CN112951446A

CN112951446A - Medicine query method, device, equipment and storage medium based on medicine atlas

Info

Publication number: CN112951446A
Application number: CN202110412613.6A
Authority: CN
Inventors: 郝碧波; 李春宇
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-04-16
Filing date: 2021-04-16
Publication date: 2021-06-11

Abstract

The application provides a medicine query method, a device, equipment and a storage medium based on a medicine atlas, wherein the method comprises the following steps: acquiring first target data comprising a medicine name and a medicine attribute from different data sources; acquiring second target data including association information between different medicines; based on a preset naming rule, carrying out naming standardization processing on the first target data and the second target data to obtain standardized first data and standardized second data; generating a target medicine map capable of indicating the name and the attribute of the medicine and the association information between different medicines according to the standardized first data and the standardized second data based on a knowledge map algorithm; determining at least one medicine in the target medicine map as a target medicine according to the query instruction; and outputting the name and the attribute of the target medicine and the associated information between the target medicine and the rest medicines in the target medicine map. Data redundancy can be reduced, and medicine query efficiency is improved. Also related to blockchain techniques, the target medical profile may be stored in blockchain link points.

Description

Medicine query method, device, equipment and storage medium based on medicine atlas

Technical Field

The present application relates to the field of medical knowledge maps, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for querying a medicine based on a medical knowledge map.

Background

The required information can be inquired through the knowledge graph in the information inquiry, the knowledge graph is generally formed by a relational database and a graph database through a mapping relation, different databases are used under different inquiry conditions, the condition that the inquiry is needed to be carried out on the other database when an intermediate result is inquired in one database can occur, the inquiry time is prolonged, and when the knowledge graph is constructed, the data redundancy and errors are easily generated when the knowledge graph is constructed through data in different data sources.

Disclosure of Invention

The application provides a medicine query method, a medicine query device, medicine query equipment and a computer readable storage medium based on a medicine atlas, aiming at reducing data redundancy and error probability generated when the medicine atlas is generated and improving the efficiency of querying medicines through the medicine atlas.

In a first aspect, the present application provides a method for querying a medicine based on a medicine atlas, the method comprising the steps of:

acquiring first target data from different data sources, wherein the first target data comprises medicine names and medicine attributes of medicines;

acquiring second target data, wherein the second target data comprises association information used for indicating association degrees among different medicines;

based on a preset naming rule, carrying out naming standardization processing on the first target data to obtain standardized first data, and carrying out naming standardization processing on the second target data to obtain standardized second data;

generating a target medicine map according to the standardized first data and the standardized second data based on a knowledge map algorithm, wherein the target medicine map can indicate medicine names, medicine attributes and associated information among different medicines;

determining at least one drug in the target medicine map as a target drug according to a query instruction;

and outputting the medicine name and the medicine attribute of the target medicine and the association information between the target medicine and the rest medicines in the target medicine map.

In a second aspect, the present application further provides a drug query device, including:

the system comprises a first data acquisition module, a second data acquisition module and a third data acquisition module, wherein the first data acquisition module is used for acquiring first target data from different data sources, and the first target data comprises the medicine name and the medicine attribute of a medicine;

the second data acquisition module is used for acquiring second target data, and the second target data comprises correlation information used for indicating the degree of correlation between different medicines;

the naming module is used for carrying out naming standardization processing on the first target data to obtain standardized first data and carrying out naming standardization processing on the second target data to obtain standardized second data based on a preset naming rule;

the map generation module is used for generating a target medicine map according to the standardized first data and the standardized second data based on a knowledge map algorithm, and the target medicine map can indicate names, attributes and associated information between different medicines;

and the medicine inquiry module is used for determining at least one article in the target medicine map as a target medicine according to the inquiry instruction.

And the medicine output module is used for outputting the name and the attribute of the target medicine and the associated information between the target medicine and the rest medicines in the target medicine map.

In a third aspect, the present application also provides a computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the medicine atlas-based drug query method as described above.

In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the steps of the medicine atlas-based medicine query method as described above.

The application provides a medicine query method, a medicine query device, medicine query equipment and a computer readable storage medium based on a medicine atlas, wherein first target data are obtained from different data sources, and the first target data comprise medicine names and medicine attributes of medicines; acquiring second target data, wherein the second target data comprises association information used for indicating association degrees among different medicines; based on a preset naming rule, carrying out naming standardization processing on the first target data to obtain standardized first data, and carrying out naming standardization processing on the second target data to obtain standardized second data; generating a target medicine map according to the standardized first data and the standardized second data based on a knowledge map algorithm, wherein the target medicine map can indicate medicine names, medicine attributes and associated information among different medicines; determining at least one drug in the target medicine map as a target drug according to a query instruction; and outputting the medicine name and the medicine attribute of the target medicine and the association information between the target medicine and the rest medicines in the target medicine map. In the process of establishing the target medicine atlas, the medicine names and the medicine attributes acquired from different data sources are named and standardized, so that data redundancy is reduced, the probability of data errors is reduced, the target medicine atlas can simultaneously provide inquiry of the medicine names and the medicine relations, and the inquiry time is effectively reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flowchart illustrating steps of a medicine query method based on a medicine atlas according to an embodiment of the present application;

fig. 2 is a schematic block diagram of a tree structure of a medicine query method based on a medicine atlas according to an embodiment of the present application;

fig. 3 is a flow chart illustrating sub-steps of a medicine query method based on a medicine atlas according to an embodiment of the present application;

FIG. 4 is a flow diagram illustrating sub-steps of the method for medication map based drug query of FIG. 3;

FIG. 5 is a flowchart illustrating a method for querying a medicine based on a medicine atlas according to an embodiment of the present application;

FIG. 6 is a schematic block diagram of a drug query device provided in an embodiment of the present application;

fig. 7 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.

