CN112965958B - Intelligent system for medicine standardization and medicine catalogue matching - Google Patents
Intelligent system for medicine standardization and medicine catalogue matching Download PDFInfo
- Publication number
- CN112965958B CN112965958B CN202110316258.2A CN202110316258A CN112965958B CN 112965958 B CN112965958 B CN 112965958B CN 202110316258 A CN202110316258 A CN 202110316258A CN 112965958 B CN112965958 B CN 112965958B
- Authority
- CN
- China
- Prior art keywords
- medicine
- medicines
- module
- drug
- knowledge base
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an intelligent system for medicine standardization and medicine catalog matching, which comprises a medicine knowledge base construction related to an intelligent system, a medicine standardization intelligent system and a medicine catalog matching intelligent system, wherein the medicine knowledge base construction related to the intelligent system comprises the following modules: m1 drug module: collecting all marketed drug information; m2 classification module: classifying the medicines according to the preparation characteristics of the medicines, constructing a medicine knowledge base on the basis, describing various aspects of the medicines from the preparation perspective and embodying the essence of the medicines; the medicine is standardized by the medicine identifying words and distinguishing words, is not limited by the medicine information description sequence and the inconsequential description character difference, does not need to be subjected to complicated text calculation process and complicated result analysis, is simple, efficient and accurate, and provides possibility for medicine information interconnection and information sharing.
Description
Technical Field
The invention belongs to the technical field of information, and particularly relates to an intelligent system for drug knowledge base construction, drug standardization and drug catalog matching.
Background
The health data has various sources, numerous and complex contents and scattered information, and interconnection and information sharing are difficult to realize at present. The medicine data come from various links such as medicine research and development, production, circulation, use and the like, and similar problems also exist. Drug standardization is the key to realizing information sharing and resource integration, provides possibility for drug and even big data analysis and data mining in the whole sanitary field, and is the basis for further building an intelligent analysis model and forming a business analysis report.
The current common method is to judge the text similarity of the sub-information of the original target information and the sub-information of the standard information one by one, calculate the comprehensive matching score, and determine the standard information corresponding to the maximum comprehensive matching score as the matching information of the original target information. Due to different sources, different links and human factors, the description sequence of the medicine information is not invariable, the sub-information sequence of the original target information is not easy to determine, and different types of sub-information comparison between the original target information and standard information exists, so that the standardization cannot be realized; in addition, medicine description modes are also various, and a small difference in character description can cause a complicated text calculation process and complex result analysis, so that more human participation and continuous method modification are required, and the efficiency is low. The invention is not limited by the description sequence of the medicine information and the difference of the irrelevant medicine description words, and provides a simple, efficient and accurate medicine standardized intelligent system.
Drug big data analysis and data mining also often need to be established on the basis of matching between two drug catalogs, which is essentially to compare drugs and screen the optimal matching in different comparison results according to different requirements. However, even the drug data described in the standard specification is difficult to directly compare, for example: medicine A (metronidazole injection-20 ml: 0.1g) and medicine B (metronidazole-0.1 g for injection). The quantity of metronidazole as an active ingredient of the two medicines is the same, and the specifications cannot be directly compared due to different dosage forms and different specification description forms. In addition, due to different sources, time periods and the like of the medicine catalogs, the varieties and the quantities contained in the catalogs are different, and the matching rules of each matching are different. How to solve the problems, the invention constructs a medicine data model from the aspect of the preparation characteristics of the medicine, thereby providing an intelligent medicine catalog matching system with wide application range.
Disclosure of Invention
The invention aims to provide a medicine standardization intelligent system aiming at the phenomena of disordered medicine information, different description sequences and different description modes, realizes simple, efficient and accurate standardization of medicines and solves the problem of medicine information sharing obstacle. Meanwhile, aiming at different varieties contained in different drug catalogs and different matching rules, the drug catalog matching intelligent system with wide application range is further provided through a drug data model constructed from the aspect of the preparation characteristics of drugs. The invention lays a foundation for big data analysis and data mining of the medicine.
