Application method and device based on drug concept knowledge graph and electronic equipment

Abstract

The invention provides an application method and device based on a drug concept knowledge graph, and electronic equipment. The method comprises the following steps: constructing a drug directed acyclic graph based on a relationship between drugs; when the drug information is changed, determining a recommended drug list based on a drug directed acyclic graph; and performing medicine replacement based on the recommended medicine list. According to the invention, the service problems of clinical care in the aspects of medicine use and medicine execution can be quickly solved.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph technology, and in particular to an application method, device and electronic equipment based on a drug concept knowledge graph. Background Art

[0002] Although the number of drugs registered with the State Food and Drug Administration is huge (more than 190,000), the number of drugs used in hospitals each year basically remains at 4,000-5,000. According to the latest medical insurance catalog, the "2022 Drug Catalog" contains a total of 2,967 Western medicines and Chinese patent medicines, including 1,586 Western medicines and 1,381 Chinese patent medicines. In addition, there are 892 kinds of Chinese herbal medicines that can be paid for by the fund. Since 2018, relevant state departments have promoted the reform of volume-based procurement of drugs and high-value medical consumables with volume-based procurement as the core. After three years of efforts, the reform of centralized volume-based procurement has entered a new stage of normalization and institutionalization, and the amount involved accounts for 30% of the total annual drug procurement of public medical institutions.

[0003] Advances in the pharmaceutical industry have given doctors more options when facing diseases, and doctors will give priority to the use of drugs purchased in bulk in clinical practice. In clinical information systems, such as electronic medicine record systems (EMR), in order to standardize diagnosis and treatment and improve diagnosis and treatment efficiency, clinical pathways, medical order templates and other pre-made treatment measures are used for specific diseases or specific business scenarios. However, in the case of centralized procurement of drugs or inventory changes, there is a big difference between the pre-made diagnosis and treatment plans and the actual drug supply. In clinical practice, there will be business scenarios such as insufficient inventory of certain drugs, changing drug manufacturers, and giving priority to centralized procurement drugs. How can the clinical information system quickly respond to changes in these business scenarios? This is a very urgent business need. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide an application method, device and electronic device based on a drug concept knowledge graph to quickly solve the business problems of clinical medical care at the drug use and drug execution levels.

[0005] In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:

[0006] In the first aspect, an embodiment of the present invention provides an application method based on a drug concept knowledge graph, including: constructing a drug directed acyclic graph based on the relationship between drugs; when drug information changes, determining a recommended drug list based on the drug directed acyclic graph; and replacing drugs based on the recommended drug list.

[0007] In one embodiment, a directed acyclic graph of drugs is constructed based on the relationship between drugs, including: constructing a directed acyclic graph of drugs based on pharmacological classification, medical insurance classification, hospital classification, chemical name of drugs and trade name of drugs.

[0008] In one embodiment, a recommended drug list is determined based on a drug directed acyclic graph, including: based on the drug directed acyclic graph, using a depth-first search algorithm and / or a breadth-first search algorithm to find recommended drugs for drugs to be replaced, and sorting the recommended drugs according to their similarity with the drugs to be replaced to obtain a recommended drug list.

[0009] In one embodiment, based on a directed acyclic graph of drugs, a depth-first search algorithm is used to find recommended drugs for drugs to be replaced, including: determining an initial visited vertex based on the directed acyclic graph of drugs; traversing the directed acyclic graph of drugs by depth-first search starting from each unvisited adjacent point of the initial visited vertex in turn until all vertices in the directed acyclic graph of drugs connected to the initial visited vertex are visited, thereby obtaining recommended drugs for drugs to be replaced; if there are unvisited vertices in the directed acyclic graph of drugs, the unvisited vertices are used as the initial visited vertices, and the above steps are repeated until all vertices in the directed acyclic graph of drugs are visited.

[0010] In one embodiment, based on a directed acyclic graph of drugs, a breadth-first search algorithm is used to find recommended drugs for drugs to be replaced, including: obtaining a queue that stores node data of the directed acyclic graph of drugs; obtaining a node from the head of the queue, and determining whether the node can be expanded according to a preset expansion rule; if the node can be expanded, generating a new node; if the new node is not in the queue, adding the new node to the end of the queue, and determining whether the new node is the target node; if the new node is the target node, ending the search, otherwise, re-obtaining a node from the head of the queue and repeating the above steps.