The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. 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 application.

The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

The embodiment of the application provides a medicine inquiry method and device based on a medicine atlas, computer equipment and a computer readable storage medium. The medicine query method based on the medicine atlas can be applied to terminal equipment, and the terminal equipment can be electronic equipment such as a mobile phone, a tablet computer, a notebook computer and a desktop computer.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.

Referring to fig. 1, fig. 1 is a flowchart illustrating a medicine query method based on a medicine atlas according to an embodiment of the present application.

As shown in fig. 1, the medicine atlas-based medicine query method includes steps S110 to S160.

Step S110, first target data are obtained from different data sources, and the first target data comprise medicine names and medicine attributes of medicines.

The data sources may illustratively be databases of different companies or hospitals in the pharmaceutical industry, it being understood that the databases of companies or hospitals may have drug names and/or drug attributes for several drugs stored therein.

For example, the drug name and the drug attribute of the drug may be stored in a node of the blockchain, and the drug name and the drug attribute of the drug may be obtained from the node of the blockchain. The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

For example, the drug names and drug attributes of a plurality of drugs may be obtained from a plurality of data sources, or the drug names and drug attributes of a plurality of drugs may be obtained from one data source. The drugs retrieved from multiple data sources may be duplicated, i.e., the same drug may appear in different data sources, and the drug names and drug attributes of the same drug may be different in different data sources.

For example, the drug properties of a drug product may include the type, composition, and/or use of the drug product, for example, the drug properties of a compound soluble capsule may be a capsule type, edible gelatin, carrier a group a drug powder, etc. It is understood that the above description of the drug property is only an exemplary example, and does not limit the drug property of the drug.

Illustratively, the acquired first target data is stored in a hybrid database, wherein the hybrid database can simultaneously realize the storage, management and query functions of a relational schema (relational) and a graph schema (graph).

For example, as shown in table 1 below, after the obtained first target data is stored in the hybrid database, an entity table (entity table) is generated according to the first target data, where the entity table (entity table) may be used to store the drug name of the drug and the corresponding drug attribute.

TABLE 1

Step S120, second target data is obtained, and the second target data comprises association information used for indicating association degrees among different articles.

Illustratively, there may be associations between different drugs, e.g., different drugs may be used to treat the same disease, belong to the same category, or be manufactured in close composition.

For example, when determining a drug for treating a disease, querying a certain drug and simultaneously obtaining other drugs having a certain degree of association with the drug can improve the degree of selection of a doctor and facilitate analysis of the drug and the disease.

Illustratively, as shown in table 2 below, the obtained second target data is stored in the hybrid database, and a relationship table (relationship table) is generated according to the second target data, wherein the relationship table (relationship table) may store the association degree between different medicines. For example, the same name of the drug in the relationship table (relationship table) may be stored under the path identified by the name (path _ same), and the same source, that is, the same data source may be acquired under the path identified by the source (path _ source), it is understood that the storage path in the relationship table (relationship table) is only an exemplary example, and is not limited to the storage path of the relationship table (relationship table), and the storage path may also have functions and components, and the like.

TABLE 2

In some embodiments, said obtaining second target data comprises: second target data is obtained from a different data source.

For example, as shown in step S110, the second target data may be obtained from a plurality of different data sources, and it can be understood that when the data sources store the drugs, the drugs with the same component may be classified into the same category according to a classification criterion, such as a classification criterion of the component, or the drugs with similar or identical functions may be classified into the same category according to a classification criterion of the function. The association information between the medicines can be directly known when the second target data is acquired from the data source.

In other embodiments, the obtaining second target data comprises: and determining the second target data according to the first target data.

For example, the association information of the association degree between the medicines may be determined according to the acquired first target data, and if the medicines with a certain association degree have the same word in the medicine name or the medicine attribute, the association degree between the corresponding medicines may be determined according to the medicine name and the medicine attribute between different medicines. It will be appreciated that the names of drugs that act similarly will also be close.

In some embodiments, said determining said second target data from said first target data comprises: performing word segmentation on the drug name and the drug attribute of the drug in the first target data and extracting a plurality of keywords; comparing keywords extracted from the drug names and the drug attributes of different drugs; and determining the degree of association between the corresponding medicines according to the comparison result to obtain association information for indicating the degree of association between the medicines.

Illustratively, the Word segmentation processing is performed on the drug name and the drug attribute of the drug in the acquired first target data, and the Word segmentation and the keyword extraction may be performed through natural speech processing (NLP) such as a TF-IDF method, a TextRank method, or a Word2Vec Word clustering method.

Illustratively, the extracted keywords are compared to obtain a comparison result, where the comparison result may be the drug names of different drugs and/or the number of the same keywords in the drug attributes, so as to determine the degree of association therebetween.

For example, 7 keywords are extracted from the a medicine, 10 keywords are extracted from the B medicine, and 5 words appear in both the keywords of the a medicine and the keywords of the B medicine, the degree of association between the a medicine and the B medicine can be determined.

For example, the association degree between the medicines can be determined by the number of the same keywords and the total number of the extracted keywords, so as to obtain the association information, for example, if 7 keywords are extracted from the a medicines, including 5 keywords which are the same as the keywords extracted from the B medicines, the association degree between the a medicines and the B medicines is 70%, and conversely, the association degree between the B medicines and the a medicines is 50%. It can be understood that the association degree between the medicine a and the medicine B may be different from the association degree between the medicine B and the medicine a, specifically, when the medicine a is queried, the association degree of the medicine B may be displayed to be 70%, and when the medicine B is queried, the association degree of the medicine a may be displayed to be 50%.

In one embodiment, before determining the degree of association between the corresponding drugs according to the comparison result, determining whether there is an association between the drugs according to the drug names of the drugs, and if there is an association between the drugs, determining the degree of association between the drugs according to the drug attributes of the drugs.

For example, whether there is a possibility of association between drugs is determined by drug names of different drugs, and it can be understood that drugs with the same action or similar components will generally be represented in the names, that is, the same keywords will not be used in the drug names corresponding to the drugs.

Illustratively, keyword extraction processing is performed on the drug names of at least two drugs, and comparison is performed to determine whether a correlation exists, and if the correlation exists, the degree of correlation between the drug names is further determined.

For example, a drug with the drug name of the A-type bromelain enteric-coated tablet and a drug with the drug name of the B-type bromelain capsule can extract pineapples and a plurality of keywords of protease from the drug names, so that the correlation between the two drugs can be determined, and then the keywords of the drug attributes are extracted for comparison, such as extraction of edema eliminating, enzyme drugs and enteric-coated tablets from the A-type bromelain enteric-coated tablet, and extraction of edema eliminating, enzyme drugs and capsules from the B-type bromelain capsule. In the drug attributes, only the keywords corresponding to the carriers are different, one is enteric-coated tablets and the other is capsules, so that the degree of association can be determined to be 80%.

By determining the degree of association between medicines, when a certain medicine is inquired, the medicines related to the medicine can be displayed, the selectivity is improved, and the time for inquiring information can be effectively reduced when the disease and medicine analysis is performed, if the medicines can be used for treating the same disease, and the effect and the side effect generated by the medicines are analyzed.

In some embodiments, the method further comprises: determining the drug name of the drug and the weight value of the keyword in the drug attribute; the determining the degree of association between the corresponding medicines according to the comparison result comprises: and determining the association degree between the corresponding medicines according to the keyword comparison results of the medicine names and the medicine attributes of different medicines and the weight values of the keywords.

For example, after extracting keywords from the drug name and/or the drug attribute of the drug, the weight value of the keyword may be determined, for example, the weight value of the keyword is determined to be 10% for a capsule, an oral liquid, and the like, it is understood that the capsule, the oral liquid, and the like are in the form of the drug, the influence on the nature of the drug is limited, and the weight value of the keyword is determined to be 50% for a protease, and it is understood that the component of the drug is important for the effect and the suitability for the population, and the weight value of the keyword of the component is set to be higher than the weight value of the keyword in the form of the.

In some embodiments, the weight values of the keywords in the drug name and drug property of the drug may be determined from the standard drug name and standard drug property in the data dictionary.

Illustratively, as provided in the sub-step S131 of the step S130 described below, the data dictionary is established based on a preset naming rule, where the preset naming rule may be a user' S own name or a standard drug name provided by an official channel, and the data dictionary indicates the standard drug name and the standard drug attribute of the drug through a tree structure, and the tree structure includes at least two layers, each layer including several different keywords in the standard drug name. As shown in fig. 2, it can be understood that the tree structure has a plurality of layers, each layer corresponds to a plurality of different keywords in the standard drug name, and a weight value can be set for the keyword of each layer, for example, the weight value of the keyword at the first layer of the tree structure is 10%, the weight value of the keyword at the second layer of the tree structure is higher than that of the keyword at the first layer, and so on, it can be understood that the weight value of the keyword at the highest layer (leaf node) of the tree structure is the highest.

It is understood that the tree structure shown in fig. 2 is only an exemplary example, and the tree structure in this application is not limited thereto, and the tree structure may have more layers.

The determining the degree of association between the corresponding medicines according to the comparison result comprises: and determining the association degree between the corresponding medicines according to the keyword comparison results of the medicine names and/or the medicine attributes of different medicines and the weight values of the keywords.

Illustratively, according to the comparison result of the keywords of different medicines, that is, identical keywords appear in the medicine names and/or the medicine attributes of different medicines, and the association degree between the corresponding medicines is determined according to the weight value corresponding to each identical keyword.

For example, the association degree between the A cough syrup, the C fever reducing capsule and the B cough capsule is determined, the syrup and the capsule key words are positioned on the second layer of the tree structure, and the cough key words are positioned on the third layer of the tree structure, so that the weight value of the cough key words is greater than that of the capsule key words, the result is that the association degree between the A cough syrup and the B cough capsule is greater than that between the B cough capsule and the C fever reducing capsule, and the association degree between different medicines can be obtained more accurately.

The weight values of the extracted keywords are determined through a plurality of keywords of the names of the standard medicines in each layer in the tree structure, so that the association degree between different medicines is determined, and a more accurate calculation result of the association degree can be obtained.

Step S130, based on a preset naming rule, conducting naming standardization processing on the first target data and the second target data to obtain standardized first data and standardized second data.

For example, since the drug names and drug attributes of drugs obtained from different data sources may differ, in order to reduce data redundancy and reduce the probability of data errors, the drug names and drug attributes of drugs are subjected to naming standardization.

For example, the preset naming rule may be a standard drug name named by the user, or a standard drug name provided by an official channel, so as to achieve the purpose of naming standardization of drug names and drug attributes acquired from different data sources.

For example, the same medicine may be acquired in the process of acquiring the first target data, but the medicine names of the same medicine are different and are easily considered to be different medicines, so that the medicine names of the medicine are separately stored in an entity table (entity table) of the hybrid database, and after the naming standardization process, the medicine names of the medicine are unified, so that the situation that the same medicine is separately stored can be reduced, and data redundancy can be reduced.

Illustratively, when a medicine atlas is generated according to first target data and second target data, if naming standardization is not performed, mismatching between the first target data and the second target data may occur, for example, if a medicine is named aa in the first target data, and the name of the medicine a is named aab in the second target data, aa and aab may be considered as different medicines, so that association degrees of aa and aab with other medicines are respectively established, data redundancy is generated, and accuracy in query is reduced.

By naming the first target data and the second target data for standardization, data redundancy can be effectively reduced, the calculation amount of a computer can be reduced when a medicine atlas is generated according to the first target data and the second target data, the generation speed is increased, and the probability of data errors is reduced.

In some embodiments, as shown in FIG. 3, step S130 includes steps S131-S132.

Step S131, a data dictionary established based on a preset naming rule is obtained, and the data dictionary indicates standard medicine names and standard medicine attributes of medicines in a tree structure.

For example, as shown in fig. 2, a data dictionary having a tree structure based on a preset naming rule may be obtained, and the data dictionary may indicate standard drug names and standard drug attributes of drugs in the tree structure.

It is to be understood that the drug name is composed of a plurality of words and/or english words, and in the data dictionary, the plurality of words and/or english words in the standard drug name and/or the standard drug attribute are indicated by a tree structure.

Step S132, judging whether the medicine name and the medicine attribute of the medicine are the same as the standard medicine name and the standard medicine attribute according to the data dictionary, and naming and standardizing the medicine name and the medicine attribute in the first target data and the second target data according to the judgment result.

For example, the obtained first target data and the second target data may be compared with the data dictionary to determine whether the drug name and the drug attribute of the drug in the first target data are the same as the standard drug name and the standard drug attribute in the data dictionary.

For example, an entity table (entry table) and a relationship table (relationship table) in the hybrid database may be compared with the data dictionary.

Illustratively, the name standardization processing is carried out on the medicine names and the medicine attributes in the first target data and the second target data according to the judgment result.

For example, if it is determined that the drug name and the drug attribute of the drug are the same as the standard drug name and the standard drug attribute of the data dictionary, no processing is performed. And if the drug name and the drug attribute of the drug are judged to be different from the standard drug name and the standard drug attribute of the data dictionary, modifying the drug name and the drug attribute of the drug into the standard drug name and the standard drug attribute in the data dictionary.

In some embodiments, the tree structure includes at least two levels. As shown in fig. 4, step S132 includes steps S1321 to S1323.

Step S1321, comparing the medicine name and the medicine attribute of the medicine with the standard medicine name and the standard medicine attribute of the Nth layer number in the tree structure, wherein N is a natural number which is greater than 0 and is not greater than the total layer number of the tree structure.

Illustratively, in the tree structure of the data dictionary, at least two layers are included, it is understood that each layer of the tree structure corresponds to several different keywords in the names of the standard medicines, for example, in one tree structure, the keyword of the name of the standard medicine in the first layer is oral medicine, the keyword of the name of the standard medicine in the second layer is syrup, oral liquid, and so on, until the layer number (leaf node) equal to the total layer number of the tree structure corresponds to a specific name of the standard medicine, such as a type a syrup for stopping cough and moistening lung for children.

Illustratively, the drug names and/or drug attributes of the drugs in the entity table (entity table) and the relationship table (relationship table) are compared layer by layer in the tree structure to perform the naming standardization process.

Step S1322 is to modify the drug name and the drug attribute of the drug according to the standard drug name and the standard drug attribute of the nth layer if it is determined that the drug name and the drug attribute of the drug are different from the standard drug name and the standard drug attribute of the nth layer of the tree structure, and add 1 to N if N is smaller than the total number of layers of the tree structure.

Illustratively, when the drug name and the drug attribute of the drug are compared with the nth layer of the tree structure, the drug name and the drug attribute are different from a plurality of keywords in the standard drug name and the standard drug attribute of the layer, the plurality of keywords in the standard drug name and the standard drug attribute of the layer replace corresponding words in the drug name and the drug attribute of the drug, and after replacement, the N +1 layer is entered for continuous comparison until the comparison is completed until the number of layers corresponding to the depth of the tree. It is understood that N is a natural number greater than 0 and not greater than the total number of layers of the tree structure. The depth of the tree is used to characterize the total number of levels of the tree structure.

For example, the tree structure has 5 levels, and the drug names of the drugs are compared from the first level of the tree structure until the 5 th level is finished.

Step S1323, if the medicine name and the medicine attribute of the medicine are judged to be the same as the standard medicine name and the standard medicine attribute of the N-th layer of the tree structure, and if N is smaller than the total layer of the tree structure, adding 1 to N.

Illustratively, if it is determined that the drug name and the drug attribute of the drug are the same as the standard drug name and the standard drug attribute of the nth layer of the tree structure, the step of determining whether N is less than the total number of layers of the tree structure is performed without modifying the drug name and the drug attribute of the drug.

Illustratively, the drug names and/or drug attributes of the drugs in the entity table (entity table) and the relationship table (relationship table) are compared from the first layer of the tree structure, if the drug names and drug attributes of the drugs are the same as the keywords of the standard drug names and standard drug attributes of the first layer of the tree structure, the drugs enter the second layer of the tree structure to be continuously compared, and so on until the comparison is completed until the number of layers corresponding to the depth of the tree.

Exemplarily, a processing flow is shown in fig. 5, where fig. 5 is a schematic flow chart of a medicine query method based on a medicine atlas provided in an embodiment of the present application, a medicine name and a medicine attribute are compared with a keyword corresponding to an nth layer of a tree structure at the nth layer of the tree structure, and if a comparison result is the same and N is smaller than the total number of layers of the tree structure, the N +1 st layer is entered for continuous comparison. And if the comparison results are different, replacing and modifying the drug name and the drug attribute, and entering the (N + 1) th layer for continuous comparison when N is less than the total layer number of the tree structure.

The medicine names and the medicine attributes of the medicines are compared layer by layer in the tree structure of the data dictionary, so that the medicine names and the medicine attributes of the medicines can be subjected to naming standardization processing, and the accuracy of naming standardization can be improved.

And step S140, generating a target medicine map according to the standardized first data and the standardized second data based on a knowledge map algorithm, wherein the target medicine map can indicate medicine names, medicine attributes and associated information between different medicines of the medicines.

Illustratively, the naming normalization process is followed by obtaining normalized first data and normalized second data, and generating a target medical profile from the normalized first data and the normalized second data.

Illustratively, the target medicine atlas can indicate names, attributes and associated information between different medicines, so that the applicability of the target medicine atlas is increased.

For example, after naming standardization processing is performed on the drug name and the drug attribute of the drug in the entity table (entity table), a standardized entity table (standard entity table) is obtained, and an entity name view (entity view) is generated based on the standardized entity table (standard entity table), which can be understood as the entity name view (entity view) can perform visual output on the drug name and the drug attribute of the drug.

For example, the entity name view may be in tabular form or in parenthesis, it being understood that the name view may show the drug name of the drug as well as the drug attributes, e.g., some protease tablets may be shown as "A protease (enzymes, catalysts, catalysis), B protease (enzymes, carriers, transport)". The entity name view (entity view) can visually display the drug name and the drug attribute of the drug.

For example, after naming and standardizing the drug names of the drugs in the relationship table (standardized relationship table), a standardized relationship table (standardized relationship table) is obtained, and a relationship view (relationship view) is generated based on the standardized relationship table (standardized relationship table), it can be understood that the relationship view (relationship view) can visually output the association information between different drugs.

Illustratively, the relationship view (relationship view) may be in the form of a score, i.e. two different drugs are scored, the score indicating the degree of association between them, the higher the score, the higher the degree of association; the method can also be in a line form, namely different medicines are connected by line segments, and the degree of association between the medicines is represented by the thickness or color of the line segments.

Illustratively, the target medical map may be generated based on a knowledge map algorithm, wherein the knowledge map algorithm may be a map building function provided by a hybrid database, and mapping through an entity name view (entity view) and a relationship view (relationship view).

It can be understood that the generated target medicine map can provide not only the medicine name and the medicine attribute of the medicine, but also the association information between different medicines. The method and the system can simultaneously provide inquiry of the drug name and the drug relation, and effectively reduce inquiry time.

Illustratively, the generated target medicine atlas can be stored in block chain nodes, and the block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

It is understood that both the entity name view (entry view) and the relationship view (relationship view) can be stored in the block chain.

In some embodiments, an update instruction is received, the update instruction being used to instruct updating of drug names, drug attributes, and degrees of association between different drugs of drugs in a target medical profile, the target medical profile being updated based on the update instruction.

For example, after receiving the update command, the hybrid database performs name standardization processing on the drug name and the drug attribute of the drug in the update command based on the preset naming rule, please refer to step S130, so as to update the entity table and the relationship table, thereby updating the target medicine map.

The naming standardization processing before the updating can effectively reduce the probability of data errors when the target medicine atlas is updated, so that the updating accuracy is improved.

And S150, determining at least one medicine in the target medicine map as a target medicine according to the query instruction.

For example, the generated target medicine map may be used to perform a query of a target medicine in response to a query instruction of a user, so that the user can query a medicine name and a medicine attribute of at least one target medicine, and also query association information between the target medicine and the rest of medicines in the target medicine map. The speed of inquiring the medicine through the medicine atlas is improved, other medicines related to the target medicine can be output at the same time, and batch data analysis of a user is facilitated.

And step S160, outputting the medicine name and the medicine attribute of the target medicine and the association information between the target medicine and the rest medicines in the target medicine map.

Illustratively, after the target drug is determined, the drug name, the drug attribute, and the association information between the target drug and the rest of the drugs in the target pharmaceutical map are output.

For example, in response to different query instructions of a user, the name and the attribute of the target drug may be queried and output separately, or the association information between the target drug and the rest of the drugs in the target drug map may be output separately.

It will be appreciated that the target medication map may provide a drug name for a drug, a drug attribute query, and an association information query between different drugs, respectively.

In some embodiments, the query comprises a name attribute query, said determining at least one drug in the target drug graph as a target drug according to the query comprises extracting a drug name and/or a drug attribute keyword for the drug in the name attribute query; and performing keyword comparison in the target medicine atlas according to the keywords so as to determine a target medicine.

For example, when a drug name and a drug attribute query of a drug are performed, a target drug may be determined from a number of drugs of a target drug map through a name attribute query instruction, and a drug name and a drug attribute of the target drug may be output.

For example, when querying the drug name and the drug attribute of the target drug, the user may know the drug name of the drug, want to query the drug attribute corresponding to the drug name, or want to find a drug that can address the related disease, that is, know the drug attribute of the drug, want to query the drug name corresponding to the drug name, and it can be understood that the name attribute query instruction may include the drug name or the drug attribute of the target drug, perform keyword extraction on the drug name or the drug attribute of the target drug in the name attribute query instruction, compare the extracted keywords in the target drug map, and output a plurality of drugs with higher comparison coincidence, so that the user can query the target drug.

For example, after the target medicine is determined, the target medicine and the associated information of the rest medicines in the target medicine map may be output together, and it can be understood that the information of all the medicines associated with the target medicine may be output together, which may cause excessive data and decrease output efficiency.

The medicine names and the medicine attributes of the medicines can be efficiently inquired in the target medicine map by comparing the keywords, but when the associated information of the target medicines and the rest medicines in the target medicine map is output, the data is too much, and the associated information of the target medicines and another appointed medicine cannot be quickly acquired.

In some embodiments, the query instruction comprises a relational query instruction, the method further comprising: generating a medicine relation graph according to the relation query instruction; and performing image comparison in the target medicine map according to the generated medicine relation map so as to determine the association information between the target medicine and the rest medicines in the target medicine map.

For example, when performing association information query between medicines, association information between medicines may be determined from the target medicine graph through a relationship query instruction, and it may be understood that an output result of the target medicine graph includes association information between the target medicine and the rest of medicines in the target medicine graph.

For example, when performing a relationship query of a target drug, a user may know the relationship between at least two drugs, that is, one drug may be considered as the target drug, and the other drug or the rest drugs that the user wants to know may be considered as designated drugs, at this time, the user may only know the names of the target drug and a certain designated drug, and wants to query the association information between them, and it may be understood that the relationship query instruction may include the drug name of the target drug and the drug name of the designated drug, establish a relationship diagram for the drug names in the relationship query instruction, and perform image comparison on the established relationship diagram in the target drug map, and it may be understood that the association information between the drugs is stored in the target drug map, and the connection line or score value between the drugs is represented by the connection line or score value between the drugs, if there is an association between the queried drugs, the corresponding connection line or score value of the drugs can be found, the correlation degree of the corresponding medicine can be found quickly through image comparison, and correlation information does not need to be output after the medicine is slowly compared among a plurality of medicines.

In some embodiments, the query further comprises a composite query for a name or attribute of the target drug and a degree of association of the target drug with the specified drug. The method further comprises the following steps: extracting the drug name or the key word of the drug attribute of the target drug according to the composite query instruction, and generating a drug relation graph according to the target drug and the specified drug; and comparing keywords according to the keywords, and comparing images according to the relation graph to determine the medicine name or the medicine attribute of the target medicine and the associated information of the target medicine and the specified medicine.

For example, the compound query instruction can simultaneously query the drug name and the drug attribute of the target drug and the association information between the drug name and the specified drug, and simultaneously perform keyword comparison and image comparison according to the keywords in the compound query instruction and the established relationship map, so as to obtain the drug name and the drug attribute of the target drug and the association information between the drug name and the specified drug.

Illustratively, through compound query, the drug name, the drug attribute and the associated information of the rest specified drugs in the target medicine map can be simultaneously queried, and separate query is not needed, so that the operation times are reduced.

In the medicine query method based on the medicine atlas provided in the above embodiment, the first target data is obtained from different data sources, and the first target data includes the medicine name and the medicine attribute of the medicine; acquiring second target data, wherein the second target data comprises association information used for indicating association degrees among different medicines; based on a preset naming rule, carrying out naming standardization processing on the first target data to obtain standardized first data, and carrying out naming standardization processing on the second target data to obtain standardized second data; generating a target medicine map according to the standardized first data and the standardized second data based on a knowledge map algorithm, wherein the target medicine map can indicate medicine names, medicine attributes and associated information among different medicines; determining at least one drug in the target medicine map as a target drug according to a query instruction; and outputting the medicine name and the medicine attribute of the target medicine and the association information between the target medicine and the rest medicines in the target medicine map. The method has the advantages that the drug names and drug attributes of the drugs acquired from different data sources can be named and standardized in the process of establishing the target drug map, data redundancy and the probability of data errors are reduced, the target drug map can simultaneously provide query for the drug names, the drug attributes and the drug relationships, and query time is effectively reduced.