In order to achieve the purpose, the invention provides the following technical scheme:
the intelligent system for drug standardization and drug catalog matching comprises an intelligent system-related drug knowledge base construction module, a drug standardization intelligent system and a drug catalog matching intelligent system, wherein the intelligent system-related drug knowledge base construction module comprises the following modules:
m1 drug module: collecting all marketed drug information;
m2 classification module: classifying the medicines according to the preparation characteristics of the medicines, constructing a medicine knowledge base on the basis, describing various aspects of the medicines from the preparation perspective, and embodying the essence of the medicines;
m3 data metadata module: the medicine is composed of common names, dosage forms, specifications, specification attributes, packaging materials or basic elements of a production enterprise, and basic elements are used as basic data elements to construct a basic medicine data model for all marketed medicines;
m4 data meta attribute module: determining the attribute of each data element of different types of medicines according to the classification;
m5 standard module: standardizing attribute values of data elements of different types of medicines according to the determined rule, and endowing codes to the data elements;
m6 non-standard module: in addition to the above descriptions according to the specification of the determination rule, the medicines have other common description modes, and the common descriptions of the universal name data elements of the medicines also include trade names, alias names or colloquial names;
the intelligent system for drug standardization comprises the following modules:
m1 identifies the word module: selecting the common name, the dosage form, the specification attribute, the packaging material and the attribute value of a data element of a production enterprise in a drug knowledge base as an identification word of each element of the drug, wherein the identification word comprises standard description and non-standard description; combining the attribute values of the data elements into an identification phrase of the medicine, wherein the attribute values of the same data elements are in an OR relationship, and the attribute values of different data elements are in an AND relationship;
m2 distinguisher module: only by judging whether a medicine identification phrase is included or not, the same medicine description is possibly corresponding to different medicines in a medicine knowledge base, and distinguishing words are introduced to be used as differences among similar medicines;
m3 information summarization module: splicing description texts of original medicines, not distinguishing sequences, and summarizing information of the original medicines;
m4 standardization module: unifying the expression modes of the metering units in the original medicine information according to the expression modes of the metering units of the identification words; removing meaningless characters; judging whether the original medicine information simultaneously contains a mark phrase and a distinguishing phrase of a certain medicine in a medicine knowledge base, if so, giving the code and the information of the medicine to the original medicine to realize the standardization of the medicine;
m5 maintenance module 1: if the original medicine information does not contain any identification phrases and analysis phrases of the medicines in the medicine knowledge base, analyzing the description of each element of the original medicine, and if the description is common, supplementing the identification words of the medicine in the medicine knowledge base; returning to the standardization module to realize medicine standardization;
m6 maintenance module 2: if the original medicine information contains more than 1 identification phrase and distinguishing phrase of the medicines in the medicine knowledge base, the essential difference between the medicines is obtained by comparing the medicines in the medicine knowledge bases in detail, and the distinguishing words of the medicines in the medicine knowledge base are supplemented; returning to the standardization module to realize medicine standardization;
the intelligent system for matching the medicine catalogue comprises the following modules:
m1 basic data module: selecting related data in a medicine knowledge base as basic data of the model, wherein the related data comprises a classification module, a data element module or a data element attribute module;
m2 analyze catalog module: determining the range of the analyzed medicines which are included in the comparison according to the analysis catalog, and endowing the medicines in the catalog with the standard ID of a medicine knowledge base through a medicine standardized intelligent system;
m3 references the directory module: selecting a reference catalog, determining a reference medicine range, and endowing medicines in the catalog with a standard ID of a medicine knowledge base through a medicine standardized intelligent system;
m5 comparison module: according to the matching rule 1, introducing the contents of data elements needing to be included in the drug knowledge base for comparison of an analysis catalog and a reference catalog through a standard ID respectively, comparing the common attributes of the same data elements of the drugs of the two catalogs one by one, synthesizing the comparison results, and assigning values to the comparison results of each attribute;
m7 matching module: and according to the matching rule 2, combining the comparison result values of the data elements and the attributes thereof which are included in the sequence according to the sequence as a matching sequence value, thereby screening out the optimal matching.
Preferably, the information summarizing module comprises a data storage module.
Preferably, the standard module further comprises a data processing module.
Compared with the prior art, the invention has the beneficial effects that: the medicines are standardized through the medicine identifying words and distinguishing words, the medicine information identification method is not limited by the medicine information description sequence and inconsequential description character differences, does not need to go through a complicated text calculation process and complicated result analysis, is simple, efficient and accurate, and provides possibility for medicine information interconnection and information sharing.
The basic data of the drug standardization model is identification words and distinguishing words of the drug instead of massive drug original information, so that the drug standardization model is simple to maintain and small in data storage capacity.
The medicine data model is constructed in the aspect of the preparation characteristics of the medicines, so that the comparison among the medicines is consistent with the preparation characteristics of the medicines, the essential comparison of the medicines is reflected instead of simple difference on description characters, and the application range is wide.
Drawings
FIG. 1 is a schematic diagram of the construction of a drug knowledge base associated with the intelligent system of the present invention;
FIG. 2 is a schematic diagram of a classification module, a data element module, and a data element attribute module according to the present invention;
FIG. 3 is a schematic illustration of the contents of a knowledge base of a drug of the present invention;
FIG. 4 is a schematic diagram of a drug standardization intelligence system of the present invention;
FIG. 5 is a schematic diagram of a word identifying module and a word distinguishing module according to the present invention;
FIG. 6 is a schematic diagram of an information summary module according to the present invention;
FIG. 7 is a schematic diagram of a drug catalog matching intelligence system of the present invention;
FIG. 8 is a schematic diagram of a comparison module and a matching module according to the present invention;
FIG. 9 is a schematic diagram of a comparison module and a matching module according to the present invention;
FIG. 10 is a schematic view of a comparison module of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
referring to fig. 1, the construction of the drug knowledge base related to the intelligent system includes the following modules:
m1 drug module: collecting all marketed drug information;
from the national drug administration, including domestic and imported drugs;
m2 classification module: classifying the medicines according to the preparation characteristics of the medicines, constructing a medicine knowledge base on the basis, describing various aspects of the medicines from the preparation perspective and embodying the essence of the medicines;
firstly, classifying according to chemical drugs, biological products and Chinese patent drugs; secondly, according to the classification of the preparation form, the medicine is divided into solid preparation, liquid preparation, cream, patch, pill and the like, for example: the tablet and capsule belong to solid preparation, and the oral liquid and mixture belong to liquid preparation, as shown in figure 2;
m3 data meta-module: the medicines generally comprise basic elements such as common names, dosage forms, specifications, specification attributes, packaging materials, manufacturing enterprises and the like, and basic elements are used as basic elements to construct a basic medicine data model for all marketed medicines, which is shown in figure 2;
m4 data meta attribute module: according to the above classification, determining the attributes of each data element of different types of medicines, see fig. 2;
the same type of drug has common formulation characteristics, and the information contained in the description text will be similar;
for example, the medicine' metronidazole injection-10 ml: 0.25 g-Tianjin Jinyao pharmaceutical Co., Ltd ", the specification of which describes the volume of the drug and the amount of the active ingredient, and the specifications of other drugs belonging to chemical drugs and liquid preparations also contain the information, so that the properties of the specifications of the drugs belonging to chemical drugs and liquid preparations are the loading amount (the volume of the preparation), the content (the amount of the active ingredient) and the concentration;
for example, the specification of a medicine belonging to chemical medicines and solid preparations, namely cefradine for injection-1.0 g-Shiqi pharmaceutical Co., Ltd, describes the amount of active ingredients of the medicine, and the specifications of other medicines belonging to chemical medicines and solid preparations also contain the information, so that the attributes of the specifications of the medicines belonging to the chemical medicines and the solid preparations are contents;
for example, the specifications of the medicines belonging to Chinese patent medicines and pills, namely 'pill of six ingredients with rehmannia-4 g (6 g per bag) -Fuci Lanzhou pharmaceutical Co., Ltd', describe the capacity and the weight of the medicines, and the specifications of other medicines belonging to Chinese patent medicines and pills also contain the information, so that the properties of the specifications of the medicines belonging to Chinese patent medicines and pills comprise the loading amount, the content, the weight of the pills and the like;
the attributes of the same type of drug data elements are the same, and the attributes of different types of drug data elements may be different;
m5 standard module: standardizing attribute values of data elements of different types of medicines according to the determined rules and endowing codes to the attribute values, as shown in FIG. 3; the standard module also comprises a data processing module, and the data processing method of the data processing module comprises but is not limited to word segmentation through a regular expression, information extraction and the like;
the common name of the medicine follows the naming principle of the common name of Chinese medicines, the general rule of the chemical medicine is application/characteristics + international non-patent name + salt/acid radical + dosage form, the general rule of the biological product is manufacturing method/source/character/approach + international non-patent name/disease + dosage form, and the general rule of the Chinese patent medicine is Chinese medicinal material/Chinese medicinal decoction piece/Chinese medicinal extract + dosage form; the standard rule of the common name is information such as international non-patent name/disease/traditional Chinese medicine decoction pieces/traditional Chinese medicine extract and the like, does not contain dosage form information, and a regular expression is constructed according to the general naming rule of the different types of medicines to obtain the information as the value of the common name attribute;
the dosage forms of the medicine are classified according to established rules, such as film-coated tablets, sugar-coated tablets and plain tablets which are all standardized as 'tablets';
the specifications of the same type of medicines have the same preparation characteristics, the description texts are similar, corresponding regular expressions are respectively constructed for each type of medicines, and the information of each attribute is obtained; for example, the description of pill specifications generally includes "pill/granule weight xx", "xx per bottle/bag package", and the like, a regular expression is constructed according to a common description mode, information such as the number of pills, the loading amount, the content and the like of pills is obtained, and the information is further standardized as the pill weight, the loading amount and the content attribute of pills;
pharmaceutical manufacturing enterprises generally consist of administrative divisions, word sizes, industries and organizational forms in turn, for example, "Tianjin Jinyao pharmaceutical company Limited", "Tianjin" is an administrative division, "Jinyao" is a word size, "pharmaceutical industry" is an industry, and "company Limited" is an organizational form; the standard rule of the attribute of the data element of the production enterprise, namely the standard value for enterprise abbreviation, is (administrative division) + word size, if no administrative division information exists, only the word size information is taken; information contained in administrative divisions, industries (pharmaceutical industry, biotechnology, pharmacy and the like) and organizational forms (companies, companies and the like) is determined and limited, and the administrative division information and the font size information of a production enterprise are obtained as enterprise abbreviation by constructing a regular expression of the administrative divisions + font size + industry + organizational forms;
m6 non-standard module: in addition to the above description according to the specification of the determination rule, the medicine has other common description modes, for example, the common description of the universal name data element of the medicine also includes a trade name, an alias, a colloquial name, etc., see fig. 3;
the common description sources of the data elements comprise original data in various links of medicine development, production, circulation, use and the like, such as HIS data, transaction data of a transaction platform, acquisition data and the like of a medical institution, different expression modes of the same medicine are analyzed on the basis of long-term accumulated standard original data, for example, the original common name is subjected to word segmentation, the frequency distribution of the residual words is counted except the standard descriptions of dosage forms, acid radicals, salt radicals and common names, and high-frequency words describing the common name of the medicine are selected as non-standard but common descriptions of the data elements of the common name of the medicine.
The second embodiment:
referring to fig. 4, the intelligent system for drug standardization includes the following modules:
m1 identifies the word module: selecting the common name, the dosage form, the specification attribute, the packaging material and the attribute value of a data element of a production enterprise in a drug knowledge base as an identification word of each element of the drug, wherein the identification word comprises standard description and non-standard description; combining the attribute values of the data elements into a marking phrase of the medicine, wherein the attribute values of the same data elements are in an OR relationship, and the attribute values of different data elements are in an AND relationship
In fig. 5, the identification word of the common name of the medicine 31 is azithromycin, the identification word of the specification is 0.125g or 12.5wiu, the identification word of the dosage form is hard capsule or capsule, the identification word of the manufacturing enterprise is sienna university constant pharmaceutical finite liability company or sienna university constant, and then the identification word of the medicine 31 is azithromycin + (0.125g or 12.5wiu) + (hard capsule or capsule) + (sienna university constant pharmaceutical finite liability company or sienna university constant), "+" indicates and is related; for example, if the original drug information "azithromycin-sika da gao heng pharmacy-0.125 g-capsule" contains the content of the identified phrase, the original drug corresponds to the drug 31 in the drug knowledge base;
based on the construction foundation of a medicine knowledge base, namely a medicine data model is constructed from the characteristics of medicine preparations, and the attribute values of data elements in the medicine knowledge base are particularly sources of non-standard values, and identification words of medicines have essential and common characteristics and are key information for identifying the medicines;
m2 distinguisher module: only by judging whether a medicine identification phrase is included or not, the same medicine description is possibly corresponding to different medicines in a medicine knowledge base, and distinguishing words are introduced to be used as differences among similar medicines;
in fig. 5, the identification phrase of the medicine 31 is azithromycin + (0.125g or 12.5wiu) + (hard capsule or capsule) + (sika da gazette pharmaceutical company ltd or sika gazette), and the identification phrase of the medicine 33 is azithromycin + (0.125g or 12.5wiu) + (soft capsule or capsule + soft) + (sika gazette pharmaceutical company ltd or sika gazette); for example, the drug description "azithromycin-sika da gao heng-0.125 g-gelcaps" contains both the identifying phrase for drug 31 and the identifying phrase for drug 33; however, the medicine 31 and the medicine 33 are two different medicines, and the dosage forms of the two medicines are different, the medicine 31 is a capsule, and the medicine 33 is a soft capsule, so that the 'soft' in the identification words of the dosage form of the medicine 33 is introduced as a distinguishing word thereof for distinguishing similar medicines which are easy to be confused;
the differentiating words of the medicine are a continuous rich and perfect process, and the primary differentiating words can be obtained through two steps: firstly, screening similar medicines; judging the difference points of similar medicines;
the screened similar drugs can be obtained by standardizing all drugs in a drug knowledge base, namely, the identification phrases of all drugs in the drug knowledge base are used as original drug information, and the drug ID is given to the drug knowledge base through the standardization of a drug standardization intelligent system; if the number of drug IDs assigned to the drug is more than 1, the drug is a similar confusable drug with the drug to which it is assigned (excluding itself); establishing a similar medicine grouping relation in the medicine knowledge base, for example, in fig. 5, the smallest medicine ID in the similar medicines may be used as a grouping identifier, the medicine 31 and the medicine 33 are similar medicines, and the grouping identifier is "31";
judging the difference points of the similar medicines can be obtained by comparing the similar medicines, namely, each group of similar medicines are respectively used as an analysis catalog and a reference catalog, and compared by a medicine catalog matching intelligent system, and the detailed process is shown in the third embodiment; for example, in fig. 5, the similar drugs (drug 31 and drug 33) are compared to each other to obtain different dosage forms, and the dosage form data element identifier of the two drugs are compared to obtain "soft" in the dosage form data element identifier of the drug 33 as the differentiation word for the drug 33;
m3 information summarization module: splicing description texts of original medicines, not distinguishing sequences, and summarizing information of the original medicines; the information summarizing module comprises a data storage module, and the data storage module is used for storing the medicine information.
The description of the original medicines is various and even the description sequence is disordered, and the original medicines C, E and G are not consistent with the description sequence of other medicines in fig. 6; the original medicine information is summarized without distinguishing the sequence;
m4 standardization module: unifying the expression modes of the metering units in the original medicine information according to the expression modes of the metering units of the identification words; removing meaningless characters such as spaces, bars "-", diagonals "/", etc.; judging whether the original medicine information simultaneously contains a mark phrase and a distinguishing phrase of a certain medicine in a medicine knowledge base, if so, giving the code and the information of the medicine to the original medicine to realize the standardization of the medicine;
here, whether the text contains the text can be judged by using Boyer-Moore algorithm, Knuth-Morris-Pratt algorithm or text containing function, etc.;
for example, in FIG. 6, the original drugs A-F all contain and only contain the identification phrases of the drugs 31 in the drug knowledge base of FIG. 5, and the original drugs A-F are now standardized to the drugs 31 in the drug knowledge base;
m5 maintenance module 1: if the original medicine information does not contain any identification phrases and analysis phrases of the medicines in the medicine knowledge base, analyzing the description of each element of the original medicine, and if the description is common, supplementing the identification words of the medicine in the medicine knowledge base; returning to the standardization module to realize medicine standardization;
for example, in fig. 6, the original drug G does not find a corresponding drug in the drug knowledge base, and the reason for analysis finds that the common name of the original drug G is described as an english name, at this time, the attribute non-standard values of all the drug common name data elements in the drug knowledge base are added with the drug english name content and used as one of the identification words of the common name, and the drug english name content is returned to the standardization module, and the original drug G is found to be the drug 31 in the drug knowledge base;
m6 maintenance module 2: if the original medicine information contains more than 1 identification phrase and distinguishing phrase of the medicines in the medicine knowledge base, obtaining essential difference among the medicines by comparing the medicines in the medicine knowledge base in detail, and supplementing the distinguishing words of the medicines in the medicine knowledge base; returning to the standardization module to realize medicine standardization;
for example, original drug H in FIG. 6 contains both identifying phrases of two drugs in the drug knowledge base of FIG. 5: the medicines 35 and 38 are analyzed and compared with the medicines 35 and 38 in different dosage forms, and the medicines are different in nature; the dosage form of the medicine 35 is 'tablet', the dosage form of the medicine 38 is 'dispersible tablet', the distinguishing word 'disperse' is added to the medicine 38, the medicine returns to the standardization module, and the original medicine H standard is the medicine 38 in the medicine knowledge base;
the drug knowledge base is used for continuously carrying out self standardization test, and simultaneously along with the accumulation of original drug data, the identification words and the distinguishing words of the drug can be gradually improved, and the standardization result of the drug is more accurate.
Example three:
referring to fig. 7, the intelligent system for matching drug catalogs comprises the following modules:
m1 basic data module: selecting related data in a drug knowledge base as basic data of a model, wherein the related data comprises a classification module, a data metadata attribute module and the like, the data model of the drug is established on the basis of drug preparation classification, the preparation characteristics of the drug are described in a standard way from all aspects, and a data basis is provided for the essential comparison of the drug, and the data basis is shown in figure 3;
m2 analyze catalog module: determining the range of the analyzed medicines which are included in the comparison according to the analysis catalog, and endowing the medicines in the catalog with the standard ID of a medicine knowledge base through a medicine standardized intelligent system;
for example, assay catalog A contains drugs with standard IDs of 1-12, see FIG. 3;
m3 references the directory module: selecting a reference catalog, determining a reference medicine range, and endowing medicines in the catalog with a standard ID of a medicine knowledge base through a medicine standardized intelligent system;
for example, reference catalog B contains drugs with standard IDs of 11-12, see FIG. 3;
for example, the actual demand 1 is: analyzing the comparison between the data elements of the catalog A and the reference catalog B, wherein the data elements are the same in the common name and are converted into the medicine, namely the matching rule 1-1: drug data element incorporated for comparison-generic name;
for example, the actual demand 2 is: analyzing the matching condition between the medicines with the same universal name and the same catalog dosage form in the catalog A and the reference catalog B, and converting the matching condition into the comparison between the data elements of the medicines, namely the matching rule 1-2: drug data elements incorporated for comparison-generic names, cataloged dosage forms, specifications, manufacturing companies, where the cataloged dosage forms can be classified according to specific rules, such as oral sustained release dosage forms, oral liquid dosage forms, injections, etc.;
for example, in the second embodiment, the difference points of similar drugs are judged and converted into the comparison between the data elements of the drugs, i.e. the matching rules 1-3: drug data elements for inclusion of comparisons-generic name, formulation, specification, manufacturing enterprise;
m5 comparison module: according to the matching rule 1, the contents of data elements which need to be included in the drug knowledge base for comparison of the analysis catalog and the reference catalog are respectively introduced through the standard ID, the common attributes of the same data elements of the drugs of the two catalogs are compared one by one, the comparison result is synthesized, and meanwhile, the comparison result of each attribute is assigned, for example: the "same/yes" value is 1, the "different/no" value is 0;
the attributes of the same data elements of different types of medicines may be different, and the attribute comparison common to the data elements is selected during medicine comparison, so that the essential comparison between the two medicines can be realized; for example, in FIG. 3, medicine 8 (metronidazole injection-20 ml: 0.1g) and medicine 12 (metronidazole-0.1 g for injection); the medicine 8 belongs to chemical medicine and liquid preparation, the medicine 12 belongs to chemical medicine and solid preparation, the common names and the attributes of the preparations are the same, and the attributes of the specifications are different; if all attributes of the specifications are compared, the specifications of the two medicines are different, but the amounts of active ingredients of the two medicines are actually the same, and the essential difference of the medicines can be reflected by comparing the content which is the common attribute of the specification data elements;
if the data elements for comparison do not exist in the original drug knowledge base, such as the catalog dosage forms in the matching rules 1-2, the drugs in the knowledge base can be classified according to the classification rules of the catalog dosage forms, and the catalog dosage forms can be used as new data elements to supplement the content of the drug knowledge base or as external data elements for comparison;
the comparison results according to matching rule 1-1 are shown in FIG. 8;
the comparison results according to matching rules 1-2 are shown in FIG. 9;
according to the comparison results of the matching rules 1-3, as shown in fig. 10, the similar drug groups (drug 31 and drug 33) are different in dosage form, and the descriptions of the dosage forms of the two drugs are further compared to obtain the distinguishers of the drugs in the similar drug groups;
for example, the actual demand 1 is: selecting the medicines with the same universal name in the analysis catalog A and the reference catalog B, and converting the medicines into the order between the data elements of the medicines, namely matching rules 2-1: the sorted medicine data element order is brought in-generic name;
for example, actual demand 2 is: analyzing the matching condition between the medicines with the same universal name and the same catalog dosage form in the catalog A and the reference catalog B, converting the medicines into the sequence between the data elements of the medicines, namely the matching rule 2-2: the sorted medicine data element sequence is included-universal name, catalog dosage form, specification, dosage form and enterprise;
m7 matching module: according to the matching rule 2, combining the comparison result values of the data elements and the attributes thereof which are included in the sequence according to the sequence as a matching sequence value, thereby screening out the optimal matching;
according to the sorting result of the matching rule 2-1, as shown in fig. 8, the universal name data element attribute values of all the medicines of the analysis catalog A are the same as the universal name data element attribute values of all the medicines of the reference catalog B, so that the medicines in the analysis catalog A and the medicines in the reference catalog B are all the optimal matching under the matching rule;
the result of the ordering according to matching rule 2-2 is shown in fig. 9, taking the analysis catalog a drug 1 as an example, the dosage form is the same as that of the reference catalog B drug 11, the specification and the enterprise are different, and the order value is "11010"; unlike the reference catalog B, drug 12, which is different in specification, dosage form and enterprise, the sequence value is "11000"; the order values of the analysis catalog A, medicine 1, reference catalog B, medicine 11 are greater than those of the analysis catalog A, medicine 1, reference catalog B, medicine 12, so that the analysis catalog A, medicine 1 and reference catalog B, medicine 11 are the optimal matching under the matching rule;
the intelligent system is established on the basis of a medicine knowledge base according to the characteristics of the medicine preparation; meanwhile, new data elements can be introduced according to actual requirements, and the content of the drug knowledge base is gradually enriched; the matching rules 1 and 2 are converted into the comparison and the sequencing between the medicine data elements or the external data elements, the data elements or the external data elements which are included in the comparison and the sequencing are converted along with the change of the matching rules 1 and 2, the optimal matching result between the analysis catalog and the reference catalog is changed along with the change of the data elements or the external data elements, and the model is an intelligent medicine catalog matching model which is compared from medicine preparations and reflects the essential difference between medicines and has wide application range.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. The utility model provides a medicine standardization and medicine catalogue match intelligent system, includes that intelligent system's relevant medicine knowledge base constructs, the standardized intelligent system of medicine and medicine catalogue matches intelligent system which characterized in that: the construction of the medicine knowledge base related to the intelligent system comprises the following modules:
m1 drug module: collecting all marketed drug information;
m2 classification module: classifying the medicines according to the preparation characteristics of the medicines, constructing a medicine knowledge base on the basis, describing various aspects of the medicines from the preparation perspective and embodying the essence of the medicines;
m3 data meta-module: the medicines are composed of common names, dosage forms, specifications, specification attributes, packaging materials or basic elements of manufacturing enterprises, and basic elements are used as basic data elements to construct basic medicine data models for all medicines on the market;
m4 data meta attribute module: determining the attribute of each data element of different types of medicines according to the classification;
m5 standard module: standardizing attribute values of data elements of different types of medicines according to the determined rule, and endowing codes to the data elements;
m6 non-standard module: in addition to the above descriptions according to the specification of the determination rule, the medicines have other common description modes, and the common descriptions of the universal name data elements of the medicines also include trade names, alias names or colloquial names;
the intelligent system for drug standardization comprises the following modules:
m1 identifies the word module: selecting the common name, the formulation, the specification attribute, the packaging material and the attribute value of a data element of a production enterprise in a medicine knowledge base as an identification word of each element of the medicine, wherein the identification word comprises standard description and non-standard description; combining the attribute values of the data elements into an identification phrase of the medicine, wherein the attribute values of the same data elements are in an OR relationship, and the attribute values of different data elements are in an AND relationship;
m2 distinguisher module: only by judging whether a medicine identification phrase is included or not, the same medicine description is possibly corresponding to different medicines in a medicine knowledge base, and distinguishing words are introduced to be used as differences among similar medicines;
m3 information summarization module: splicing description texts of original medicines, not distinguishing orders, and summarizing information of the original medicines;
m4 standardization module: unifying the expression modes of the metering units in the original medicine information according to the expression modes of the metering units of the identification words; removing meaningless characters; judging whether the original medicine information simultaneously contains a mark phrase and a distinguishing phrase of a certain medicine in a medicine knowledge base, if so, giving the code and the information of the medicine to the original medicine to realize the standardization of the medicine;
m5 maintenance module 1: if the original medicine information does not contain any identification phrases and analysis phrases of the medicines in the medicine knowledge base, analyzing the description of each element of the original medicine, and if the description is common, supplementing the identification words of the medicine in the medicine knowledge base; returning to the standardization module to realize medicine standardization;
m6 maintenance module 2: if the original medicine information contains more than 1 identification phrase and distinguishing phrase of the medicines in the medicine knowledge base, the essential difference between the medicines is obtained by comparing the medicines in the medicine knowledge bases in detail, and the distinguishing words of the medicines in the medicine knowledge base are supplemented; returning to the standardization module to realize medicine standardization;
the intelligent system for matching the medicine catalogue comprises the following modules:
m1 basic data module: selecting related data in a drug knowledge base as basic data of the model, wherein the related data comprises a classification module, a data element module or a data element attribute module;
m2 analyze catalog module: determining the range of the analyzed medicines which are included in the comparison according to the analysis catalog, and endowing the medicines in the catalog with the standard ID of a medicine knowledge base through a medicine standardized intelligent system;
m3 references the directory module: selecting a reference catalog, determining a reference medicine range, and endowing medicines in the catalog with a standard ID of a medicine knowledge base through a medicine standardized intelligent system;
m4 match rule 1 module: according to the actual demand matched with the medicine catalog, converting the actual demand into the comparison among the data elements of the medicines, and determining the data elements of the medicines which need to be brought into the comparison;
m5 comparison module: according to the matching rule 1, the contents of data elements needing to be included in the drug knowledge base for comparison of the analysis catalog and the reference catalog are respectively introduced through the standard ID, the common attributes of the same data elements of the drugs of the two catalogs are compared one by one, the comparison results are integrated, and meanwhile, the comparison result of each attribute is assigned;
m6 match rule 2 module: according to the actual demand matched with the medicine catalog, converting the actual demand into the order between the data elements and the attributes of the medicines, and determining the order of the data elements and the attributes of the medicines or the external data which need to be brought into the ordering;
m7 matching module: and according to the matching rule 2, combining the comparison result values of the data elements and the attributes thereof which are included in the sequence according to the sequence as a matching sequence value, thereby screening out the optimal matching.
2. The intelligent system for drug standardization and drug catalog matching as set forth in claim 1, wherein: the information summarizing module comprises a data storage module.
3. The intelligent system for drug standardization and drug catalog matching as set forth in claim 1, wherein: the standard module further comprises a data processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110316258.2A CN112965958B (en) | 2021-03-24 | 2021-03-24 | Intelligent system for medicine standardization and medicine catalogue matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110316258.2A CN112965958B (en) | 2021-03-24 | 2021-03-24 | Intelligent system for medicine standardization and medicine catalogue matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112965958A CN112965958A (en) | 2021-06-15 |
| CN112965958B true CN112965958B (en) | 2022-05-31 |
Family
ID=76278376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110316258.2A Active CN112965958B (en) | 2021-03-24 | 2021-03-24 | Intelligent system for medicine standardization and medicine catalogue matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112965958B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113488119B (en) * | 2021-06-18 | 2024-02-02 | 重庆医科大学 | Drug small molecule numerical value characteristic structured database and establishment method thereof |
| CN113392133A (en) * | 2021-06-29 | 2021-09-14 | 浪潮软件科技有限公司 | Intelligent data identification method based on machine learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184052A (en) * | 2015-08-13 | 2015-12-23 | 易保互联医疗信息科技（北京）有限公司 | Automatic coding method and system for medicine information |
| CN109192321A (en) * | 2018-09-26 | 2019-01-11 | 北京理工大学 | The construction method and calculating storage device of drug knowledge mapping |
| CN111475686A (en) * | 2020-03-17 | 2020-07-31 | 平安科技（深圳）有限公司 | Medicine classification method and device, storage medium and intelligent equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160292366A1 (en) * | 2013-11-12 | 2016-10-06 | Ecbig (E-Commerce & Business Integration) Aps | System and method of combining medicinal product information of medicaments |
| CN111198887B (en) * | 2019-12-31 | 2021-02-26 | 北京左医健康技术有限公司 | Medicine indexing method, medicine retrieval method and system |
-
2021
- 2021-03-24 CN CN202110316258.2A patent/CN112965958B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184052A (en) * | 2015-08-13 | 2015-12-23 | 易保互联医疗信息科技（北京）有限公司 | Automatic coding method and system for medicine information |
| CN109192321A (en) * | 2018-09-26 | 2019-01-11 | 北京理工大学 | The construction method and calculating storage device of drug knowledge mapping |
| CN111475686A (en) * | 2020-03-17 | 2020-07-31 | 平安科技（深圳）有限公司 | Medicine classification method and device, storage medium and intelligent equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112965958A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112965958B (en) | Intelligent system for medicine standardization and medicine catalogue matching | |
| Khader et al. | Pharmacy robotic dispensing and planogram analysis using association rule mining with prescription data | |
| US9275367B2 (en) | System for designating, displaying and selecting types of process parameters and product outcome parameters | |
| Vázquez-Espino et al. | Development and validation of a short sport nutrition knowledge questionnaire for athletes | |
| CN111968756A (en) | Knowledge graph construction method and device for medicine specification | |
| Dwyer et al. | Commentary: An impossible dream? Integrating dietary supplement label databases: Needs, challenges, next steps | |
| CN101673291A (en) | Method, system and device of data retrieval of patent documents | |
| Pinches et al. | Curation and analysis of clinical pathology parameters and histopathologic findings from eTOXsys, a large database project (eTOX) for toxicologic studies | |
| Iseppi et al. | Rasch model for assessing propensity to entomophagy | |
| CN109817300B (en) | Medicine-taking rule generation method based on artificial intelligence | |
| Vander Stichele et al. | Aggregations of substance in virtual drug models based on ISO/CEN standards for Identification of Medicinal Products (IDMP) | |
| Shah et al. | An algorithm to derive a numerical daily dose from unstructured text dosage instructions | |
| Lester et al. | Comparing the variability of ingredient, strength, and dose form information from electronic prescriptions with RxNorm drug product descriptions | |
| Dwyer et al. | Progress in development of an integrated dietary supplement ingredient database at the NIH Office of Dietary Supplements | |
| Ośko et al. | Assessment of the Mineral Composition and the Selected Physicochemical Parameters of Dietary Supplements Containing Green Tea Extracts | |
| Koshechkin et al. | Implementation of IDMP standards as a means of creating a unified information space in the field of drug circulation | |
| CN114927232B (en) | Drug research and development type mining and searching method and device and electronic equipment | |
| CN113689924A (en) | Similar medical record retrieval method and device, electronic equipment and readable storage medium | |
| Schjøtt et al. | Review of Clinical Questions Submitted to Norwegian Drug Information Centres Concerning Administration and Dosage to Older Patients of Relevance to Patient-Centric Care | |
| Perelli et al. | Update of Dietary Supplement Label Database Addressing on Coding in Italy | |
| WO2012151499A2 (en) | A system for designating, displaying and selecting types of process parameters and product outcome parameters | |
| Lardos et al. | Towards a Novel Methodology for the Identification of Plants in Historical Texts: A Case Study Based on the Byzantine Pharmacy Text John the Physician's Therapeutics | |
| JP2003150710A (en) | Drug interaction matrix retrieval system | |
| Safdari et al. | Drug classification systems: Applications and characteristics | |
| Kenna et al. | Character Networks of the Íslendinga Sögur and Þættir |
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 |