[0011] In the second aspect, an embodiment of the present invention provides an application device based on a drug concept knowledge graph, including: a construction module, used to construct a drug directed acyclic graph based on the relationship between drugs; a recommendation module, used to determine a recommended drug list based on the drug directed acyclic graph when drug information changes; a replacement module, used to replace drugs based on the recommended drug list.

[0012] In one embodiment, the construction module is also used to: construct a directed acyclic graph of drugs based on the pharmacological classification, medical insurance classification, hospital classification, chemical name of the drugs, and trade name of the drugs.

[0013] In one embodiment, the recommendation module is also used to: based on the directed acyclic graph of drugs, use a depth-first search algorithm and / or a breadth-first search algorithm to find recommended drugs for the drugs to be replaced, and sort the recommended drugs according to their similarity with the drugs to be replaced to obtain a recommended drug list.

[0014] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the steps of any one of the methods provided in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods provided in the first aspect are executed.

[0016] The embodiments of the present invention bring the following beneficial effects:

[0017] The above-mentioned application method, device and electronic device based on the drug concept knowledge graph provided by the embodiment of the present invention first constructs a drug directed acyclic graph based on the relationship between drugs; then when the drug information changes, the recommended drug list is determined based on the drug directed acyclic graph; finally, the drug is replaced based on the recommended drug list. The above-mentioned method establishes a drug concept graph through a directed acyclic graph, and displays the manifestation of pharmaceutical objects based on the structured domain knowledge of the directed acyclic graph. When encountering changes in drug information such as drug discontinuation, out of stock, and change of manufacturer in clinical practice, the drug can be replaced according to the drug directed acyclic graph, thereby quickly solving the business problems of clinical medical care at the drug use and drug execution levels.

[0018] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A flowchart of an application method based on a drug concept knowledge graph provided by an embodiment of the present invention;

[0022] Figure 2 A directed acyclic graph of medicines provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of the structure of an application device based on a drug concept knowledge graph provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] With the promotion of policies such as the normalization of centralized procurement and medical insurance cost control, the pharmaceutical market is accelerating towards innovation; clinicians have more room to choose drugs when facing diseases. However, in clinical practice, business scenarios such as drug discontinuation, no inventory, and change of manufacturers are often encountered, especially under the normalization of centralized procurement. In the medical information system, how to more conveniently solve the needs of clinical medical care in the use and execution of drugs when there are changes in drugs has also become very urgent.

[0027] At present, in the drug dictionary, the commonly used method is to classify drugs according to two levels, such as the general layer of drugs and the commodity layer of drugs. Through the storage relationship of the drug dictionary, we can know that some drugs are in the same general layer, but the general layer is defined at the chemical level. The general layer of drugs to the medical insurance drug catalog, the general layer of drugs in different hospitals, the commodity layer and the medical insurance drug catalog are all established through mapping relationships.

[0028] The two levels of existing drugs are data maintained by the hospitals themselves. These data and the medical insurance drug catalog are established through mapping dictionaries. The drug dictionary established according to this model is all hospital data and can only be re-established through mapping before going online. Moreover, the drug level can only reach the general layer. Attributes above the general layer, such as the same variety, similar efficacy, etc., cannot be structured. When using this data in business, it is limited to the two-level attributes of these dictionaries.

[0029] Based on this, an application method, device and electronic device based on a drug concept knowledge graph provided by an embodiment of the present invention can quickly solve business problems of clinical medical care at the drug use and drug execution levels.

[0030] To facilitate understanding of this embodiment, firstly, an application method based on a drug concept knowledge graph disclosed in an embodiment of the present invention is introduced in detail. The method can be executed by an electronic device, such as a smart phone, a computer, a tablet computer, etc. Figure 1 The flowchart of an application method based on a drug concept knowledge graph is shown, indicating that the method mainly includes the following steps S101 to S103:

[0031] Step S101: construct a directed acyclic graph of drugs based on the relationship between drugs.

[0032] In one embodiment, a drug directed acyclic graph can be constructed based on the pharmacological classification, medical insurance classification, hospital classification, drug chemical name and drug trade name of the drug. Specifically, the drug ontology concepts are organized into a hierarchical tree from the pharmacological classification, medical insurance classification and hospital classification, drug chemical name, and drug trade name, and a graph relationship between drugs is established to construct a drug directed acyclic graph. In the embodiment of the present invention, the domain knowledge structured by the directed acyclic graph is used to display the representation of pharmaceutical objects, and the ontology directed acyclic graph is used to represent the nodes of the drug. In the ontology directed acyclic graph, the parent node represents a concept related to its children. The nodes in the directed acyclic graph provide a multi-dimensional view of medical concepts with different degrees of specificity. For all leaf nodes with the same parent node on the drug ontology hierarchical concept map, the similarity is set to 1, that is, they have the same attributes.