Referring to fig. 6, fig. 6 is a schematic diagram of a drug query device according to an embodiment of the present application, where the drug query device may be configured in a server or a terminal for executing the drug query method based on a medical atlas.

As shown in fig. 6, the medicine inquiry apparatus includes: a first data acquisition module 110, a second data acquisition module 120, a naming module 130, a map generation module 140, a drug query module 150, and a drug output module 160.

The first data obtaining module 110 is configured to obtain first target data from different data sources, where the first target data includes a drug name and a drug attribute of a drug.

A second data obtaining module 120, configured to obtain second target data, where the second target data includes association information indicating a degree of association between different medicines.

The naming module 130 is configured to perform naming normalization processing on the first target data to obtain normalized first data, and perform naming normalization processing on the second target data to obtain normalized second data, based on a preset naming rule.

A map generation module 140, configured to generate a target medicine map according to the normalized first data and the normalized second data based on a knowledge-map algorithm, where the target medicine map is capable of indicating medicine names, medicine attributes, and association information between different medicines of the medicines.

And the drug query module 150 is configured to determine at least one drug in the target medical profile as a target drug according to the query instruction.

A drug output module 160, configured to output a drug name and a drug attribute of the target drug, and association information between the target drug and the rest of the drugs in the target medical map.

Illustratively, the unified naming module 130 includes a dictionary obtaining sub-module and a name processing sub-module.

And the dictionary acquisition submodule is used for acquiring a data dictionary established based on a preset naming rule, and the data dictionary indicates the standard medicine names and standard medicine attributes of the medicines in a tree structure.

And the name processing submodule is used for judging whether the medicine name and the medicine attribute of the medicine are the same as the standard medicine name and the standard medicine attribute or not according to the data dictionary and carrying out naming standardization processing on the medicine name and the medicine attribute in the first target data and the second target data according to the judgment result.

Exemplarily, the name processing sub-module is further configured to compare the drug name and the drug attribute of the drug with the standard drug name and the standard drug attribute of the nth layer in the tree structure, where N is a natural number greater than 0 and not greater than the total layer of the tree structure;

if the medicine name and the medicine attribute of the medicine are judged to be different from the standard medicine name and the standard medicine attribute of the Nth layer of the tree structure, modifying the medicine name and the medicine attribute of the medicine according to the standard medicine name and the standard medicine attribute of the Nth layer, and adding 1 to N if the N is smaller than the total layer of the tree structure;

and if the medicine name and/or the medicine attribute of the medicine is judged to be the same as the standard medicine name and/or the standard medicine attribute of the Nth layer of the tree structure, and if N is smaller than the total layer of the tree structure, adding 1 to N.

Illustratively, the second data obtaining module 120 is further configured to obtain second target data from a different data source.

Or for determining the second target data from the first target data.

Illustratively, the second data obtaining module 120 further includes a keyword extracting sub-module, a keyword comparing sub-module, and an association degree determining sub-module.

And the keyword extraction submodule is used for segmenting the medicine name and the medicine attribute of the medicine in the first target data and extracting a plurality of keywords.

And the keyword comparison submodule is used for comparing keywords extracted from the medicine names and the medicine attributes of different medicines.

And the association degree determining submodule is used for determining the association degree between the corresponding medicines according to the comparison result to obtain association information used for indicating the association degree between the medicines.

Illustratively, the drug query device further comprises a weight determination sub-module.

And the weight determining submodule is used for determining the drug name of the drug and the weight value of the keyword in the drug attribute.

And the association degree determining submodule is also used for determining the association degree between corresponding medicines according to the keyword comparison results of the medicine names and the medicine attributes of different medicines and the weight values of the keywords, so as to obtain association information for indicating the association degree between the medicines.

Illustratively, the drug query module 150 includes a name attribute query submodule and a relationship query submodule.

And the name attribute query submodule is used for extracting the medicine name and/or the medicine attribute key words of the medicine in the name attribute query instruction, and performing key word comparison in the target medicine atlas according to the key words so as to determine the target medicine.

And the relation query submodule is used for generating a medicine relation graph according to the relation query instruction and carrying out image comparison in the target medicine graph according to the generated medicine relation graph so as to determine the association information between the target medicine and the rest medicines in the target medicine graph.

It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus, the modules and the units described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The methods, apparatus, and devices of the present application are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

The above-described methods and apparatuses may be implemented, for example, in the form of a computer program that can be run on a computer device as shown in fig. 7.

Referring to fig. 7, fig. 7 is a schematic block diagram illustrating a structure of a computer device according to an embodiment of the present disclosure. The computer device may be a server or a terminal.

As shown in fig. 7, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.

The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of the medication map based drug query methods.

The processor is used for providing calculation and control capability and supporting the operation of the whole computer equipment.

