clinical manifestation information, Tongue Information, pulse condition information and the personal information of patient;
TCM syndrome sequence is generated according to acquired clinical manifestation information, wherein the TCM syndrome sequence includes at least one
TCM syndrome language;
Tongue picture diagnostic message is generated according to the Tongue Information;
Pulse condition diagnostic message is generated according to the pulse condition information;
Obtain default tcm diagnosis table, wherein include in the tcm diagnosis table at least one illness information and at least one with
The tcm diagnosis information of the clinical manifestation information of the illness information matches and at least one and the illness information matches,
In, the diagnostic message includes default information of pulse examination and default tongue inspection information;
It is arranged according to the TCM syndrome word order, clinical manifestation information and the Chinese medicine disease is obtained from the default tcm diagnosis table
The illness information that word order column matching degree is not less than preset value is waited, candidate illness information is denoted as;
Obtain the tcm diagnosis information of the candidate illness information;
Remember that default information of pulse examination in the tcm diagnosis information and the pulse condition diagnostic message are matched, and the tcm diagnosis
Default tongue inspection information in information matches illness information with the matched candidate illness of the tongue picture diagnostic message;
The matching illness information is sent to patient and/or doctor.
2. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as described in claim 1, which is characterized in that the individual
Information includes one of age of patient, occupation, constitution or a variety of;
Then, described that tongue picture diagnostic message is generated according to the Tongue Information, it specifically includes:
Obtain default tongue picture correction chart, wherein the default tongue picture correction chart includes at least one characteristic information, and with the spy
Reference ceases matched tongue picture and corrects feature;
According to the personal information of acquired patient, characteristic information and the personal letter are obtained from the default tongue picture correction chart
Matched tongue picture amendment feature is ceased, amendment benchmark Tongue Information is denoted as;
Tongue picture diagnostic message is generated according to the Tongue Information of acquired patient and the amendment benchmark Tongue Information;
Then, described that pulse condition diagnostic message is generated according to the pulse condition information, it specifically includes:
Obtain default pulse condition correction chart, wherein the default pulse condition correction chart includes at least one characteristic information, and with the spy
Reference ceases matched pulse condition and corrects feature;
According to the personal information of acquired patient, characteristic information and the personal letter are obtained from the default pulse condition correction chart
Matched pulse condition amendment feature is ceased, amendment benchmark pulse condition information is denoted as;
Pulse condition diagnostic message is generated according to the pulse condition information of acquired patient and the amendment benchmark pulse condition information.
3. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as described in claim 1, which is characterized in that when acquired
Candidate illness in be not present, the default information of pulse examination is matched with the pulse condition diagnostic message, and the default tongue inspection information
When tcm diagnosis information matched with the tongue picture diagnostic message;
Obtain default illness property list, wherein include at least one illness information in the default illness property list, and with it is described
The main characterization information of illness information matches, wherein the main characterization information includes tongue picture or pulse condition;
According to the candidate illness information, matched main characterization information is obtained from the default illness property list;
When the main characterization information is pulse condition;
Remember that the matched candidate illness of default information of pulse examination and the pulse condition diagnostic message in the tcm diagnosis information is
With illness information;
When the main characterization information is tongue picture;
Remember that default tongue inspection information and the matched candidate illness of the tongue picture diagnostic message in the tcm diagnosis information are to match
Illness information.
4. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as described in claim 1, which is characterized in that the basis
Acquired clinical manifestation information generates TCM syndrome sequence, specifically includes:
Extract at least one illness unit in order from acquired clinical manifestation information, and according to extracted illness unit
And its sequence of extraction and generate illness sequence;
Obtain default primary symptom database, wherein the primary symptom database includes at least one primary symptom information;
According to the default primary symptom database, the illness unit in the illness sequence with the primary symptom information matches is remembered, based on
Disease unit is remembered with the unmatched illness unit of the primary symptom information in the illness sequence, is non-primary symptom unit;
Obtain the non-primary symptom unit with the primary symptom units match;
According to the primary symptom unit and matched non-primary symptom unit, matched Chinese medicine disease is obtained from default TCM syndrome database
Wait language;
TCM syndrome sequence is generated according to acquired TCM syndrome language.
5. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as claimed in claim 4, which is characterized in that remember the disease
I-th of primary symptom unit is the i-th primary symptom unit in disease sequence, wherein i ∈ [1, n], n are primary symptom unit in the illness sequence
Number;
Then, the non-primary symptom unit of the acquisition and the primary symptom units match, specifically includes:
All non-primary symptom units between jth primary symptom unit and+1 primary symptom unit of jth are obtained, are denoted as and the jth primary symptom unit
Matched non-primary symptom unit, wherein j ∈ [1, n).
6. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as claimed in claim 5, which is characterized in that the acquisition
With the non-primary symptom unit of the primary symptom units match, further includes:
All non-primary symptom units after the n-th primary symptom unit are obtained, the non-primary symptom list with the n-th primary symptom units match is denoted as
Member.
7. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as claimed in claim 4, which is characterized in that described default
TCM syndrome database includes Primary database and second databases, wherein the Primary database includes at least one level-one
TCM syndrome language, each level-one TCM syndrome language are matched with unique second databases respectively, in the second databases
Including at least one and the matched second level TCM syndrome language of the level-one TCM syndrome language;
Then, described according to the primary symptom unit and matched non-primary symptom unit, matching is obtained from default TCM syndrome database
TCM syndrome language, specifically include:
The level-one TCM syndrome language with the primary symptom units match is obtained from the Primary database;
It obtains and the matched second databases of level-one TCM syndrome language;
From acquired second databases, the second level TCM syndrome language with the non-primary symptom units match is obtained;
The acquired second level TCM syndrome language of note is matched TCM syndrome language.
8. a kind of aided diagnosis of traditional Chinese medicine method of combination artificial intelligence as claimed in claim 4, which is characterized in that as the master
When disease unit does not have matched non-primary symptom unit,
Then, described according to the primary symptom unit and matched non-primary symptom unit, matching is obtained from default TCM syndrome database
TCM syndrome language, further includes:
The level-one TCM syndrome language with the primary symptom units match is obtained from the Primary database;
Remember that the level-one TCM syndrome language is matched TCM syndrome language.
9. a kind of aided diagnosis of traditional Chinese medicine device of combination artificial intelligence, which is characterized in that including memory and be stored in described deposit
Executable code and at least one processor in reservoir;
Wherein, the memory is stored with executable code, default tcm diagnosis table, default tongue picture correction chart, default pulse condition and repairs
Positive table, default illness property list, default primary symptom database, default TCM syndrome database;
The processor is coupled to the memory, and is configured to execute the executable code, to realize such as claim
The aided diagnosis of traditional Chinese medicine method of combination artificial intelligence described in 1 to 8 any one.
10. a kind of aided diagnosis of traditional Chinese medicine device of combination artificial intelligence, which is characterized in that including patient information obtain module, in
It cures disease sequence generating module, tongue picture diagnostic module, pulse condition diagnostic module, tcm diagnosis table and obtains module, candidate illness acquisition
Module, matching illness obtain module and sending module;
The patient information obtains module, for obtaining clinical manifestation information, Tongue Information, pulse condition information and the personal letter of patient
Breath;
The TCM syndrome sequence generating module, for generating TCM syndrome sequence according to acquired clinical manifestation information,
Described in TCM syndrome sequence include at least one TCM syndrome language;
The tongue picture diagnostic module, for generating tongue picture diagnostic message according to the Tongue Information;
The pulse condition diagnostic module, for generating pulse condition diagnostic message according to the pulse condition information;
The tcm diagnosis table obtains module, for obtaining default tcm diagnosis table, wherein includes extremely in the tcm diagnosis table
Few illness information and at least one with the clinical manifestation information of the illness information matches and at least one and the disease
The tcm diagnosis information of disease information matches, wherein the diagnostic message includes default information of pulse examination and default tongue inspection information;
Candidate's illness obtains module, for being arranged according to the TCM syndrome word order, obtains from the default tcm diagnosis table
It takes clinical manifestation information and the TCM syndrome word order column matching degree to be not less than the illness information of preset value, is denoted as candidate illness letter
Breath;
The matching illness obtains module, for obtaining the tcm diagnosis information of the candidate illness information, and remembers the Chinese medicine
Default information of pulse examination and the pulse condition diagnostic message in diagnostic message is matched, and the default tongue in the tcm diagnosis information
It is to match illness information that information, which is examined, with the matched candidate illness of the tongue picture diagnostic message;