[0033] See also Figure 2 As shown in the figure, taking a tertiary hospital as an example, the drug data (including those in use and discontinued) stored in the drug library of the hospital currently totals 4,650, all of which are stored in the leaf nodes of the drug concept map. Taking Al-Mepirin Tablets as an example, there are 3 leaf nodes in total. Al-Mepirin Tablets 1 is a drug currently in use in the hospital, and the other two are drugs that have been used or will be used in the future, and they all have a common parent node.

[0034] Step S102: When drug information changes, a recommended drug list is determined based on the drug directed acyclic graph.

[0035] Step S103: Replace the medicine based on the recommended medicine list.

[0036] In one embodiment, when drug information changes, such as when insufficient drug inventory / drug discontinuation occurs during clinical pathway execution, recommended drugs for replacement drugs can be searched based on the drug directed acyclic graph. Specifically, after the clinician clicks the word "Change", a list of selectable drugs (i.e., a recommended drug list) will appear. There is a recommended ranking in the selectable drug list. The recommended ranking is determined based on the similarity of the nodes in the drug directed acyclic graph. The higher the degree of similarity, the higher the ranking, indicating that the similarity between these drugs and the current drugs to be replaced is higher. Therefore, the clinician can directly perform the drug change operation when the pathway is used.

[0037] The above-mentioned application method based on the drug concept knowledge graph provided by the embodiment of the present invention establishes a drug concept graph through a directed acyclic graph, and displays the expression form of pharmaceutical objects based on the structured domain knowledge of the directed acyclic graph. When encountering changes in drug information such as drug discontinuation, out of stock, or change of manufacturer in clinical practice, drugs can be replaced according to the drug directed acyclic graph, thereby quickly solving clinical medical care business problems at the drug use and drug execution levels.

[0038] In one embodiment, for the aforementioned step S102, that is, when determining a recommended drug list based on the drug directed acyclic graph, methods including but not limited to the following can be used: based on the drug directed acyclic graph, a depth-first search algorithm and / or a breadth-first search algorithm are used to find recommended drugs for the drugs to be replaced, and the recommended drugs are sorted according to their similarity with the drugs to be replaced to obtain a recommended drug list.

[0039] In specific implementation, the depth-first search algorithm includes: first, determining the initial visited vertex based on the drug directed acyclic graph; then, performing a depth-first search to traverse the drug directed acyclic graph starting from each unvisited adjacent point of the initial visited vertex in turn until all vertices in the drug directed acyclic graph connected to the initial visited vertex are visited, and the recommended drug to be replaced is obtained; if there are unvisited vertices in the drug directed acyclic graph, the unvisited vertex is used as the initial visited vertex, and the above steps are repeated until all vertices in the drug directed acyclic graph are visited.

[0040] Specifically, the recommended order can be determined based on a depth-first search algorithm. Assuming that the initial state is that all vertices in the directed acyclic graph have not been visited, starting from a certain vertex (i.e., the initial visit vertex), first visit the vertex, and then traverse the graph in depth-first search from each unvisited adjacent point of the initial visit vertex, until all vertices in the graph that are connected to the vertex by a path are visited. If there are still other vertices that have not been visited at this time, select another unvisited vertex as the starting visit vertex, and repeat the above process until all vertices in the graph have been visited. It should be noted that when traversing after selecting a starting point, move forward if you can, and if you cannot move forward, go back one step and then move forward, or go back one step and continue to move forward. Repeat this process until all vertices connected to the selected point have been traversed.

[0041] In specific implementation, the breadth-first search algorithm includes: first, obtaining a queue that stores node data of a directed acyclic graph of drugs; then, obtaining a node from the head of the queue, and determining whether the node can be expanded according to a preset expansion rule; if the node can be expanded, generating a new node; if the new node is not in the queue, adding the new node to the end of the queue, and determining whether the new node is the target node; if the new node is the target node, ending the search, otherwise, re-obtaining a node from the head of the queue and repeating the above steps.

[0042] Specifically, in the breadth-first search algorithm, the expansion of nodes on the solution tree is carried out according to their levels in the tree. First, the first-level nodes are generated, and at the same time, it is checked whether the target node is in the generated nodes. If not, all the first-level nodes are expanded one by one to obtain the second-level nodes, and it is checked whether the second-level nodes contain the target node, ..., before expanding any node at level n+1, every possible state of the nodes at level n must be considered. Therefore, for the same level of nodes, the value of solving the problem is the same, and they can be expanded in any order. The principle usually adopted is to expand the nodes generated first.

[0043] In order to facilitate the search, a table is set in this embodiment to store all nodes. Since the breadth-first search algorithm needs to satisfy the principle that the first generated nodes are expanded first, the table storing nodes can generally adopt a queue data structure.

[0044] The search steps of the breadth-first search algorithm generally include:

[0045] (1) Take a node from the head of the queue and check whether the node can be expanded according to the expansion rule. If it can be expanded, a new node is generated.

[0046] (2) Check whether the newly generated node already exists in the queue. If the new node has already appeared in the queue, abandon the node and return to step (1); if the new node has never appeared in the queue, add it to the end of the queue.

[0047] (3) Check whether the new node is the target node. If the new node is the target node, the search is successful and the program ends; if the new node is not the target node, return to step (1) and take out the node from the head of the queue for expansion.

[0048] There are two possible results: finding the target node, or expanding all nodes without finding the target node. If the target node exists on a finite layer of the solution tree, the breadth-first search algorithm can definitely find the best path to the target node, so the breadth-first search algorithm is particularly suitable for problems that only require the optimal solution. When the solution path needs to be given, it is necessary to save the source of each node, that is, which node the node is expanded from.

[0049] The above method provided by the embodiment of the present invention can be applied to business scenarios such as clinical pathway maintenance, medical order template maintenance, medical order template reference, and reminding doctors and nurses when the pharmacy changes drugs. For example: When maintaining the clinical pathway, in the pathway definition interface, batch verification can be performed to see if there are discontinued or out-of-stock drugs in the pathway, and then one-click replacement can be performed. Clinicians do not need to re-maintain pathways one by one, and work efficiency is more efficient. When maintaining and referencing medical order templates, discontinued / out-of-stock drugs can be directly replaced.

[0050] The above-mentioned application method based on the drug concept knowledge graph provided by the embodiment of the present invention establishes a drug concept graph through a directed acyclic graph. Based on the similarity of leaf nodes, when encountering business scenarios such as drug discontinuation, out of stock, and change of manufacturer in clinical practice, the medical order template can be deactivated / replaced with out-of-stock drugs, and the deactivated / out-of-stock drugs used in the clinical pathway can be replaced in the clinical information system. After the pharmacy updates the drug catalog, it is pushed to the business system such as the outpatient doctor station, the resident doctor station, the inpatient nurse station, etc. in real time, so as to quickly solve the business problems of clinical medical care at the drug use and drug execution levels.

[0051] For the application method based on the drug concept knowledge graph provided in the above embodiment, the embodiment of the present invention also provides an application device based on the drug concept knowledge graph, see Figure 3 The schematic diagram of the structure of an application device based on a drug concept knowledge graph is shown, indicating that the device mainly includes the following parts:

[0052] A construction module 301 is used to construct a directed acyclic graph of drugs based on the relationship between drugs;

[0053] A recommendation module 302, for determining a recommended drug list based on the drug directed acyclic graph when drug information changes;

[0054] The replacement module 303 is used to replace drugs based on the recommended drug list.

[0055] The above-mentioned application device based on the drug concept knowledge graph provided by the embodiment of the present invention establishes a drug concept graph through a directed acyclic graph, and displays the expression form of pharmaceutical objects based on the structured domain knowledge of the directed acyclic graph. When encountering changes in drug information such as drug discontinuation, out of stock, or change of manufacturer in clinical practice, drugs can be replaced according to the drug directed acyclic graph, thereby quickly solving clinical medical care business problems at the drug use and drug execution levels.

[0056] In one embodiment, the construction module 301 is also used to construct a directed acyclic graph of drugs based on the pharmacological classification, medical insurance classification, hospital classification, chemical name of the drugs and trade name of the drugs.

[0057] In one embodiment, the recommendation module 302 is also used to: based on the directed acyclic graph of drugs, use a depth-first search algorithm and / or a breadth-first search algorithm to find recommended drugs for drugs to be replaced, and sort the recommended drugs according to their similarity with the drugs to be replaced to obtain a recommended drug list.

[0058] In one embodiment, the recommendation module 302 is also used to: determine the initial visited vertex based on the drug directed acyclic graph; perform a depth-first search to traverse the drug directed acyclic graph starting from each unvisited adjacent point of the initial visited vertex in turn until all vertices in the drug directed acyclic graph connected to the initial visited vertex are visited, and obtain recommended drugs for the drugs to be replaced; if there are unvisited vertices in the drug directed acyclic graph, use the unvisited vertices as the initial visited vertex, and repeat the above steps until all vertices in the drug directed acyclic graph are visited.

[0059] In one embodiment, the recommendation module 302 is also used to: obtain a queue storing node data of a directed acyclic graph of drugs; obtain a node from the head of the queue and determine whether the node can be expanded according to a preset expansion rule; if the node can be expanded, generate a new node; if the new node is not in the queue, add the new node to the end of the queue and determine whether the new node is the target node; if the new node is the target node, end the search, otherwise, re-acquire a node from the head of the queue and repeat the above steps.

[0060] It should be noted that the implementation principle and technical effects of the device provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. The specific numerical values ​​provided in the implementation of the present invention are only exemplary and are not limited here.

[0061] An embodiment of the present invention further provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above implementation methods.

[0062] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present invention, the electronic device 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0063] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0064] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0065] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0066] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor to execute, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0067] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.

[0068] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0069] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An application method based on drug concept knowledge graph, It is characterized in that include: Construct a directed acyclic graph of drugs based on the relationship between drugs; When drug information changes, a recommended drug list is determined based on the drug directed acyclic graph; Drug replacement is performed based on the recommended drug list.

2. The method according to claim 1, It is characterized in that Construct a directed acyclic graph of drugs based on the relationship between drugs, including: A directed acyclic graph of drugs is constructed based on the pharmacological classification, medical insurance classification, hospital classification, drug chemical name and drug trade name.

3. The method according to claim 1, It is characterized in that Determining a recommended drug list based on the drug directed acyclic graph includes: Based on the drug directed acyclic graph, a depth-first search algorithm and / or a breadth-first search algorithm are used to find recommended drugs for the drugs to be replaced, and the recommended drugs are sorted according to their similarities with the drugs to be replaced to obtain a recommended drug list.

4. The method according to claim 3, It is characterized in that Based on the drug directed acyclic graph, a depth-first search algorithm is used to find recommended drugs for the drugs to be replaced, including: Determining an initial access vertex based on the drug directed acyclic graph; Performing a depth-first search from each unvisited adjacent point of the initial visit vertex in turn to traverse the drug directed acyclic graph until all vertices in the drug directed acyclic graph connected to the initial visit vertex are visited, thereby obtaining a recommended drug for the drug to be replaced; If there are unvisited vertices in the drug directed acyclic graph, the unvisited vertices are used as initial visited vertices, and the above steps are repeated until all vertices in the drug directed acyclic graph are visited.

5. The method according to claim 3, It is characterized in that Based on the drug directed acyclic graph, a breadth-first search algorithm is used to find recommended drugs for the drugs to be replaced, including: Obtaining a queue storing node data of the directed acyclic graph of the medicine; Obtain a node from the queue head, and determine whether the node can be expanded according to a preset expansion rule; If the node can be expanded, a new node is generated; If the new node is not in the queue, the new node is added to the end of the queue, and it is determined whether the new node is a target node; If the new node is the target node, the search is terminated; otherwise, a new node is obtained from the head of the queue and the above steps are repeated.

6. An application device based on drug concept knowledge graph, It is characterized in that include: A construction module for constructing a directed acyclic graph of drugs based on the relationships between drugs; A recommendation module, used for determining a recommended drug list based on the drug directed acyclic graph when drug information changes; A replacement module is used to replace drugs based on the recommended drug list.

7. The device according to claim 6, It is characterized in that The building blocks are also used to: A directed acyclic graph of drugs is constructed based on the pharmacological classification, medical insurance classification, hospital classification, drug chemical name and drug trade name.

8. The device according to claim 6, It is characterized in that The recommendation module is also used to: Based on the drug directed acyclic graph, a depth-first search algorithm and / or a breadth-first search algorithm are used to find recommended drugs for the drugs to be replaced, and the recommended drugs are sorted according to their similarities with the drugs to be replaced to obtain a recommended drug list.

9. An electronic device, It is characterized in that The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are executed.

Images