The internal memory provides an environment for the execution of a computer program on a non-volatile storage medium, which when executed by the processor, causes the processor to perform any one of the methods for drug lookup based on a medical profile.

The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Wherein, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the steps of:

In an embodiment, the processor is configured to, when implementing that the first target data is subjected to naming standardization processing based on a preset naming rule to obtain standardized first data, and the second target data is subjected to naming standardization processing to obtain standardized second data, implement:

acquiring a data dictionary established based on a preset naming rule, wherein the data dictionary indicates standard medicine names and standard medicine attributes of medicines in a tree structure;

and judging whether the medicine name and the medicine attribute of the medicine are the same as the standard medicine name and the standard medicine attribute according to the data dictionary, and naming and standardizing the medicine name and the medicine attribute in the first target data and the second target data according to the judgment result.

In one embodiment, the processor is configured to, when performing the determining whether the drug name and the drug attribute of the drug are the same as the standard drug name and the standard drug attribute according to the data dictionary, and performing naming standardization processing on the drug name and the drug attribute in the first target data and the second target data according to the determination result, perform:

comparing the drug name and the drug attribute of the drug with the name and the attribute of the standard drug with the Nth layer number in the tree structure, wherein N is a natural number greater than 0 and not greater than the total layer number of the tree structure;

and if the medicine name and the medicine attribute of the medicine are judged to be the same as the standard medicine name and the standard medicine attribute of the Nth layer of the tree structure, adding 1 to N if N is smaller than the total layer of the tree structure.

In one embodiment, the processor, in effecting acquiring the second target data, is configured to effect:

acquiring second target data from different data sources; or

And determining the second target data according to the first target data.

In one embodiment, the processor, in effecting determining the second target data from the first target data, is adapted to effect:

performing word segmentation on the drug name and the drug attribute of the drug in the first target data and extracting a plurality of keywords;

comparing keywords extracted from the drug names and the drug attributes of different drugs;

and determining the degree of association between the corresponding medicines according to the comparison result to obtain association information for indicating the degree of association between the medicines.

In one embodiment, the processor, when implementing a medication map-based drug query method, is configured to implement:

determining a weight value of a keyword in a drug name and/or a drug attribute of a drug;

when the determination of the association degree between the corresponding medicines according to the comparison result is realized, the method is used for realizing that:

and determining the association degree between corresponding medicines according to the keyword comparison results of the medicine names and/or the medicine attributes of different medicines and the weight values of the keywords to obtain association information for indicating the association degree between the medicines.

In one embodiment, the processor, in effecting determining a target drug from a query instruction based on the target medication profile, is configured to effect:

extracting the drug name and/or drug attribute keywords of the drug in the name attribute query instruction;

comparing the keywords in the target medicine atlas according to the keywords to determine the target medicine, or

When the processor implements the medicine map-based medicine query method, the processor is further configured to implement:

generating a medicine relation graph according to the relation query instruction;

and performing image comparison in the target medicine map according to the generated medicine relation map so as to determine the association information between the target medicine and the rest medicines in the target medicine map.

It should be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the medicine query based on the medicine atlas may refer to the corresponding process in the embodiment of the medicine query control method based on the medicine atlas, and details are not described herein again.

Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, where the computer program includes program instructions, and when the program instructions are executed, a method implemented by the computer program may refer to various embodiments of the medicine atlas-based medicine query method of the present application.

The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.

It is to be understood that the terminology used in the description of the present application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A medicine inquiry method based on a medicine atlas is characterized by comprising the following steps:

2. The method for querying drugs based on a medicine atlas of claim 1, wherein the naming normalization processing on the first target data to obtain normalized first data and the naming normalization processing on the second target data to obtain normalized second data based on the preset naming rules comprises:

3. The method of claim 2, wherein the tree structure comprises at least two levels;

the judging whether the drug name and the drug attribute of the drug are the same as the standard drug name and the standard drug attribute according to the data dictionary, and performing naming standardization processing on the drug name and the drug attribute in the first target data and the second target data according to the judging result includes:

4. The method of medicine atlas-based drug query of any of claims 1-3, where the obtaining second objective data comprises:

acquiring second target data from different data sources; or

And determining the second target data according to the first target data.

5. The method of claim 4, wherein the determining the second objective data from the first objective data comprises:

6. The method of claim 5, wherein the method further comprises:

determining the drug name of the drug and the weight value of the keyword in the drug attribute;

the determining the degree of association between the corresponding medicines according to the comparison result comprises:

and determining the association degree between corresponding medicines according to the keyword comparison results of the medicine names and the medicine attributes of different medicines and the weight values of the keywords to obtain association information for indicating the association degree between the medicines.

7. The method of any of claims 1-3, wherein the query comprises a name attribute query for indicating a name of the drug and an attribute of the drug to be determined, and wherein determining at least one drug in the target drug graph as the target drug according to the query comprises:

The query instructions include relationship query instructions for instructing the determination of association information between a target drug and remaining drugs in the target pharmaceutical profile, the method further comprising:

8. A medication order device, comprising:

a drug query module for determining at least one item in the target pharmaceutical profile as a target drug according to a query instruction,

9. A computer device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, performs the steps of the medication map based drug query method of any one of claims 1 to 7.

10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the medicine profile-based drug query method according to any one of claims 1 to 7.