The sending module, for the matching illness information to be sent to patient and/or doctor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811187190.7A CN109326351A (en) | 2018-10-12 | 2018-10-12 | A kind of aided diagnosis of traditional Chinese medicine method and device of combination artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811187190.7A CN109326351A (en) | 2018-10-12 | 2018-10-12 | A kind of aided diagnosis of traditional Chinese medicine method and device of combination artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109326351A true CN109326351A (en) | 2019-02-12 |
Family
ID=65262008
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811187190.7A Pending CN109326351A (en) | 2018-10-12 | 2018-10-12 | A kind of aided diagnosis of traditional Chinese medicine method and device of combination artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109326351A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111445995A (en) * | 2020-03-30 | 2020-07-24 | 崔书克 | Artificial intelligence auxiliary diagnosis method and system based on traditional Chinese medicine big data analysis |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107066814A (en) * | 2017-03-09 | 2017-08-18 | 南京邮电大学 | A kind of traditional Chinese medical science intelligent auxiliary diagnosis system cooperateed with based on the four methods of diagnosis |
CN107242857A (en) * | 2017-06-12 | 2017-10-13 | 南开大学 | The intelligent traditional Chinese medical science based on deep learning integrates diagnosis and therapy system |
CN107578818A (en) * | 2017-08-25 | 2018-01-12 | 广州宝荣科技应用有限公司 | A kind of auxiliary evolution method and device based on deep learning |
CN107818822A (en) * | 2017-10-14 | 2018-03-20 | 深圳市前海安测信息技术有限公司 | The traditional Chinese medical science is preventiveed treatment of disease assisting in diagnosis and treatment system and its data processing equipment |
-
2018
- 2018-10-12 CN CN201811187190.7A patent/CN109326351A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107066814A (en) * | 2017-03-09 | 2017-08-18 | 南京邮电大学 | A kind of traditional Chinese medical science intelligent auxiliary diagnosis system cooperateed with based on the four methods of diagnosis |
CN107242857A (en) * | 2017-06-12 | 2017-10-13 | 南开大学 | The intelligent traditional Chinese medical science based on deep learning integrates diagnosis and therapy system |
CN107578818A (en) * | 2017-08-25 | 2018-01-12 | 广州宝荣科技应用有限公司 | A kind of auxiliary evolution method and device based on deep learning |
CN107818822A (en) * | 2017-10-14 | 2018-03-20 | 深圳市前海安测信息技术有限公司 | The traditional Chinese medical science is preventiveed treatment of disease assisting in diagnosis and treatment system and its data processing equipment |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111445995A (en) * | 2020-03-30 | 2020-07-24 | 崔书克 | Artificial intelligence auxiliary diagnosis method and system based on traditional Chinese medicine big data analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Vos et al. | Existential therapies: a meta-analysis of their effects on psychological outcomes. | |
Heidel | Hippocratic medicine: Its spirit and method | |
CN107578818B (en) | Auxiliary evolution method and device based on deep learning | |
CN111984771A (en) | Automatic inquiry system based on intelligent conversation | |
CN106295198A (en) | Standard patient system and method based on VR virtual reality technology | |
CN109166619A (en) | Chinese medicine intelligent diagnostics auxiliary system and method based on neural network algorithm | |
CN113436723A (en) | Video inquiry method, device, equipment and storage medium | |
CN115376648A (en) | Intelligent prescription generating device and intelligent prescription generating system | |
CN116564478A (en) | Auxiliary diagnosis method, system, equipment and storage medium for traditional Chinese medicine | |
Erol | Melting bones: The social construction of postmenopausal osteoporosis in Turkey | |
CN107423575A (en) | A kind of trans-regional medical resource concocting method, apparatus and system | |
CN109326351A (en) | A kind of aided diagnosis of traditional Chinese medicine method and device of combination artificial intelligence | |
Mosak | Evaluation in psychotherapy: a study of some current measures | |
Grimm | Toward a theory of gender: Transsexualism, gender, sexuality, and relationships | |
CN107506589A (en) | A kind of Chinese patent drug auxiliary method for pushing and device | |
CN115547499B (en) | Health management system based on interaction of Internet and chronic patient physical sign monitoring terminal | |
Lousberg et al. | Profile characteristics of the MPI‐DLV clusters of pain patients | |
Bell | Premenstrual syndrome and the medicalization of menopause: a sociological perspective | |
Stein | The role of some nonbiomedical parameters in clinical decision making: An ethnographic approach | |
CN110415827A (en) | Tcm inspection training method, electronic equipment and computer readable storage medium based on digital patient | |
CN114388125A (en) | Human-computer interaction-based physique identification method and system and storage medium | |
Saucer | Evangelical renewal therapy: A proposal for integration of religious values into psychotherapy | |
Laws | Marching into the past: A critique of Card and Olsen | |
Whitman et al. | An experimental approach to the psychoanalytic theory of dreams and conflicts | |
Berry et al. | Sex therapy |
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: 20190212 |
|
RJ01 | Rejection of invention patent application after publication |