CN111914095B - Medicine interaction relation extraction method and system - Google Patents

Medicine interaction relation extraction method and system Download PDF

Info

Publication number
CN111914095B
CN111914095B CN202010569861.7A CN202010569861A CN111914095B CN 111914095 B CN111914095 B CN 111914095B CN 202010569861 A CN202010569861 A CN 202010569861A CN 111914095 B CN111914095 B CN 111914095B
Authority
CN
China
Prior art keywords
medicine
drug
machine learning
text information
learning model
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.)
Active
Application number
CN202010569861.7A
Other languages
Chinese (zh)
Other versions
CN111914095A (en
Inventor
黎云
袁冲
余军
沈章
吕静
高峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Haiyun Health Technology Co ltd
Original Assignee
Wuhan Haiyun Health Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Haiyun Health Technology Co ltd filed Critical Wuhan Haiyun Health Technology Co ltd
Priority to CN202010569861.7A priority Critical patent/CN111914095B/en
Publication of CN111914095A publication Critical patent/CN111914095A/en
Application granted granted Critical
Publication of CN111914095B publication Critical patent/CN111914095B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367Ontology
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/10Text processing
    • G06F40/103Formatting, i.e. changing of presentation of documents
    • G06F40/117Tagging; Marking up; Designating a block; Setting of attributes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medicinal Chemistry (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention provides a medicine interaction relation extraction method and a system, wherein the method comprises the following steps: inputting a medicine instruction book into a trained machine learning model, and identifying a medicine entity relationship, wherein the machine learning model is established by extracting characteristic text information in the medicine instruction book in a semi-supervised learning training mode; the drug entity relationship is referenced by the pharmacist and the user. According to the extraction method and the extraction system for the medicine interaction relationship, provided by the embodiment of the invention, a semi-supervised learning mode is adopted, a machine learning model is trained, and the medicine entity names appearing in the medicine specification can be comprehensively judged, so that the result is more accurate.

Description

Medicine interaction relation extraction method and system
Technical Field
The invention relates to the technical field of information processing, in particular to a medicine interaction relation extraction method and system.
Background
People pay more and more attention to self health, the operation load of each big pharmacy is increased in an intangible way, and the requirements of pharmacists on self professional knowledge are higher and higher. In general, a pharmacist can prescribe a proper prescription to a patient by self-expertise, but due to limitations of time and energy, the pharmacist cannot fully understand each specific drug commodity, and thus the corresponding drug instruction becomes a first reference text of how the pharmacist can administer the drug. However, since there are many text spaces in the medicine instruction book, it may be difficult for the pharmacist to find out useful key information in a short time, and visual fatigue is easily caused when the pharmacist looks at the medicine instruction book in a high concentration for a long time, so that the manual burden of the pharmacist is increased, and medical accidents are easily caused.
At present, along with the increasing perfection of the health informatization construction of medical institutions in China, various kinds of information related to medicines can be checked in an electronic version, such as detailed descriptions related to various medicines on the national medicine administration, various published medicine websites and the like, which have very detailed related text information related to medicine administration. The method provides a basis for the development of big data work of medicines, can reasonably utilize information resources disclosed on the networks, and provides a certain basis for automation of medication references of pharmacists. However, the current general text information extraction and processing technology has great limitation and is not suitable for extracting text information in a medicine specification, and has the following defects: 1. the medical field is a very strict field with insufficient accuracy, and the requirement on the accuracy of the result is very high, and a more accurate model is needed to identify the relationship among complex drug entities, disease entities, food name entities and the like in the drug specification. 2. Identification extraction of all entities and their relationships (e.g., drug interactions, indications, contraindications, notes, etc.) that are numerous and miscellaneous in the drug specification is not a good solution. 3. The technology of identifying the pure named entities is adopted to identify various entity names (including a large number of mutually nested entity names) in the drug specification, and the lack of cooperation of professional pharmacist teams leads to insufficient accuracy of identification, does not meet the actual requirements, and can cause a plurality of problems. 4. The text information in the instruction book is not divided into fine grains enough, and the requirements of actual work of pharmacists are not met. 5. And the correctly identified data lacks a unified management form, so that subsequent data utilization cannot be performed, and the data is wasted.
Thus, a new drug interaction relationship extraction method is now needed to solve the above-mentioned problems.
Disclosure of Invention
The present invention provides a drug interaction relationship extraction method and system that overcomes or at least partially solves the above-mentioned problems, and according to a first aspect of the present invention, there is provided a drug interaction relationship extraction method comprising:
Inputting the drug instruction into a trained machine learning model, and identifying the drug entity relationship; the machine learning model is established by extracting characteristic text information in a medicine instruction book in a semi-supervised learning training mode;
the drug entity relationship is referenced by the pharmacist and the user.
Wherein the method further comprises:
Establishing the machine learning model;
The machine learning model is trained.
Wherein said building the machine learning model comprises:
acquiring medicine specification data, and constructing the medicine specification data, the medicine entity name and specific relation types among the medicine specification data and the medicine entity name into a category database;
and extracting text information in the drug instruction book based on the category database, and supplementing the missing syntax structure completely to establish the machine learning model.
Wherein said training said machine learning model comprises:
And labeling the text information extracted from the medicine instruction book by a semi-supervised learning mode.
Wherein the method further comprises:
and checking the output result of the trained machine learning model, correcting the wrong text information, and extracting all the text information with the wrong recognition so as to update the machine learning model.
Wherein the method further comprises:
and extracting the identified medicine entity relationship to form a triplet, and establishing a medicine instruction knowledge graph.
According to a second aspect of the present invention there is provided a drug interaction relationship extraction system comprising:
The recognition extraction module is used for inputting the drug instruction into a trained machine learning model, and recognizing the drug entity relationship, wherein the machine learning model is established by extracting characteristic text information in the drug instruction in a semi-supervised learning training mode;
And the comprehensive judging module is used for referencing the medicine entity relationship to pharmacists and users.
According to a third aspect of the present invention, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the drug interaction relationship extraction method as provided in the first aspect, when the program is executed by the processor.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the drug interaction relationship extraction method as provided in the first aspect above.
According to the extraction method and the extraction system for the medicine interaction relationship, provided by the embodiment of the invention, a semi-supervised learning mode is adopted, a machine learning model is trained, and the medicine entity names appearing in the medicine specification can be comprehensively judged, so that the result is more accurate.
Drawings
FIG. 1 is a schematic flow chart of a method for extracting drug interaction relationship according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an overall flow of drug interaction relationship extraction provided by an embodiment of the present invention;
FIG. 3 is a schematic diagram of a drug interaction relationship extraction system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
Fig. 1 is a schematic flow chart of a method for extracting interaction relationship of a drug according to an embodiment of the present invention, as shown in fig. 1, including:
101. Inputting the drug instruction into a trained machine learning model, and identifying the drug entity relationship; the machine learning model is established by extracting characteristic text information in a medicine instruction book in a semi-supervised learning training mode;
102. the drug entity relationship is referenced by the pharmacist and the user.
It should be noted that, the automatic medication reference is provided for the pharmacist, that is, the text information in the important items of "interaction", "contraindication" and "notice" and the like in each medicine instruction are extracted by the program script, and the information which the pharmacist needs to use can be automatically provided. For example, if a pharmacist needs to use the data of drug interactions, the established algorithm model can be used to divide the text information of drug interactions into two categories: "interaction mechanism and results", "treatment opinion". If the pharmacist needs a specific method of "treating comments" of a certain medicine, the specific method of "treating comments" can be given through the related text information by the established algorithm model, and the "interaction mechanism and result" can also be the same. For example, if it is to know whether a certain drug has an effect on a certain disease, it is "improvement" or "aggravation", and a corresponding judgment can be given from text information in the specification through an established algorithm model.
The method can greatly reduce the time cost of manual extraction of key information in the text information of the medicine instruction book by the pharmacist, and the pharmacist only performs a check operation on the result of the algorithm judgment, and can also provide the text information in the corresponding original medicine instruction book for the pharmacist. And meanwhile, corresponding medication references can be provided for users buying medicines, so that the medicines are more safe. The doctor-patient relationship problem at the present stage can be greatly relieved.
In view of the above situation, the embodiment of the invention adopts a semi-supervised learning mode, and the combination of the labeling of pharmacist expert and machine learning ensures high accuracy.
Fig. 2 is a schematic diagram of an overall flow of drug interaction relation extraction provided by an embodiment of the present invention, and as shown in fig. 2, the overall flow provided by the embodiment of the present invention includes S1-S7.
In practice, an algorithm model is trained through a semi-supervised learning mode to identify the relation of medicine entities from a newly provided medicine instruction book, an identification result is given, and the identification result is provided for a pharmacist to perform medication reference in actual work, so that the pharmacist can save searching in text information of massive medicine instruction books; the identification result can also be provided for the user to refer to, so that the medication is more safe and has basis.
It can be understood that, for a great number of complicated drug names or disease names appearing in text information of the drug instruction, the method provided by the embodiment of the invention adopts a method that a professional pharmacist team provides and marks drug name entities as a main part, and a named entity identification technology identifies the drug name entities as an auxiliary part to comprehensively judge the names of the drug entities appearing in the drug instruction, so that the result is more accurate.
On the basis of the above embodiment, the method further includes:
Establishing the machine learning model;
The machine learning model is trained.
As shown in S1-S5 of FIG. 2, the embodiment of the invention specifically requires a model building and training process.
Comprising the following steps:
Step S1: firstly, complete medicine instruction book data are obtained from public data on a medicine website through the technology of a web crawler, and each instruction book is stored locally.
Step S2: the medicine entity names provided by pharmacists, specific relation types and supplements of named entity recognition technology are utilized to form a category database, which is the basis for extracting relevant text information in the medicine instruction book in the step S3.
Step S3: the text information of two drug entities which appear simultaneously in the text information of the drug instruction is extracted by using the established category database, and the text information which lacks related subjects is supplemented with the missing syntax structure completely by using the related technology of NLP, so that the text information of the instruction is richer and more comprehensive, and the reference of pharmacists and users is facilitated.
Step S4: and (5) labeling the text information extracted from the medicine instruction book to a professional pharmacist team in a semi-supervised learning mode. In the labeling process, pharmacists provide relevant rules, deeply analyze useful information features in texts and build a machine learning training model. The above models include one or more of CRF, bi GRU, BERT.
And S5, checking the output result of the algorithm model for a pharmacist, correcting the text information of the identification errors, extracting all the text information of the identification errors, analyzing the error reasons, adjusting the parameters of the algorithm, reestablishing the model, and finally enabling the comprehensive accuracy of the identification to be the highest.
Further, after the model building and training process is completed, referring to fig. 2, the overall flow of the drug interaction relationship extraction method provided by the embodiment of the present invention further includes:
Step S6: inputting the drug instruction into the trained machine learning model, and outputting the drug entity relationship.
Step S7: the output medicine entity relationship is provided for pharmacists and users to refer to on one hand, and on the other hand, data support is provided for establishing a medicine instruction knowledge graph.
On the basis of the above embodiment, the building the machine learning model includes:
acquiring medicine specification data, and constructing the medicine specification data, the medicine entity name and specific relation types among the medicine specification data and the medicine entity name into a category database;
and extracting text information in the drug instruction book based on the category database, and supplementing the missing syntax structure completely to establish the machine learning model.
On the basis of the above embodiment, the training the machine learning model includes:
And labeling the text information extracted from the medicine instruction book by a semi-supervised learning mode.
On the basis of the above embodiment, the method further includes:
and checking the output result of the trained machine learning model, correcting the wrong text information, and extracting all the text information with the wrong recognition so as to update the machine learning model.
As shown in step S5 in fig. 2, the embodiment of the present invention may further check the output result of the algorithm model for the pharmacist, correct the text information of the recognition error, extract all the text information of the recognition error, analyze the cause of the error, adjust the parameters of the algorithm, and reestablish the model, so as to finally maximize the comprehensive accuracy of the recognition.
On the basis of the above embodiment, the method further includes:
and extracting the identified medicine entity relationship to form a triplet, and establishing a medicine instruction knowledge graph.
As shown in step S7 in fig. 2, the embodiment of the present invention may further extract the drug entity pairs and their relationships to form triplets, so as to provide data support for building a knowledge graph of the drug specification.
It can be understood that the result of the identification by the method provided by the embodiment of the invention can naturally form a triplet form of entity pair + relation, thus providing good data support for the construction of the knowledge graph of the medicine specification and making up the data defect of the knowledge graph of the medicine specification at home and abroad.
Fig. 3 is a schematic structural diagram of a drug interaction relationship extraction system according to an embodiment of the present invention, as shown in fig. 3, including: an identification extraction module 301 and a comprehensive judgment module 302, wherein:
the recognition extraction module 301 is configured to input the drug specification into a trained machine learning model, and recognize a drug entity relationship, where the machine learning model is established by extracting feature text information in the drug specification in a semi-supervised learning training manner;
the comprehensive judgment module 302 is used for referencing the medicine entity relationship to pharmacists and users.
The specific extraction of the drug interaction relationship by the identification extraction module 301 and the comprehensive judgment module 302 can be referred to the embodiment shown in fig. 1, and the embodiments of the present invention are not described herein again.
Fig. 4 illustrates a schematic structural diagram of an electronic device, and as shown in fig. 4, the server may include: a processor (processor) 401, a communication interface (Communications Interface) 402, a memory (memory) 403 and a bus 404, wherein the processor 401, the communication interface 402 and the memory 403 complete communication with each other through the bus 404. The communication interface 404 may be used for information transfer between the server and the smart tv. The processor 401 may call logic instructions in the memory 403 to perform the following method: inputting a medicine instruction book into a trained machine learning model, and identifying a medicine entity relationship, wherein the machine learning model is established by extracting characteristic text information in the medicine instruction book in a semi-supervised learning training mode; the drug entity relationship is referenced by the pharmacist and the user.
The present embodiment also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the methods provided by the above-described method embodiments, for example comprising: inputting a medicine instruction book into a trained machine learning model, and identifying a medicine entity relationship, wherein the machine learning model is established by extracting characteristic text information in the medicine instruction book in a semi-supervised learning training mode; the drug entity relationship is referenced by the pharmacist and the user.
The present embodiment provides a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: inputting a medicine instruction book into a trained machine learning model, and identifying a medicine entity relationship, wherein the machine learning model is established by extracting characteristic text information in the medicine instruction book in a semi-supervised learning training mode; the drug entity relationship is referenced by the pharmacist and the user.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, the method of the present application is only a preferred embodiment and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (7)

1. A method of extracting a drug interaction relationship, comprising:
Establishing a machine learning model, the step of establishing the machine learning model comprising: acquiring medicine specification data, constructing the medicine specification data, the medicine entity name and specific relation types among the medicine specification data, the medicine entity name and the specific relation types into a category database, and constructing the category database further comprises the following steps: identifying the drug name entity by utilizing the drug entity name provided by a pharmacist and specific relation type and named entity identification technology to supplement the drug name entity to form a category database; extracting text information in the drug instruction book based on the category database and supplementing the missing syntax structure completely to establish the machine learning model, wherein the steps of extracting text information in the drug instruction book based on the category database and supplementing the missing syntax structure completely comprise: extracting text information of two drug entities appearing simultaneously in text information of a drug instruction by using the established category database, and supplementing the missing syntax structure for the text information lacking a subject by using an NLP;
Training the machine learning model;
Inputting the medicine instruction book into the trained machine learning model, and identifying the medicine entity relation; the machine learning model is established by extracting characteristic text information in a medicine instruction book in a semi-supervised learning training mode;
the drug entity relationship is referenced by the pharmacist and the user.
2. The drug interaction relationship extraction method of claim 1, wherein the training the machine learning model comprises:
And labeling the text information extracted from the medicine instruction book by a semi-supervised learning mode.
3. The drug interaction relationship extraction method of claim 2, wherein the method further comprises:
and checking the output result of the trained machine learning model, correcting the wrong text information, and extracting all the text information with the wrong recognition so as to update the machine learning model.
4. The drug interaction relationship extraction method of claim 1, wherein the method further comprises:
and extracting the identified medicine entity relationship to form a triplet, and establishing a medicine instruction knowledge graph.
5. A drug interaction relationship extraction system, comprising:
The recognition extraction module is used for establishing a machine learning model, and the step of establishing the machine learning model comprises the following steps: acquiring medicine specification data, constructing the medicine specification data, the medicine entity name and specific relation types among the medicine specification data, the medicine entity name and the specific relation types into a category database, and constructing the category database further comprises the following steps: identifying the drug name entity by utilizing the drug entity name provided by a pharmacist and specific relation type and named entity identification technology to supplement the drug name entity to form a category database; extracting text information in the drug instruction book based on the category database and supplementing the missing syntax structure completely to establish the machine learning model, wherein the steps of extracting text information in the drug instruction book based on the category database and supplementing the missing syntax structure completely comprise: extracting text information of two drug entities appearing simultaneously in text information of a drug instruction by using the established category database, and supplementing the missing syntax structure for the text information lacking a subject by using an NLP; training the machine learning model; inputting a medicine instruction book into a trained machine learning model, and identifying a medicine entity relationship, wherein the machine learning model is established by extracting characteristic text information in the medicine instruction book in a semi-supervised learning training mode;
And the comprehensive judging module is used for referencing the medicine entity relationship to pharmacists and users.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the drug interaction relationship extraction method of any one of claims 1 to 4 when the program is executed.
7. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the drug interaction relation extraction method of any of claims 1 to 4.
CN202010569861.7A 2020-06-20 2020-06-20 Medicine interaction relation extraction method and system Active CN111914095B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010569861.7A CN111914095B (en) 2020-06-20 2020-06-20 Medicine interaction relation extraction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010569861.7A CN111914095B (en) 2020-06-20 2020-06-20 Medicine interaction relation extraction method and system

Publications (2)

Publication Number Publication Date
CN111914095A CN111914095A (en) 2020-11-10
CN111914095B true CN111914095B (en) 2024-04-19

Family

ID=73226098

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010569861.7A Active CN111914095B (en) 2020-06-20 2020-06-20 Medicine interaction relation extraction method and system

Country Status (1)

Country Link
CN (1) CN111914095B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110008959A (en) * 2019-03-26 2019-07-12 北京博瑞彤芸文化传播股份有限公司 A kind of medical data processing method and system
CN110119991A (en) * 2019-04-12 2019-08-13 深圳壹账通智能科技有限公司 Checking method, device and storage medium are compensated in medical treatment based on machine learning
CN110263226A (en) * 2019-05-10 2019-09-20 平安科技(深圳)有限公司 For the database update method, apparatus and electronic device of drug
CN110377755A (en) * 2019-07-03 2019-10-25 江苏省人民医院(南京医科大学第一附属医院) Reasonable medication knowledge map construction method based on medicine specification
CN110390021A (en) * 2019-06-13 2019-10-29 平安科技(深圳)有限公司 Drug knowledge mapping construction method, device, computer equipment and storage medium
CN111192654A (en) * 2019-12-30 2020-05-22 北京左医健康技术有限公司 Medicine taking guidance query method and device based on knowledge graph
CN111221979A (en) * 2019-12-31 2020-06-02 北京左医健康技术有限公司 Medicine knowledge graph construction method and system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11276010B2 (en) * 2017-03-06 2022-03-15 Wipro Limited Method and system for extracting relevant entities from a text corpus

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110008959A (en) * 2019-03-26 2019-07-12 北京博瑞彤芸文化传播股份有限公司 A kind of medical data processing method and system
CN110119991A (en) * 2019-04-12 2019-08-13 深圳壹账通智能科技有限公司 Checking method, device and storage medium are compensated in medical treatment based on machine learning
CN110263226A (en) * 2019-05-10 2019-09-20 平安科技(深圳)有限公司 For the database update method, apparatus and electronic device of drug
CN110390021A (en) * 2019-06-13 2019-10-29 平安科技(深圳)有限公司 Drug knowledge mapping construction method, device, computer equipment and storage medium
CN110377755A (en) * 2019-07-03 2019-10-25 江苏省人民医院(南京医科大学第一附属医院) Reasonable medication knowledge map construction method based on medicine specification
CN111192654A (en) * 2019-12-30 2020-05-22 北京左医健康技术有限公司 Medicine taking guidance query method and device based on knowledge graph
CN111221979A (en) * 2019-12-31 2020-06-02 北京左医健康技术有限公司 Medicine knowledge graph construction method and system

Also Published As

Publication number Publication date
CN111914095A (en) 2020-11-10

Similar Documents

Publication Publication Date Title
US10475132B1 (en) Computer implemented methods systems and articles of manufacture for identifying tax return preparation application questions based on semantic dependency
CN105260782A (en) Method and device for processing reserved registration information
CN108630322A (en) Drug interaction modeling and methods of risk assessment, terminal device and storage medium
CN108509484B (en) Classifier construction and intelligent question and answer method, device, terminal and readable storage medium
US20240296941A1 (en) Pharmacy sig codes auto-populating system
CN113177124A (en) Vertical domain knowledge graph construction method and system
CN110263009A (en) Generation method, device, equipment and the readable storage medium storing program for executing of log classifying rules
US11361152B2 (en) System and method for automated content labeling
Mathur Machine learning applications using python: Cases studies from healthcare, retail, and finance
CN111369290B (en) Method and system for automatically generating data acquisition module
WO2021051869A1 (en) Text data layout arrangement method, device, computer apparatus, and storage medium
US20220019729A1 (en) System and method for automated content annotation workflow
CN111882203B (en) Traditional Chinese medicine cloud service experimental system
US20230352192A1 (en) Method and apparatus for constructing drug knowledge graph
CN112016274A (en) Medical text structuring method and device, computer equipment and storage medium
CN113111162A (en) Department recommendation method and device, electronic equipment and storage medium
US9881004B2 (en) Gender and name translation from a first to a second language
CN114035793A (en) Page generation method, page generation device, equipment and storage medium
CN110473636B (en) Intelligent medical advice recommendation method and system based on deep learning
CN111914095B (en) Medicine interaction relation extraction method and system
Hotomski et al. GuideGen: An approach for keeping requirements and acceptance tests aligned via automatically generated guidance
CN117217332A (en) Medicine question-answering model training method and device, electronic equipment and storage medium
Perera et al. Data driven knowledge acquisition method for domain knowledge enrichment in the healthcare
US20230044863A1 (en) Method and system for recommendation of cognitive and skill based learning competencies
Wang et al. Electronic source data transcription for electronic case report forms in China: validation of the electronic source record tool in a real-world ophthalmology study

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant