CN109408631A - Drug data processing method, device, computer equipment and storage medium - Google Patents
Drug data processing method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109408631A CN109408631A CN201811020524.1A CN201811020524A CN109408631A CN 109408631 A CN109408631 A CN 109408631A CN 201811020524 A CN201811020524 A CN 201811020524A CN 109408631 A CN109408631 A CN 109408631A
- Authority
- CN
- China
- Prior art keywords
- drug
- drug data
- text
- disease category
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Pathology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
This application involves field of computer technology, more particularly to a kind of drug data processing method, device, computer equipment and storage medium based on machine learning.The described method includes: obtaining multiple drug datas, drug data includes specification, and specification includes multiple fields and corresponding content of text；Extract the corresponding content of text of preset field in specification；Classifier is obtained, content of text is input in classifier, the corresponding disease category of drug data is exported by classifier, and disease category is added in drug data；Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in classification of diseases coding schedule；The disease category of drug data is matched with classification of diseases coding schedule, and corresponding coded data is added to drug data.The matching rate of drug data with corresponding disease category can be effectively improved using this method.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of drug data processing side based on machine learning
Method, device, computer equipment and storage medium.
Background technique
With the rapid development of Internet technology, effectively drug data can be carried out effectively using Internet technology
Processing.The efficiency of management of drug can be effectively improved by carrying out Classification Management to drug data.Usual city in the market
Drug all carries the package insert checked and approved by national Bureau of Drugs Supervision, and the content disunity in most package insert, table
It states and has differences.In existing classifying drugs mode, only classified according to the scope of application of drug to drug, such as ATC
(Anatomical Therapeutic Chemical, anatomy acology and chemical classification system) classifying drugs.
However, the range of classification results is bigger in current classifying drugs mode, and can not accurately identify
The corresponding disease specific classification of drug, so as to cause lower to drug data and the matching rate of specific corresponding disease category.Cause
This, how to effectively improve drug data with the matching rate of corresponding disease category becomes the current technical issues that need to address.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, drug data and corresponding disease can be effectively improved by providing one kind
Drug data processing method, device, computer equipment and the storage medium of the matching rate of classification.
A kind of drug data processing method, comprising:
Multiple drug datas are obtained, the drug data includes specification, and the specification includes multiple fields and correspondence
Content of text；
Extract the corresponding content of text of preset field in the specification；
Classifier is obtained, the content of text is input in the classifier, the medicine is exported by the classifier
The corresponding disease category of product data, and the disease category is added in the drug data；
Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in the classification of diseases coding schedule；
The disease category of the drug data is matched with the classification of diseases coding schedule, and to the drug data
Add corresponding coded data.
It is described in one of the embodiments, that the corresponding disease category of the drug data is exported by the classifier,
It include: the multiple characters extracted according to the preset characters in the content of text in the content of text；It extracts described more
The corresponding text vector of a character, classifies to the text vector by the classifier, obtains the text vector category
In the probability value of each disease category；The probability value is reached into the corresponding disease category of preset threshold and is added to the drug number
In.
It is described in one of the embodiments, that the corresponding disease category of the drug data is exported by the classifier,
It include: that multiple opposite feature vocabulary in the content of text are extracted according to the default antisense character in the content of text；
It identifies the corresponding disease category of the multiple opposite feature vocabulary, the disease category is rejected；According to the text
Preset characters in content extract multiple characters in the content of text；The text vector of the multiple character is extracted,
Classified by the classifier to the text vector, obtains the probability that the text vector belongs to each disease category
Value；The probability value is reached the corresponding disease category of preset threshold to be added in the drug data.
Multiple drug datas are obtained from multiple databases in one of the embodiments, it is raw using multiple drug datas
At training set and verifying collection；Drug data in the training set is input in the disaggregated model pre-established and is trained,
Obtain preliminary classification device；The preliminary classification device is trained and is verified according to the drug data that the verifying is concentrated, is obtained
Classifier.
In one of the embodiments, the method also includes: to the drug data according to corresponding disease category into
Row sequence；The disease category of the drug data is matched with the classification of diseases coding schedule, obtains the drug data
Corresponding coded data；The drug data is encoded according to predetermined manner using the coded data, and to coding after
Drug data stored.
In one of the embodiments, the method also includes: obtain terminal send user information, the user information
Including the corresponding disease category of diagnostic result and symptom information；According in the disease type and symptom information and the drug storage
Drug data matched；The drug data for being up to preset matching degree pushes to the terminal.
A kind of drug data processing unit, comprising:
Module is obtained, for obtaining multiple drug datas, the drug data includes specification, and the specification includes more
A field and corresponding content of text；
Extraction module, for extracting the corresponding content of text of preset field in the specification；
The content of text is input in the classifier by categorization module for obtaining classifier, utilizes the classification
Device exports the corresponding disease category of the drug data, and the disease category is added in the drug data；
The acquisition module is also used to obtain classification of diseases coding schedule, includes disease category in the classification of diseases coding schedule
With corresponding coded data；
Matching module, for the disease category of the drug data to be matched with the classification of diseases coding schedule, and
Corresponding coded data is added to the drug data.
The user information for obtaining module and being also used to obtain terminal transmission in one of the embodiments, the user
Information includes the corresponding disease type of diagnostic result and symptom information；The matching module be also used to according to the disease type and
Symptom information is matched with the drug data in the drug storage；Described device further includes sending module, pre- for being up to
If the drug data of matching degree pushes to the terminal.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
Multiple drug datas are obtained, the drug data includes specification, and the specification includes multiple fields and correspondence
Content of text；
Extract the corresponding content of text of preset field in the specification；
Classifier is obtained, the content of text is input in the classifier, the medicine is exported by the classifier
The corresponding disease category of product data, and the disease category is added in the drug data；
Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in the classification of diseases coding schedule；
The disease category of the drug data is matched with the classification of diseases coding schedule, and to the drug data
Add corresponding coded data.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
Multiple drug datas are obtained, the drug data includes specification, and the specification includes multiple fields and correspondence
Content of text；
Extract the corresponding content of text of preset field in the specification；
Classifier is obtained, the content of text is input in the classifier, the medicine is exported by the classifier
The corresponding disease category of product data, and the disease category is added in the drug data；
Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in the classification of diseases coding schedule；
The disease category of the drug data is matched with the classification of diseases coding schedule, and to the drug data
Add corresponding coded data.
Above-mentioned drug data processing method, device, computer equipment and storage medium, server obtain multiple drug numbers
According to drug data includes specification, and specification includes multiple fields and corresponding content of text.Server extracts in specification
After the corresponding content of text of preset field, classifier is obtained, content of text is input in the classifier, by utilizing classification
Device exports the corresponding disease category of drug data, and the disease category is added in drug data.Server obtains disease in turn
Sick sorting code number table includes disease category and corresponding coded data in classification of diseases coding schedule.By by the disease of drug data
Sick classification is matched with classification of diseases coding schedule, and adds corresponding coded data to drug data.By utilizing classifier
After classifying to drug data, and corresponding disease category and coded data are matched, it is possible thereby to effectively by drug data
It is matched with corresponding disease category, and the matching rate of drug data and disease category can be effectively improved.
Detailed description of the invention
Fig. 1 is the application scenario diagram of drug data processing method in one embodiment；
Fig. 2 is the flow diagram of drug data processing method in one embodiment；
Fig. 3 is to be illustrated in one embodiment by the process that classifier exports the corresponding disease category step of drug data
Figure；
Fig. 4 is to be illustrated in another embodiment by the process that classifier exports the corresponding disease category step of drug data
Figure；
Fig. 5 is the structural block diagram of drug data processing equipment in one embodiment；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Drug data processing method provided by the present application, can be applied in application environment as shown in Figure 1.Wherein, eventually
End 102 is communicated with server 104 by network by network.Wherein, terminal 102 can be, but not limited to be various personal meters
Calculation machine, laptop, smart phone, tablet computer and portable wearable device, server 104 can use independent service
The server cluster of device either multiple servers composition is realized.The medicine that the available multiple terminals 102 of server 104 are sent
Product data, drug data include specification, and specification includes multiple fields and corresponding content of text.Server 104 is then into one
Step extracts the corresponding content of text of preset field in specification, obtains classifier, and the content of text extracted is input to
In classifier, disease category corresponding to the drug data is exported by classifier, and disease category is added to corresponding
In drug data.Server 104 further obtains classification of diseases coding schedule, includes disease category in classification of diseases coding schedule and right
The coded data answered, by matching the disease category of drug data with classification of diseases coding schedule, it is hereby achieved that should
Coded data corresponding to drug data, and the drug data adds corresponding coded data.By dividing drug data
It is matched after class, it is possible thereby to there is the small matching rate for improving drug data and corresponding disease category.
In one embodiment, as shown in Fig. 2, providing a kind of drug data processing method, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
Step 202, multiple drug datas are obtained, drug data includes corresponding specification, and specification includes multiple fields
With corresponding content of text.
Wherein, drug data can be the drug of each manufacturer's publication, and every kind of drug has corresponding drug data.Drug
Data include corresponding specification, include multiple fields and corresponding content of text in specification.For example, " nomenclature of drug ", " property
Multiple fields and the corresponding content of text such as shape ", " indication ", " specification ", " usage and dosage " and " adverse reaction ".Server
Multiple drug datas that available multiple terminals are sent, further, server can also obtain more from multiple databases
A drug data.
Step 204, the corresponding content of text of preset field in specification is extracted.
After server obtains multiple drug datas, extract in the corresponding text of preset field in the specification of drug data
Hold.For example, can to extract in the specification of drug data " indication ", " scope of application " or " major function " etc. pre- for server
If content of text corresponding to field.For example, including in " feeling logical piece " corresponding specification when drug data is " feeling logical piece "
" nomenclature of drug ", " composition ", " character ", " major function ", " specification ", " usage and dosage ", " adverse reaction ", " taboo " and " note
Meaning item ".Further, server extracts in specification " major function " corresponding content of text " clearing heat and detoxicating, dispelling wind solution
Table, for catching a cold, symptoms include fever, headache nasal obstruction, cough phlegm Huang, dry pharyngalgia, throat redness, Muscular stiffness ".
Step 206, classifier is obtained, content of text is input in classifier, drug data pair is exported by classifier
The disease category answered, and disease category is added in drug data.
After server extracts the corresponding content of text of preset field in specification, and then classifier is obtained, will extracted
Drug data specification in the corresponding content of text of preset field be input in classifier.By classifier to drug data
Classify, then utilizes the corresponding disease category of classifier output drug data.
Specifically, server can also extract multiple words in content of text according to the preset characters in content of text
Symbol, onestep extraction of going forward side by side go out the text vector of multiple characters.For example, server extracts above-mentioned " feeling logical piece " Ming Shuzhong " function
Cure mainly " after corresponding content of text, preset characters " being used for " subsequent character can be extracted according to preset characters " being used for ", and
Extract the corresponding multiple text vectors of multiple characters.Classified using classifier to drug data belonging to text vector,
The text vector for obtaining drug data belongs to the probability value of each disease category, and the probability value for being up to preset threshold is corresponding
Disease category is added in drug data.Wherein, disease category corresponding to drug data may include multiple.It is possible thereby to have
Effect ground exports the corresponding disease category of drug data by classifier.
Step 208, classification of diseases coding schedule is obtained, includes disease category and corresponding coded number in classification of diseases coding schedule
According to.
Step 210, the disease category of drug data is matched with classification of diseases coding schedule, and drug data is added
Corresponding coded data.
After server by utilizing classifier is classified to drug data and adds corresponding disease category, classification of diseases is obtained
Coding schedule.Wherein, classification of diseases coding schedule can be the tables of data for having pre-defined disease category and corresponding coding, including more
A disease category and corresponding coded data.For example, classification of diseases coding schedule can be ICD (International
Classification of Diseases, International Classification of Diseases) coding schedule.
Server then matches the disease category of drug data with the disease category in classification of diseases coding schedule, and right
The consistent drug data of disease category adds corresponding coded data.Wherein, disease category corresponding to drug data can wrap
Include multiple, therefore each drug data can have corresponding multiple coded datas.Coded data is the disease of common relatively specification
Coding corresponding to sick classification can effectively improve drug data to the corresponding coded data of drug data addition disease category
Treatment effeciency.After classifying by classifier to drug data, and corresponding disease category and coded data are matched, thus may be used
Effectively to match drug data with corresponding disease category, and drug data and disease class can be effectively improved
Other matching rate.
In above-mentioned drug data processing method, server obtains multiple drug datas, and drug data includes specification, explanation
School bag includes multiple fields and corresponding content of text.After server extracts the corresponding content of text of preset field in specification,
Classifier is obtained, content of text is input in the classifier, by exporting the corresponding disease of drug data using classifier
Classification, and the disease category is added in drug data.Server and then acquisition classification of diseases coding schedule, classification of diseases coding
It include disease category and corresponding coded data in table.By the way that the disease category of drug data and classification of diseases coding schedule are carried out
Matching, and corresponding coded data is added to drug data.After being classified using classifier to drug data, and match
Corresponding disease category and coded data, it is possible thereby to effectively match drug data with corresponding disease category, and
And the matching rate of drug data and disease category can be effectively improved.
In one embodiment, as shown in figure 3, the step of exporting drug data corresponding disease category by classifier,
Specifically include the following contents:
Step 302, multiple characters in content of text are extracted according to the preset characters in content of text.
Step 304, the corresponding text vector of multiple characters is extracted, is classified by classifier to text vector, is obtained
Belong to the probability value of each disease category to text vector.
Step 306, probability value is reached the corresponding disease category of preset threshold to be added in drug data.
Server obtains multiple drug datas first, and drug data includes specification, and specification includes multiple fields and right
The content of text answered.After server obtains multiple drug datas, it is corresponding to extract preset field in the specification of drug data
Content of text.For example, server can extract in the specification of drug data " indication ", " scope of application " or " function master
Control " etc. content of text corresponding to preset fields.For example, when drug data is " feeling logical piece ", " feeling logical piece " corresponding explanation
Include " nomenclature of drug " in book, " composition ", " character ", " major function ", " specification ", " usage and dosage ", " adverse reaction ", " prohibit
Avoid " and " points for attention ".Further, server extracts in specification " major function " corresponding content of text " heat-clearing solution
Poison, expelling wind to resolve the exterior, for catching a cold, symptoms include fever, headache nasal obstruction, cough phlegm Huang, dry pharyngalgia, throat redness, Muscular stiffness ".
After server extracts the corresponding content of text of preset field in specification, according to the preset characters in content of text
Multiple characters in content of text are extracted, the text vector of multiple characters is further extracted.For example, server extracts
After stating " feeling logical piece " corresponding content of text of Ming Shuzhong " major function ", predetermined word can be extracted according to preset characters " being used for "
" being used for " subsequent character is accorded with, and extracts the corresponding multiple text vectors of multiple characters.
Further, server then passes through classifier and classifies to drug data belonging to text vector, obtains drug
The text vector of data belongs to the probability value of each disease category, and the corresponding disease category of the probability value for being up to preset threshold
It is added in drug data.Wherein, disease category corresponding to drug data may include multiple.It is possible thereby to effectively pass through
Classifier exports the corresponding disease category of drug data.
In another embodiment, the step of as shown in figure 4, using classifier output drug corresponding disease category, tool
Body includes the following contents:
Step 402, according to the default antisense character in content of text, multiple opposite feature words in content of text are extracted
It converges.
Step 404, it identifies the corresponding disease category of multiple opposite feature vocabulary, disease category is rejected.
Step 406, multiple characters in content of text are extracted according to the preset characters in content of text.
Step 408, the text vector for extracting multiple characters classifies to text vector using classifier, obtains text
This vector belongs to the probability value of each disease category.
Step 410, probability value is reached the corresponding disease category of preset threshold to be added in drug data.
Drug data includes specification, and specification includes multiple fields and corresponding content of text.Server obtains multiple
After drug data, according to the default antisense character in content of text, multiple opposite feature vocabulary in content of text are extracted.Example
Such as, " feeling and lead to piece " in corresponding specification includes " nomenclature of drug ", " composition ", " character ", " major function ", " specification ", " usage
Dosage ", " adverse reaction ", " taboo " and " points for attention ".It include that " anemofrigid cold person is not applicable, table in its " points for attention "
It is now aversion to cold weight, generate heat light, lossless, headache, nasal obstruction, watery nasal discharge, throat itching and cough ".
Server identifies the default antisense character in specification in the content of text of preset field, such as " not applicable ",
The default antisense character such as " not being suitable for ", " disabling ".Server further extracts in content of text according to default antisense character
Multiple opposite feature vocabulary, i.e., text or vocabulary corresponding to default antisense character.Server identifies multiple opposite features
The corresponding disease category of vocabulary, rejects disease category.For example, in the drug data of above-mentioned " feeling logical piece ", server root
" anemofrigid cold " is extracted according to default antisense character " not applicable " and " it shows as, and aversion to cold is heavy, it is light, lossless to generate heat, headache, nose
These opposite feature vocabulary of plug, watery nasal discharge, throat itching and cough ".Server is by identifying corresponding to these opposite feature vocabulary
Disease category, i.e. " anemofrigid cold ", and this disease category is rejected to " anemofrigid cold ".
Further, server is according to the corresponding disease of the corresponding opposite feature vocabulary of default antisense character in content of text
Sick classification, after rejecting to disease category, server extracts the corresponding text of preset field in the specification of drug data
Content.For example, server can extract " indication ", " scope of application ", " function in the specification of " feeling logical piece " drug data
Cure mainly " or the preset fields such as " points for attention " corresponding to content of text.Onestep extraction of going forward side by side goes out in specification " major function "
" clearing heat and detoxicating, expelling wind to resolve the exterior, for catching a cold, symptoms include fever, headache nasal obstruction, cough phlegm are yellow, dry pharynx for corresponding content of text
Bitterly, throat redness, Muscular stiffness ".
After server extracts the corresponding content of text of preset field in specification, according to the preset characters in content of text
Multiple characters in content of text are extracted, onestep extraction of going forward side by side goes out the text vector of multiple characters.For example, server extracts
After above-mentioned " feeling logical piece " the corresponding content of text of Ming Shuzhong " major function ", it can be extracted according to preset characters " being used for " default
Character " being used for " subsequent character, and extract the corresponding multiple text vectors of multiple characters.
Further, server then passes through classifier and classifies to drug data belonging to text vector, obtains drug
The text vector of data belongs to the probability value of each disease category, and the corresponding disease category of the probability value for being up to preset threshold
It is added in drug data.Wherein, disease category corresponding to drug data may include multiple.Due to server basis
The corresponding disease category of the corresponding opposite feature vocabulary of default antisense character in content of text, rejects disease category,
The efficiency and accuracy of classification can be effectively improved when therefore classifying by classifier to drug data.
In one embodiment, before acquisition classifier, further includes: multiple drug datas are obtained from multiple databases,
Training set and verifying collection are generated using multiple drug datas；Drug data in training set is input to the classification mould pre-established
It is trained in type, obtains preliminary classification device；Preliminary classification device is trained and is verified according to the drug data that verifying is concentrated,
Obtain classifier.
Server is before obtaining classifier, and specifically, server can be from internet site or from local data base
It is middle to obtain a large amount of drug datas, training set is generated using multiple drug datas of acquisition and verifying collects.Server will be by that will train
The drug data of concentration is input in the disaggregated model neural network based pre-established and is trained, it is hereby achieved that just
Walk classifier.
After initial training obtains preliminary classification device, the drug data that verifying is concentrated then is input to tentatively by server again
It is trained and verifies in classifier, and then obtain trained classifier.By passing through network mind using a large amount of drug datas
It is trained through model, it is possible thereby to effectively train the higher classifier of accuracy rate.By utilizing neural network model
Classifier classifies to drug data, and then can effectively improve the accuracy rate of drug data classification.
In one embodiment, this method further include: drug data is ranked up according to corresponding disease category；By medicine
The disease category of product data is matched with classification of diseases coding schedule, obtains the corresponding coded data of drug data；Utilize coding
Data encode drug data according to predetermined manner, and store to the drug data after coding.
After server obtains multiple drug datas, extract in drug data specification in the corresponding text of preset field
Hold, obtain classifier, content of text is input in the classifier, by exporting the corresponding disease of drug data using classifier
Sick classification, and the disease category is added in drug data.
After server obtains the corresponding disease category of drug data by classifier, to drug data according to corresponding disease
Classification is ranked up.Wherein, disease category may include major class and group.Specifically, can according to the major class of disease category and
Hierarchical relationship between group is ranked up drug data.After server is ranked up drug data, classification of diseases is obtained
Coding schedule.Wherein, classification of diseases coding schedule can be the tables of data for having pre-defined disease category and corresponding coding, including more
A disease category and corresponding coded data.For example, classification of diseases coding schedule can be ICD (International
Classification of Diseases, International Classification of Diseases) coding schedule.
Server then matches the disease category of drug data with the disease category in classification of diseases coding schedule, obtains
The corresponding coded data of drug data, and corresponding coded data is added to the consistent drug data of disease category.Wherein, drug
Disease category corresponding to data may include multiple, therefore each drug data can have corresponding multiple coded datas.Clothes
Business device then further encodes drug data according to predetermined manner using coded data.For example, can be according to preset word
Symbol sequence encodes drug data, and preset character can be character and digit, such as ME10001, ME100012 etc..Clothes
Business device stores the drug data after coding.After matching corresponding disease category to drug data, to drug number
According to code storage is carried out, it is possible thereby to the effectively improving drug data efficiency of management and treatment effeciency.
In one embodiment, this method further include: obtain the user information that terminal is sent, user information includes diagnosis knot
The corresponding disease category of fruit and symptom information；According to the drug data progress in disease type and symptom information and drug storage
Match；The drug data for being up to preset matching degree pushes to terminal.
It, can also be according to the disease corresponding to drug data after server matches corresponding disease category to drug data
Classification recommends corresponding drug to user.Specifically, server obtains the user information that terminal is sent.Wherein, in user information
Include that user carries out the diagnostic result after diagnosis and treatment, include corresponding disease type and corresponding coded data in diagnostic result with
And symptom information.
The server then drug data progress according to the disease type and symptom information in user information and in drug storage
Match, extract the drug data for reaching preset matching degree, and the drug data for reaching preset matching degree pushes to terminal.Wherein,
Server directly can push drug data information to terminal, and the corresponding purchase link of drug data can also be pushed to terminal.
After matching corresponding disease category to drug data, the drug being consistent is pushed to corresponding terminal according to user information
Data bring convenience thus, it is possible to effectively push corresponding drug data to user for user.
It should be understood that although each step in the flow chart of Fig. 2-4 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-4
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 5, providing a kind of drug data processing unit, comprising: acquisition module 502,
Extraction module 504, categorization module 506 and matching module 508, in which:
Module 502 is obtained, for obtaining multiple drug datas, drug data includes specification, and specification includes multiple words
Section and corresponding content of text；
Extraction module 504, for extracting the corresponding content of text of preset field in specification；
Content of text is input in classifier by categorization module 506 for obtaining classifier, exports medicine using classifier
The corresponding disease category of product data, and disease category is added in drug data；
It obtains module 502 and is also used to obtain classification of diseases coding schedule, include disease category in classification of diseases coding schedule and right
The coded data answered；
Matching module 508, for matching the disease category of drug data with classification of diseases coding schedule, and to drug
Data add corresponding coded data.
In one embodiment, categorization module 506 is also used to be extracted in text according to the preset characters in content of text
Multiple characters in appearance；The corresponding text vector of multiple characters is extracted, is classified by classifier to text vector, is obtained
Text vector belongs to the probability value of each disease category；Probability value is reached into the corresponding disease category of preset threshold and is added to drug
In data.
In one embodiment, categorization module 506 is also used to extract text according to the default antisense character in content of text
Multiple opposite feature vocabulary in this content；Identify the corresponding disease category of multiple opposite feature vocabulary, to disease category into
Row is rejected；Multiple characters in content of text are extracted according to the preset characters in content of text；Extract the text of multiple characters
This vector classifies to text vector using classifier, obtains the probability value that text vector belongs to each disease category；It will be general
Rate value reaches the corresponding disease category of preset threshold and is added in drug data.
In one embodiment, which further includes model construction module, for obtaining multiple medicines from multiple databases
Product data generate training set using multiple drug datas and verifying collect；Drug data in training set is input to and is pre-established
Disaggregated model in be trained, obtain preliminary classification device；Preliminary classification device is instructed according to the drug data that verifying is concentrated
Practice and verify, obtains classifier.
In one embodiment, which further includes coding module, is used for drug data according to corresponding disease category
It is ranked up；The disease category of drug data is matched with classification of diseases coding schedule, obtains the corresponding coding of drug data
Data；Drug data is encoded according to predetermined manner using coded data, and the drug data after coding is stored.
In one embodiment, which further includes pushing module, for obtaining the user information of terminal transmission, Yong Huxin
Breath includes the corresponding disease category of diagnostic result and symptom information；According to the drug in disease type and symptom information and drug storage
Data are matched；The drug data for being up to preset matching degree pushes to terminal.
Specific about drug data processing unit limits the limit that may refer to above for drug data processing method
Fixed, details are not described herein.Modules in above-mentioned drug data processing unit can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing drug data etc..The network interface of the computer equipment is used to pass through net with external terminal
Network connection communication.To realize a kind of drug data processing method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
Multiple drug datas are obtained, drug data includes specification, and specification includes in multiple fields and corresponding text
Hold；
Extract the corresponding content of text of preset field in specification；
Classifier is obtained, content of text is input in classifier, the corresponding disease of drug data is exported by classifier
Classification, and disease category is added in drug data；
Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in classification of diseases coding schedule；
The disease category of drug data is matched with classification of diseases coding schedule, and corresponding volume is added to drug data
Code data.
In one embodiment, it also performs the steps of when processor executes computer program according in content of text
Preset characters extract multiple characters in content of text；The corresponding text vector of multiple characters is extracted, classifier pair is passed through
Text vector is classified, and the probability value that text vector belongs to each disease category is obtained；Probability value is reached into preset threshold pair
The disease category answered is added in drug data.
In one embodiment, it also performs the steps of when processor executes computer program according in content of text
Default antisense character, extracts multiple opposite feature vocabulary in content of text；Identify that multiple opposite feature vocabulary are corresponding
Disease category rejects disease category；Multiple words in content of text are extracted according to the preset characters in content of text
Symbol；The text vector for extracting multiple characters classifies to text vector using classifier, obtain text vector belong to it is each
The probability value of disease category；Probability value is reached the corresponding disease category of preset threshold to be added in drug data.
In one embodiment, it also performs the steps of when processor executes computer program and is obtained from multiple databases
Multiple drug datas are taken, training set is generated using multiple drug datas and verifying collects；Drug data in training set is input to
It is trained in the disaggregated model pre-established, obtains preliminary classification device；The drug data concentrated according to verifying is to preliminary classification
Device is trained and verifies, and obtains classifier.
In one embodiment, it is also performed the steps of to drug data according to right when processor executes computer program
The disease category answered is ranked up；The disease category of drug data is matched with classification of diseases coding schedule, obtains drug number
According to corresponding coded data；Drug data is encoded according to predetermined manner using coded data, and to the drug after coding
Data are stored.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains the use that terminal is sent
Family information, user information include the corresponding disease category of diagnostic result and symptom information；According to disease type and symptom information with
Drug data in drug storage is matched；The drug data for being up to preset matching degree pushes to terminal.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Multiple drug datas are obtained, drug data includes specification, and specification includes in multiple fields and corresponding text
Hold；
Extract the corresponding content of text of preset field in specification；
Classifier is obtained, content of text is input in classifier, the corresponding disease of drug data is exported by classifier
Classification, and disease category is added in drug data；
Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in classification of diseases coding schedule；
The disease category of drug data is matched with classification of diseases coding schedule, and corresponding volume is added to drug data
Code data.
In one embodiment, it also performs the steps of when computer program is executed by processor according in content of text
Preset characters extract multiple characters in content of text；The corresponding text vector of multiple characters is extracted, classifier is passed through
Classify to text vector, obtains the probability value that text vector belongs to each disease category；Probability value is reached into preset threshold
Corresponding disease category is added in drug data.
In one embodiment, it also performs the steps of when computer program is executed by processor according in content of text
Default antisense character, extract multiple opposite feature vocabulary in content of text；Identify that multiple opposite feature vocabulary are corresponding
Disease category, disease category is rejected；It is extracted according to the preset characters in content of text multiple in content of text
Character；The text vector for extracting multiple characters classifies to text vector using classifier, obtains text vector and belongs to often
The probability value of a disease category；Probability value is reached the corresponding disease category of preset threshold to be added in drug data.
In one embodiment, it is also performed the steps of from multiple databases when computer program is executed by processor
Multiple drug datas are obtained, training set is generated using multiple drug datas and verifying collects；By the drug data input in training set
It is trained into the disaggregated model pre-established, obtains preliminary classification device；The drug data concentrated according to verifying is to preliminary point
Class device is trained and verifies, and obtains classifier.
In one embodiment, also performed the steps of when computer program is executed by processor to drug data according to
Corresponding disease category is ranked up；The disease category of drug data is matched with classification of diseases coding schedule, obtains drug
The corresponding coded data of data；Drug data is encoded according to predetermined manner using coded data, and to the medicine after coding
Product data are stored.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains what terminal was sent
User information, user information include the corresponding disease category of diagnostic result and symptom information；According to disease type and symptom information
It is matched with the drug data in drug storage；The drug data for being up to preset matching degree pushes to terminal.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of drug data processing method, comprising:
Multiple drug datas are obtained, the drug data includes specification, and the specification includes multiple fields and corresponding text
This content；
Extract the corresponding content of text of preset field in the specification；
Classifier is obtained, the content of text is input in the classifier, the drug number is exported by the classifier
It is added in the drug data according to corresponding disease category, and by the disease category；
Classification of diseases coding schedule is obtained, includes disease category and corresponding coded data in the classification of diseases coding schedule；
The disease category of the drug data is matched with the classification of diseases coding schedule, and the drug data is added
Corresponding coded data.
2. the method according to claim 1, wherein described export the drug data pair by the classifier
The disease category answered, comprising:
Multiple characters in the content of text are extracted according to the preset characters in the content of text；
The corresponding text vector of the multiple character is extracted, is classified by the classifier to the text vector, is obtained
Belong to the probability value of each disease category to the text vector；
The probability value is reached the corresponding disease category of preset threshold to be added in the drug data.
3. the method according to claim 1, wherein described export the drug data pair by the classifier
The disease category answered, comprising:
According to the default antisense character in the content of text, multiple opposite feature vocabulary in the content of text are extracted；
It identifies the corresponding disease category of the multiple opposite feature vocabulary, the disease category is rejected；
Multiple characters in the content of text are extracted according to the preset characters in the content of text；
The text vector for extracting the multiple character classifies to the text vector by the classifier, obtains institute
State the probability value that text vector belongs to each disease category；
The probability value is reached the corresponding disease category of preset threshold to be added in the drug data.
4. the method according to claim 1, wherein before the acquisition classifier, further includes:
Multiple drug datas are obtained from multiple databases, generate training set using multiple drug datas and verifying collects；
Drug data in the training set is input in the disaggregated model pre-established and is trained, preliminary classification is obtained
Device；
The preliminary classification device is trained and is verified according to the drug data that the verifying is concentrated, obtains classifier.
5. the method according to claim 1, wherein the method also includes:
The drug data is ranked up according to corresponding disease category；
The disease category of the drug data is matched with the classification of diseases coding schedule, it is corresponding to obtain the drug data
Coded data；
The drug data is encoded according to predetermined manner using the coded data, and to the drug data after coding into
Row storage.
6. method according to any one of claims 1 to 5, which is characterized in that the method also includes:
The user information that terminal is sent is obtained, the user information includes the corresponding disease category of diagnostic result and symptom information；
It is matched according to the disease type and symptom information with the drug data in the drug storage；
The drug data for being up to preset matching degree pushes to the terminal.
7. a kind of drug data processing unit, comprising:
Module is obtained, for obtaining multiple drug datas, the drug data includes specification, and the specification includes multiple words
Section and corresponding content of text；
Extraction module, for extracting the corresponding content of text of preset field in the specification；
The content of text is input in the classifier by categorization module for obtaining classifier, defeated using the classifier
The corresponding disease category of the drug data out, and the disease category is added in the drug data；
The acquisition module is also used to obtain classification of diseases coding schedule, includes disease category in the classification of diseases coding schedule and right
The coded data answered；
Matching module, for matching the disease category of the drug data with the classification of diseases coding schedule, and to institute
It states drug data and adds corresponding coded data.
8. device according to claim 7, which is characterized in that the user for obtaining module and being also used to obtain terminal transmission
Information, the user information include the corresponding disease type of diagnostic result and symptom information；The matching module is also used to basis
The disease type and symptom information are matched with the drug data in the drug storage；Described device further includes sending mould
Block, the drug data for being up to preset matching degree push to the terminal.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811020524.1A CN109408631B (en) | 2018-09-03 | 2018-09-03 | Medicine data processing method, device, computer equipment and storage medium |
| PCT/CN2019/098553 WO2020048264A1 (en) | 2018-09-03 | 2019-07-31 | Method and apparatus for processing drug data, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811020524.1A CN109408631B (en) | 2018-09-03 | 2018-09-03 | Medicine data processing method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109408631A true CN109408631A (en) | 2019-03-01 |
| CN109408631B CN109408631B (en) | 2023-06-20 |
Family
ID=65463896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811020524.1A Active CN109408631B (en) | 2018-09-03 | 2018-09-03 | Medicine data processing method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109408631B (en) |
| WO (1) | WO2020048264A1 (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993227A (en) * | 2019-03-29 | 2019-07-09 | 京东方科技集团股份有限公司 | Method, system, device and the medium of automatic addition International Classification of Diseases coding |
| CN110767320A (en) * | 2019-10-31 | 2020-02-07 | 北京东软望海科技有限公司 | Data processing method and device, electronic equipment and readable storage medium |
| CN110781858A (en) * | 2019-11-05 | 2020-02-11 | 泰康保险集团股份有限公司 | Information processing method and device, electronic equipment and computer readable storage medium |
| CN110781298A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Medicine classification method and device, computer equipment and storage medium |
| CN110827947A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | ICD (interface control document) code determining method and device, electronic device and readable storage medium |
| CN110827948A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | Medication data processing method and device, electronic equipment and readable storage medium |
| CN110827949A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | Method and device for determining disease code, electronic equipment and readable storage medium |
| WO2020048264A1 (en) * | 2018-09-03 | 2020-03-12 | 平安医疗健康管理股份有限公司 | Method and apparatus for processing drug data, computer device, and storage medium |
| CN110941717A (en) * | 2019-11-22 | 2020-03-31 | 深圳马可孛罗科技有限公司 | Passenger ticket rule analysis method and device, electronic equipment and computer readable medium |
| CN111933242A (en) * | 2020-08-12 | 2020-11-13 | 陈灿 | Medicine usage coding information processing method, system, storage medium and terminal |
| CN111933244A (en) * | 2020-08-17 | 2020-11-13 | 医渡云（北京）技术有限公司 | Medicine data encoding method and device, computer readable medium and electronic equipment |
| CN112036478A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Identification method and device for chronic disease reimbursement medicine and computer equipment |
| CN112053760A (en) * | 2020-08-12 | 2020-12-08 | 北京左医健康技术有限公司 | Medication guide method, medication guide device, and computer-readable storage medium |
| CN113821649A (en) * | 2021-01-15 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Method, device, electronic equipment and computer medium for determining medicine code |
| CN114329140A (en) * | 2021-12-28 | 2022-04-12 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
| CN116955497A (en) * | 2023-04-07 | 2023-10-27 | 广州标点医药信息股份有限公司 | Classification method for Chinese patent medicine data |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111785385A (en) * | 2020-06-29 | 2020-10-16 | 微医云(杭州)控股有限公司 | Disease classification method, device, equipment and storage medium |
| CN112035664B (en) * | 2020-08-28 | 2024-06-18 | 深圳平安医疗健康科技服务有限公司 | Medicine classifying method and device and computer equipment |
| CN112016309B (en) * | 2020-09-04 | 2024-03-08 | 平安科技（深圳）有限公司 | Extraction drug combination method, device, apparatus and storage medium |
| CN112818085B (en) * | 2021-01-28 | 2024-06-18 | 东软集团股份有限公司 | Value range data matching method and device, storage medium and electronic equipment |
| US20220285035A1 (en) * | 2021-03-08 | 2022-09-08 | Electronics And Telecommunications Research Institute | Device and method of predicting disease by using elderly cohort data |
| CN113436746B (en) * | 2021-06-30 | 2024-04-12 | 平安科技（深圳）有限公司 | Medication recommendation method, device, equipment and storage medium based on sorting algorithm |
| CN116306573B (en) * | 2023-03-15 | 2024-07-09 | 广联达科技股份有限公司 | Intelligent analysis method, device and equipment for engineering practice and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615753A (en) * | 2015-02-13 | 2015-05-13 | 杜雨阳 | Method and system of acquiring application relations between drugs and diseases |
| CN106709520A (en) * | 2016-12-23 | 2017-05-24 | 浙江大学 | Topic model based medical record classification method |
| CN107833637A (en) * | 2017-06-19 | 2018-03-23 | 平安医疗健康管理股份有限公司 | Medicine regular record update method, device, computer equipment and medium |
| CN108182177A (en) * | 2018-01-24 | 2018-06-19 | 谢德刚 | A kind of mathematics knowledge-ID automation mask method and device |
| WO2021068321A1 (en) * | 2019-10-12 | 2021-04-15 | 平安科技（深圳）有限公司 | Information pushing method and apparatus based on human-computer interaction, and computer device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108257667A (en) * | 2016-12-28 | 2018-07-06 | 中国科学院深圳先进技术研究院 | A kind of data processing method and terminal device |
| CN107330288A (en) * | 2017-07-10 | 2017-11-07 | 叮当（深圳）健康机器人科技有限公司 | A kind of medication information acquisition method and device |
| CN108062556B (en) * | 2017-11-10 | 2021-09-14 | 广东药科大学 | Drug-disease relationship identification method, system and device |
| CN109408631B (en) * | 2018-09-03 | 2023-06-20 | 深圳平安医疗健康科技服务有限公司 | Medicine data processing method, device, computer equipment and storage medium |
-
2018
- 2018-09-03 CN CN201811020524.1A patent/CN109408631B/en active Active
-
2019
- 2019-07-31 WO PCT/CN2019/098553 patent/WO2020048264A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104615753A (en) * | 2015-02-13 | 2015-05-13 | 杜雨阳 | Method and system of acquiring application relations between drugs and diseases |
| CN106709520A (en) * | 2016-12-23 | 2017-05-24 | 浙江大学 | Topic model based medical record classification method |
| CN107833637A (en) * | 2017-06-19 | 2018-03-23 | 平安医疗健康管理股份有限公司 | Medicine regular record update method, device, computer equipment and medium |
| CN108182177A (en) * | 2018-01-24 | 2018-06-19 | 谢德刚 | A kind of mathematics knowledge-ID automation mask method and device |
| WO2021068321A1 (en) * | 2019-10-12 | 2021-04-15 | 平安科技（深圳）有限公司 | Information pushing method and apparatus based on human-computer interaction, and computer device |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020048264A1 (en) * | 2018-09-03 | 2020-03-12 | 平安医疗健康管理股份有限公司 | Method and apparatus for processing drug data, computer device, and storage medium |
| CN109993227A (en) * | 2019-03-29 | 2019-07-09 | 京东方科技集团股份有限公司 | Method, system, device and the medium of automatic addition International Classification of Diseases coding |
| CN110781298B (en) * | 2019-09-18 | 2023-06-20 | 平安科技（深圳）有限公司 | Medicine classification method, apparatus, computer device and storage medium |
| CN110781298A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Medicine classification method and device, computer equipment and storage medium |
| WO2020220635A1 (en) * | 2019-09-18 | 2020-11-05 | 平安科技（深圳）有限公司 | Pharmaceutical drug classification method and apparatus, computer device and storage medium |
| CN110827947A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | ICD (interface control document) code determining method and device, electronic device and readable storage medium |
| CN110827949A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | Method and device for determining disease code, electronic equipment and readable storage medium |
| CN110827948A (en) * | 2019-10-31 | 2020-02-21 | 北京东软望海科技有限公司 | Medication data processing method and device, electronic equipment and readable storage medium |
| CN110827948B (en) * | 2019-10-31 | 2022-12-23 | 望海康信(北京)科技股份公司 | Medication data processing method and device, electronic equipment and readable storage medium |
| CN110767320A (en) * | 2019-10-31 | 2020-02-07 | 北京东软望海科技有限公司 | Data processing method and device, electronic equipment and readable storage medium |
| CN110781858A (en) * | 2019-11-05 | 2020-02-11 | 泰康保险集团股份有限公司 | Information processing method and device, electronic equipment and computer readable storage medium |
| CN110941717A (en) * | 2019-11-22 | 2020-03-31 | 深圳马可孛罗科技有限公司 | Passenger ticket rule analysis method and device, electronic equipment and computer readable medium |
| CN110941717B (en) * | 2019-11-22 | 2023-08-11 | 深圳马可孛罗科技有限公司 | Passenger ticket rule analysis method and device, electronic equipment and computer readable medium |
| CN111933242A (en) * | 2020-08-12 | 2020-11-13 | 陈灿 | Medicine usage coding information processing method, system, storage medium and terminal |
| CN112053760A (en) * | 2020-08-12 | 2020-12-08 | 北京左医健康技术有限公司 | Medication guide method, medication guide device, and computer-readable storage medium |
| CN112053760B (en) * | 2020-08-12 | 2021-07-27 | 北京左医健康技术有限公司 | Medication guide method, medication guide device, and computer-readable storage medium |
| CN111933244A (en) * | 2020-08-17 | 2020-11-13 | 医渡云（北京）技术有限公司 | Medicine data encoding method and device, computer readable medium and electronic equipment |
| CN112036478A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Identification method and device for chronic disease reimbursement medicine and computer equipment |
| CN113821649B (en) * | 2021-01-15 | 2022-11-08 | 北京沃东天骏信息技术有限公司 | Method, device, electronic equipment and computer medium for determining medicine code |
| WO2022151896A1 (en) * | 2021-01-15 | 2022-07-21 | 北京沃东天骏信息技术有限公司 | Method and apparatus for determining drug code, electronic device, and computer medium |
| CN113821649A (en) * | 2021-01-15 | 2021-12-21 | 北京沃东天骏信息技术有限公司 | Method, device, electronic equipment and computer medium for determining medicine code |
| CN114329140A (en) * | 2021-12-28 | 2022-04-12 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
| CN116955497A (en) * | 2023-04-07 | 2023-10-27 | 广州标点医药信息股份有限公司 | Classification method for Chinese patent medicine data |
| CN116955497B (en) * | 2023-04-07 | 2024-07-23 | 广州标点医药信息股份有限公司 | Classification method for Chinese patent medicine data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109408631B (en) | 2023-06-20 |
| WO2020048264A1 (en) | 2020-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109408631A (en) | Drug data processing method, device, computer equipment and storage medium | |
| Xu et al. | Multi-interactive memory network for aspect based multimodal sentiment analysis | |
| CN108986908B (en) | Method and device for processing inquiry data, computer equipment and storage medium | |
| Collell et al. | Imagined visual representations as multimodal embeddings | |
| Geman et al. | Visual turing test for computer vision systems | |
| CN109446302A (en) | Question and answer data processing method, device and computer equipment based on machine learning | |
| CN111159407B (en) | Method, apparatus, device and medium for training entity recognition and relation classification model | |
| CN109215754A (en) | Medical record data processing method, device, computer equipment and storage medium | |
| CN113127632B (en) | Text summarization method and device based on heterogeneous graph, storage medium and terminal | |
| CN109871446A (en) | Rejection method for identifying, electronic device and storage medium in intention assessment | |
| Wang et al. | LS-CNN: Characterizing local patches at multiple scales for face recognition | |
| CN110390021A (en) | Drug knowledge mapping construction method, device, computer equipment and storage medium | |
| Tang et al. | Learning multi-instance deep discriminative patterns for image classification | |
| Chen et al. | Recursive context routing for object detection | |
| CN112036154A (en) | Electronic medical record generation method and device based on inquiry dialogue and computer equipment | |
| CN107943792B (en) | Statement analysis method and device, terminal device and storage medium | |
| CN112580328A (en) | Event information extraction method and device, storage medium and electronic equipment | |
| CN108664595A (en) | Domain knowledge base construction method, device, computer equipment and storage medium | |
| CN112015900A (en) | Medical attribute knowledge graph construction method, device, equipment and medium | |
| CN108108354A (en) | A kind of microblog users gender prediction's method based on deep learning | |
| TWI752486B (en) | Training method, feature extraction method, device and electronic device | |
| CN111651606B (en) | Text processing method and device and electronic equipment | |
| CN107025212A (en) | Coding method, code device, coding/decoding method and decoding apparatus | |
| US20220318506A1 (en) | Method and apparatus for event extraction and extraction model training, device and medium | |
| CN116682536A (en) | Traditional Chinese medicine prescription recommendation method based on improved Bert4Rec |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220519 Address after: 518048 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Area H, 666 Beijing East Road, Huangpu District, Shanghai 200001 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |