WO2021238436A1 - 多药共用查询方法、移动终端及存储介质 - Google Patents
多药共用查询方法、移动终端及存储介质 Download PDFInfo
- Publication number
- WO2021238436A1 WO2021238436A1 PCT/CN2021/086133 CN2021086133W WO2021238436A1 WO 2021238436 A1 WO2021238436 A1 WO 2021238436A1 CN 2021086133 W CN2021086133 W CN 2021086133W WO 2021238436 A1 WO2021238436 A1 WO 2021238436A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- query
- graph
- node
- drug
- subgraph
- Prior art date
Links
- 229940079593 drug Drugs 0.000 title claims abstract description 141
- 239000003814 drug Substances 0.000 title claims abstract description 141
- 238000000034 method Methods 0.000 title claims abstract description 62
- 201000010099 disease Diseases 0.000 claims description 43
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 43
- 230000015654 memory Effects 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 description 13
- 206010067484 Adverse reaction Diseases 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 7
- 230000006838 adverse reaction Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 6
- 208000017667 Chronic Disease Diseases 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000002483 medication Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 206010013710 Drug interaction Diseases 0.000 description 1
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 description 1
- 230000007012 clinical effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000010534 mechanism of action Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000002547 new drug Substances 0.000 description 1
- 239000000820 nonprescription drug Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 229940126680 traditional chinese medicines Drugs 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G06F16/319—Inverted lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3322—Query formulation using system suggestions
- G06F16/3323—Query formulation using system suggestions using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3338—Query expansion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H20/13—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered from dispensers
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Definitions
- This application relates to the field of medical technology, in particular to a multi-drug sharing query method, a mobile terminal and a storage medium.
- the embodiments of the present application provide a multi-drug sharing query method, a mobile terminal, and a computer-readable storage medium.
- This application provides a multi-drug sharing query method, and the multi-drug sharing query method includes:
- the query conditions include drug information and disease information
- the step of constructing a query graph according to the query conditions includes:
- the query graph is constructed according to the drug information and disease information.
- the step of segmenting the query graph to obtain multiple query subgraphs includes:
- the central query node and the adjacent query nodes of the central query node are divided into a query subgraph.
- the step of querying the knowledge graph based on the multiple query subgraphs and returning the medication query result includes:
- the processing cost of the query subgraph in the search space is calculated to determine the query plan of the query graph.
- the step of calculating the processing cost of the query subgraph in the search space to determine the query plan of the query graph includes:
- the query plan is determined according to the sorting results of the processing costs of the multiple query subgraphs.
- the step of calculating the processing cost of the query subgraph in the search space to determine the query plan of the query graph includes:
- the predicate inverted index of the nodes of the knowledge graph is established to compress the search space.
- the step of establishing the inverted index of the predicate of the node of the knowledge graph to compress the search space includes:
- the search space is compressed based on the result of matching the incoming and/or outgoing predicate structure of the query node in the query graph with the predicate inverted index of the node of the knowledge graph.
- the step of calculating the processing cost of the query subgraph in the search space to determine the query plan of the query graph includes:
- the query sequence of the query subgraph is determined according to the query plan.
- the step of determining the query sequence of the query subgraph according to the query plan includes:
- the query order of the query node is determined according to the sorting result.
- the step of determining the query order of the query node according to the sorting result includes:
- the result set is returned as the medication query result.
- the step of returning the result set as the medication query result includes:
- the step of filtering the result set to obtain accurate query results includes:
- This application provides a mobile terminal, including one or more processors, a memory; and one or more programs, wherein the one or more programs are stored in the memory and are used by the one or more
- the processor executes, and the program includes instructions for executing the multi-drug sharing query method as described above.
- the present application provides a non-volatile computer-readable storage medium containing computer-executable instructions.
- the processor is caused to execute the multi-drug Shared query method.
- the multi-drug sharing query method, mobile terminal, and computer-readable storage medium of the embodiment of the present application a large amount of disease drug data and the complexity between them are managed through a knowledge map, and the query conditions are constructed into a query graph, and the query graph is used Searching in the data graph of the knowledge graph effectively solves the problems that may be faced by elderly patients in complex and multi-disease coexistence and multi-drug sharing scenarios. By dividing the query graph into query subgraphs, the efficiency of query processing is improved.
- Fig. 1 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- Fig. 2 is a schematic diagram of modules of a multi-drug sharing query device according to some embodiments of the present application.
- Fig. 3 is a schematic diagram of the knowledge graph of some embodiments of the present application.
- Fig. 4 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- Fig. 5 is a schematic flow chart of a multi-drug sharing query method according to some embodiments of the present application.
- Fig. 6 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- FIG. 7 is a schematic flowchart of a method for querying multiple drugs sharing in some embodiments of the present application.
- FIG. 8 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- FIG. 9 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- FIG. 10 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application
- FIG. 11 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- FIG. 12 is a schematic flowchart of a multi-drug sharing query method according to some embodiments of the present application.
- FIG. 13 is an interactive schematic diagram of a multi-drug sharing query method according to some embodiments of the present application.
- This application provides a multi-drug sharing query method.
- an embodiment of the present application provides a mobile terminal.
- the mobile terminal includes a processor.
- the processor is used to construct a query graph according to query conditions, to segment the query graph to obtain multiple query subgraphs, and to query the knowledge graph based on the multiple query subgraphs and return medication query results.
- the mobile terminal can be a consumer electronic device such as a mobile phone, a tablet computer, a personal computer, or a smart medical diagnostic device, which is not limited here.
- the embodiment of the present application also provides a multi-drug sharing query device 110.
- the multi-drug sharing query method of the embodiment of the application can be implemented by the multi-drug sharing query device 110 of the embodiment of the application.
- the multi-drug sharing query device 110 includes a query graph construction module 112, a segmentation module 114, and a query module 116.
- S10 can be implemented by the query graph construction module 112
- S20 can be implemented by the segmentation module 114
- S30 can be implemented by the query module 116.
- the query graph construction module 112 is used to construct a query graph according to query conditions.
- the segmentation module 114 is used to segment the query graph to obtain multiple query subgraphs.
- the query module 116 is configured to query the knowledge graph according to multiple query subgraphs and return the medication query results.
- the massive disease drug data and the complexity between them are managed through knowledge graphs, the query conditions are constructed into a query graph, and the query graph is used Searching in the data graph of the knowledge graph effectively solves the problems that may be faced by elderly patients in complex and multi-disease coexistence and multi-drug sharing scenarios.
- the efficiency of query processing is improved.
- multi-drug sharing refers to the simultaneous use of multiple drugs for the same patient to treat one or more diseases.
- a considerable number of elderly patients have multiple chronic diseases, such as three or more. Because every disease requires one or several drugs for treatment, and because the treatment process of chronic diseases is longer, the treatment effect is not obvious, and the recovery cycle is slow, so in the process of medication, elderly patients are more likely to have psychological problems.
- Fluctuations in the state may result in the following behaviors: collecting "earth recipes” and "secret recipes from ancestors” for the treatment of related diseases; following the propaganda of drug advertisements, or being influenced by patients, friends or colleagues, not following the doctor's instructions, and blindly adding Medicines, such as adding new medicines, traditional Chinese medicines, and over-the-counter medicines without knowing the pharmacology; buying health care products without choosing.
- multi-drug sharing analysis involves expression of complex relationships such as disease-disease, disease-drug, drug-drug, drug-component, etc.
- knowledge can be constructed by domain experts and case data-driven methods. Graphs, and manage and organize these complex relationships through graphs. It can be understood that, compared with the path and tree structure, the graph is more able to express complex structure information, and at the same time facilitates the management and expansion of massive heterogeneous data.
- the problem of multi-drug sharing is transformed into a problem of query graph matching in the graph data of the knowledge graph. Quickly analyze the relationship path in the knowledge map, so as to help medical staff to more clearly analyze the complex multi-drug sharing factors in the treatment and life of elderly patients, deal with drug interactions and adverse reactions more accurately, and formulate effective for elderly patients , Safe and personalized medication plan.
- multi-drug sharing is not limited to whether there is a relationship between simple drugs and drugs, but also comprehensively consider whether the drug path satisfies various rule constraints.
- complex multi-attribute queries have more advantages. Practical meaning. For example: whether there is a significant interaction between drugs, whether there is a drug-disease interaction with a significant clinical effect, whether the drug has indications, whether the drug has contraindications, whether the drug dosage is correct, whether there is repeated medication, and whether the drug treatment time Reasonable, compared with equivalent alternative drugs, whether the selected drug is economical, etc.
- the disease-drug knowledge graph can be constructed by medical workers in various disease fields based on prior knowledge such as existing drug knowledge and experience and existing formulary as basic information.
- the knowledge graph can include the following knowledge relationships: the pharmacology of the drug itself, dosage, route of administration, mechanism of action, adverse reactions, uses, contraindicated foods, etc., drug-drug mutual rental, compatibility contraindications, etc., the relationship between drugs and symptoms The adaptability, contraindications, the relationship between symptoms and diseases, and adverse reactions between diseases and drugs.
- the knowledge graph includes a data resource layer, a logical relationship layer, and a node method layer.
- the data resource layer includes clinical pathways, drug instructions, interactions, and/or related educational resources.
- the logic layer integrates the data resource layer and experience knowledge.
- the node display layer is used to display the knowledge relationship in a graph, and users can explore the knowledge network.
- the process of constructing a knowledge graph generally includes the steps of knowledge representation, extraction, fusion, reasoning, and quality.
- the specific method can refer to the related technology of knowledge graph construction, which will not be repeated here.
- the constructed data graph of the pharmacy knowledge graph can be represented by the following relational expression:
- V is the set of nodes in the data graph
- E is the set of edges in the data graph
- doctors or patients input medicines, combined with the patient's disease, body examination and other information obtained through the hospital information system or electronic medical records, and construct a query map with this information, which can obtain more comprehensive information through the knowledge map query.
- the method of constructing the query graph for query in the knowledge graph is more efficient than extracting each single information of the patient to search in the knowledge graph. Understandably, using single information to query the knowledge map may obtain a large amount of information and contain redundant information that the patient does not need. However, the redundant information cannot be screened, and manual identification and selection are still required, and there are risks. In addition, when inquiring, there are more patients' information that needs to be inquired. Inquiring one by one is time-consuming and low in efficiency.
- the missing nodes and/or relationships can be completed first, and the completed graph If there are interactions between certain drugs in the structure, there will be corresponding directions between the nodes representing the drugs in the graph.
- designated relationship queries such as designated interactions, bad taboos, and other relationships. In this way, the obtained query result graph is a more comprehensive and complete comprehensive analysis of the patient.
- the process of medication query is actually the process of matching the query graph in the data graph, and the subgraph in the data graph that matches the structure of the query graph is also the result of the medication query.
- the search range of the data needs to be re-determined, that is, the search space, or the search space needs to be compressed to make the query faster.
- each query node in the query graph may have multiple matching nodes in the data graph, and it will be cumbersome to match the query graph as a whole with the data graph.
- the query graph is divided into multiple query subgraphs with simple structures, and the search space of each query subgraph is further narrowed by matching the query subgraph with the data graph.
- the query conditions include drug information and disease information
- S10 includes:
- S11 Construct a query graph based on drug information and disease information.
- S11 can be implemented by the query graph construction module 112, that is, the query graph construction module 114 can be used to construct a query graph based on drug information and disease information.
- the processor is used to construct a query graph based on drug information and disease information.
- the query graph can be represented by the following relational expression:
- V Q represents the set of nodes in the query graph, Represents the set of directed edges connecting two nodes.
- A is the label set of nodes and edges in the query graph, I Q is the mapping function, and vars represents the set of variables in the graph.
- the inquirer that is, the patient or doctor, enters information such as his own disease, current medications, etc.
- the processor constructs the query graph according to the input information, and matches the query graph with the knowledge graph.
- Multi-drug sharing query The entered diseases and drugs can be used as nodes in the query graph, and the drug-drug, drug-disease, and disease-disease relationships can be used as the edges of the query graph.
- the query map can also be created previously and retrieved from the background via user selection input, which is not limited here.
- S20 includes:
- S21 and S22 can be implemented by the segmentation module 114.
- the segmentation module 114 is used to select the central query node and to divide the central query node and the adjacent query nodes of the central query node into A query subgraph.
- the segmentation of the query subgraph needs to follow the principle of center covering nodes. Specifically, when a node has an out-degree and an in-degree, it can be considered that the node is the central query node, and the node and the neighboring nodes of the node are divided into a query subgraph. If the two neighboring nodes and the center query If the nodes form a closed graph, the query subgraph includes the graph. For example, for a node V, if the node V makes the edges from the node to other nodes in the query subgraph all in the query subgraph, the node V is the central query node. It should be noted that in the segmentation process, any edge in the query graph must be covered by at least one query subgraph.
- the central covering node is the central query node of the query subgraph, so as to ensure that the segmented query subgraph can cover all Query graph.
- V2 and V4 are the central query nodes.
- the above query graph can be The subgraph is divided into two query subgraphs: V1 ⁇ V2 ⁇ V3, V3 ⁇ V4 ⁇ V5.
- the search space changes from the nodes in the data graph corresponding to the query graph and the relationship between the nodes to the nodes and the relationship between the nodes in the data graph corresponding to the query subgraph, and the search space is compressed .
- S30 includes:
- S31 Calculate the processing cost of the query subgraph in the search space to determine the query plan of the query graph.
- S31 may be implemented by the query module 116, that is, the query module 116 is used to calculate the processing cost of the query subgraph in the search space to determine the query plan of the query graph.
- the processor is used to calculate the processing cost of the query subgraph in the search space to determine the query plan of the query graph.
- the basic unit of processing cost is each query subgraph, and the efficiency of query subgraph matching will affect the overall efficiency of the query.
- a query graph it contains 3 central query nodes, which are divided into 3 query subgraphs. Therefore, there are six kinds of query sequences for querying subgraphs, and the processing cost of each sequence is different.
- S31 includes:
- S311 Calculate the query cost of each node to be queried in the query subgraph
- S312 Calculate the connection cost of each query node in the query subgraph according to the query cost to determine the processing cost
- S313 Determine the query plan according to the sorting results of the processing costs of the multiple query subgraphs.
- S311-S313 can be implemented by the query module 116, that is, the query module 116 is used to calculate the query cost of each node to be queried in the query subgraph, and to calculate the query sub-graph based on the query cost.
- the connection cost of each query node in the graph determines the processing cost and is used to determine the query plan according to the sorting result of the processing cost of multiple query subgraphs.
- the processor is used to calculate the query cost of each node to be queried in the query sub-graph, and to calculate the connection cost of each query node in the query sub-graph based on the query cost to determine the processing cost and to determine the processing cost.
- the sorting result of the processing cost of each query subgraph determines the query plan.
- the cost of each node to be queried is first calculated.
- the cost of the node to be queried is also the number of nodes matching the query node in the search space and the query subgraph where the query node is located. The ratio of the total number of query nodes in the graph.
- connection cost of each node to be queried in the query subgraph is calculated, that is, the cost of a single node is multiplied or added.
- the connection cost has an impact factor, which can be set according to whether there is a common node with other query subgraphs. In this way, the processing cost of the query subgraph is calculated, and the optimal query plan of the query graph can be further obtained.
- querying through the relationship of nodes can quickly match the data graph, and the query efficiency can be improved.
- the optimal query plan of the query graph can be obtained by calculating the processing cost of the query subgraph.
- the cost can be selected from low to high, that is, from easy to difficult.
- S31 includes:
- S314 Establish a predicate inverted index of the nodes of the knowledge graph to compress the search space.
- S314 can be implemented by the query module 116.
- the query module 116 is used to build the predicate inverted index of the nodes of the knowledge graph to compress the search space.
- the processor is used to build the predicate inverted index of the nodes of the knowledge graph to compress the search space.
- the predicate that is, the relationship
- the inverted list of nodes based on the incoming and outgoing predicate structure respectively.
- the query nodes in the query graph can be filtered, and finally the nodes that match the structure of the query graph are obtained.
- judging whether the structure of the node is the same can be achieved by judging whether the structure of the predicate passed in and out of the node is the same.
- a data graph For example, for a data graph, it contains predicates p1, p2, p3, and the data graph contains nodes v1-v18. According to its data graph structure, establish an inverted list of nodes based on the structure of incoming and outgoing predicates:
- the nodes in the data graph and the relationship between the nodes are complex, and the number of predicates is less than the number of nodes, so an inverted list based on the predicate structure can be established.
- Establishing an inverted list can quickly locate the node in the data graph corresponding to the predicate structure of the query node in the list, thereby compressing the search space.
- S314 includes:
- S3141 Compress the search space based on the result of matching the incoming and/or outgoing predicate structure of the query node in the query graph with the predicate inverted index of the node of the knowledge graph.
- S3141 may be implemented by the query module 116.
- the query module 116 is configured to compress the search space based on the result of matching the incoming and/or outgoing predicate structure of the query node in the query graph with the predicate inverted index of the node of the knowledge graph.
- the processor is configured to compress the search space based on the result of matching the incoming and/or outgoing predicate structure of the query node in the query graph with the predicate inverted index of the node of the knowledge graph.
- the corresponding node set is (v1, v2, v4, v8), and based on the outgoing predicate structure, there are predicate p1 in the data graph.
- the set of nodes is (v1, v5, v6, v7, v8). So, is there a query node in the query graph? V, which has an incoming predicate structure p and an outgoing predicate structure p1, so the query node? V can find the search space S1 (p1
- the nodes that match V are v1 and v8.
- S31 further includes:
- S315 Determine the query sequence of the query subgraphs according to the query plan.
- S315 can be implemented by the query module 116.
- the query module 116 is used to determine the query order of query subgraphs according to the query plan.
- the processor is used to determine the query order of the query subgraphs according to the query plan.
- the query order can be obtained after the query plan is determined, and each query subgraph is queried in the search space according to the query order.
- the query graph is divided into multiple query subgraphs.
- the query can be sorted according to the number of nodes and edges in each query subgraph, and the query order can be determined according to the number of sorting results.
- executing the query according to the query sequence can ensure that the query action conforms to a certain logical sequence, so that the query result can be returned quickly without repetition and omission.
- S315 further includes:
- S3151 Sort the number of nodes with the same predicate structure in the query graph for each query node in the current query subgraph;
- S3152 Determine the query order of the query node according to the sorting result.
- S33-S34 can be implemented by the query module 116.
- the query module 116 is used to sort the number of nodes with the same predicate structure of each query node in the query graph in the current query subgraph, and used to determine the query order of the query nodes according to the sorting result.
- the processor is used to sort the number of nodes with the same predicate structure in the query graph of each query node in the current query subgraph, and is used to determine the query order of the query nodes according to the sorting result.
- the query node with the least number of nodes with the same structure after each query node in the current query subgraph is matched by the predicate structure is used as the currently processed query node.
- the number of nodes with the same structure of each query node can be sorted, and the query order of the query nodes can be determined according to the sorting result of the number of nodes with the same structure, for example, from less to more.
- other query sequences are also possible, which are not limited here.
- S3152 further includes:
- S31521 Obtain the matching node of the query node and the predicate structure of the matching node in the search space according to the query order of the query node and store it in the result set;
- S35 and S36 can be implemented by the query module 116.
- the query module 116 is configured to obtain the matching nodes of the query nodes and the associated nodes of the matching nodes in the search space according to the query order of the query nodes and store them in the result set, and to return the result set as the medication query result.
- the processor is used to obtain the matching node of the query node and the associated node of the matching node in the search space according to the query order of the query node and store them in a result set, and to return the result set as a medication query result.
- the matching nodes of the current query node can be obtained from the corresponding search space, that is, the matching node of the current query node in the search space
- the nodes with the same predicate structure are stored in the result set, and the nodes associated with the predicate structure of the matching node are also put into the result set, thereby expanding the query graph.
- information such as diseases and drugs can be regarded as nodes in the query subgraph.
- the relationship between two nodes, such as the relationship between two drugs, the relationship between drugs and diseases, etc., can be seen Action is the edge of the query subgraph, which is the predicate structure.
- Searching for matching nodes and associated nodes of query nodes in the search space can be regarded as simple information such as diseases and medicines input.
- the knowledge graph the content related to the input information is improved, that is, a simple query is used
- the subgraph is used to query the graph to match the data graph content with a complex structure, including returning more nodes and the expansion of associated nodes, so as to provide users with more comprehensive and accurate guidance.
- a matching node with a consistent structure and associated nodes of the matching node are obtained from the search space.
- the query results of each query subgraph are stored in the result set, so that the result set contains matching nodes and associated nodes of each query node.
- the result set is returned to the inquirer as the final medication query result.
- the processor may process the returned result set, and draw an icon of the graph structure corresponding to the result set according to the relationship between the node and the predicate, and display it to the queryer.
- the user enters disease 1, disease 2, drug 1, drug 2, and after querying, returns the contraindications of drug 2, the compatibility between drug 1 and drug 2, drug 3 for treating disease 2, drug 3 and drug 1
- the interaction between the two, etc. to provide users with more information about diseases and medications.
- S31522 includes:
- this step can be implemented by the query module 116.
- the query module 116 is used to filter the result set to obtain accurate query results.
- the processor is used to filter the result set to obtain accurate query results.
- this step further includes sub-steps:
- this sub-step may be implemented by the query module 116.
- the query module 116 is used to filter duplicate nodes in the result set according to the knowledge graph and the query graph to obtain accurate query results.
- the processor is used to filter duplicate nodes in the result set according to the knowledge graph and the query graph to obtain accurate query results.
- the complex graph data can be quickly searched for results that meet the query request, which can make the response speed and efficiency faster without losing data information. higher.
- the precision and recall will be greatly improved, and because the knowledge graph has semantics, attribute information and description logic, the query results can have a clear explanation and reasoning path.
- the embodiment of the present application also provides a computer-readable storage medium.
- One or more non-volatile computer-readable storage media containing computer-executable instructions when the computer-executable instructions are executed by one or more processors, cause the processors to execute the multi-drug sharing query method of any of the above embodiments .
- the embodiment of the present application also provides a mobile terminal.
- the mobile terminal includes one or more memories and one or more processors, and one or more programs are stored in the memory and configured to be executed by the one or more processors.
- the program includes a method for executing the multi-drug sharing query described in any one of the above implementations.
- the processor can be used to provide computing and control capabilities to support the operation of the entire mobile terminal.
- the memory in the mobile terminal provides an environment for the operation of computer-readable instructions in the memory.
- the program can be stored in a non-volatile computer-readable storage medium. During execution, it may include the processes of the above-mentioned method embodiments.
- the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), etc.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
Claims (14)
- 一种多药共用查询方法,其特征在于,包括以下步骤:根据查询条件构建查询图;切分所述查询图以得到多个查询子图;和根据所述多个查询子图在知识图谱中进行查询并返回用药查询结果。
- 根据权利要求1所述的多药共用查询方法,其特征在于,所述查询条件包括药物信息和疾病信息,所述根据查询条件构建查询图的步骤包括:根据所述药物信息和疾病信息构建所述查询图。
- 根据权利要求1所述的多药共用查询方法,其特征在于,所述切分所述查询图以得到多个查询子图的步骤包括:选取中心查询节点;将所述中心查询节点及所述中心查询节点的相邻查询节点划分为一个查询子图。
- 根据权利要求1所述的多药共用查询方法,其特征在于,所述根据所述多个查询子图在知识图谱中进行查询并返回用药查询结果的步骤包括:计算所述查询子图在搜索空间中的处理代价以确定所述查询图的查询计划。
- 根据权利要求4所述的多用共用查询方法,其特征在于,所述计算所述查询子图在搜索空间中的处理代价以确定所述查询图的查询计划的步骤包括:计算所述查询子图中每个待查询节点的查询代价;根据所述查询代价计算所述查询子图中各个查询节点的连接代价以确定所述处理代价;根据多个所述查询子图的处理代价的排序结果确定所述查询计划。
- 根据权利要求4所述的多药共用查询方法,其特征在于,所述计算所述查询子图在搜索空间中的处理代价以确定所述查询图的查询计划的步骤包括:建立所述知识图谱的节点的谓词倒排索引以对所述搜索空间进行压缩。
- 根据权利要求6所述的多药共用查询方法,其特征在于,所述建立所述知识图谱的节点的谓词的倒排索引对所述搜索空间进行压缩的步骤包括:基于所述查询图中的查询节点的传入和/或传出谓词结构与所述知识图谱的节点的谓词倒排索引进行匹配的结果对所述搜索空间进行压缩。
- 根据权利要求4所述的多药共用查询方法,其特征在于,所述计算所述查询子图在搜索空间中的处理代价以确定所述查询图的查询计划的步骤包括:根据所述查询计划确定所述查询子图的查询顺序。
- 根据权利要求8所述的多药共用查询方法,其特征在于,所述根据所述查询计划确定所述查询子图的查询顺序的步骤包括:对当前查询子图中各查询节点在所述查询图中谓词结构一致的节点数目进行排序;根据所述排序的结果确定所述查询节点的查询顺序。
- 根据权利要求9所述的多药共用查询方法,其特征在于,所述根据所述排序的结果确定所述查询节点的查询顺序的步骤包括:根据所述查询节点的查询顺序在所述搜索空间中获取所述查询节点的匹配节点及所述匹配节点的关联节点并存储在结果集中;以所述结果集作为所述用药查询结果返回。
- 根据权利要求10所述的多药共用查询方法,其特征在于,所述以所述结果集作为所述用药查询结果返回的步骤包括:对所述结果集进行过滤处理,以得到精确查询结果。
- 根据权利要求11所述的多药共用查询方法,其特征在于,所述对所述结果集进行过滤处理以得到精确查询结果的步骤包括:根据所述知识图谱和所述查询图过滤所述结果集中的重复节点以得到精确查询结果。
- 一种移动终端,其特征在于,包括:一个或多个处理器、存储器;和一个或多个程序,其中所述一个或多个程序被存储在所述存储器中,并且被所述一个或多个处理器执行,所述程序包括用于执行根据权利要求1-12任意一项所述的多药共用查询方法的指令。
- 一种计算机可执行指令的非易失性计算机可读存储介质,其特征在于,当所述计算机可执行指令被一个或多个处理器执行时,使得所述处理器执行权利要求1-12中任一项所述的多药共用查询方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010474272.0 | 2020-05-29 | ||
CN202010474272.0A CN113742443A (zh) | 2020-05-29 | 2020-05-29 | 多药共用查询方法、移动终端及存储介质 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021238436A1 true WO2021238436A1 (zh) | 2021-12-02 |
Family
ID=78724573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/086133 WO2021238436A1 (zh) | 2020-05-29 | 2021-04-09 | 多药共用查询方法、移动终端及存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113742443A (zh) |
WO (1) | WO2021238436A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114255885A (zh) * | 2021-12-14 | 2022-03-29 | 浙江创邻科技有限公司 | 一种基于图数据的新药研发管理***及方法 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114625811B (zh) * | 2022-05-16 | 2022-08-23 | 支付宝(杭州)信息技术有限公司 | 一种提高子图匹配效率的方法和*** |
CN115842684B (zh) * | 2023-02-21 | 2023-05-12 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | 一种基于mdata子图匹配的多步攻击检测方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090179A (zh) * | 2017-12-15 | 2018-05-29 | 北京海致星图科技有限公司 | 一种Spark并发子图查询的方法 |
CN109918489A (zh) * | 2019-02-28 | 2019-06-21 | 上海乐言信息科技有限公司 | 一种多策略融合的知识问答方法和*** |
CN110347846A (zh) * | 2019-07-15 | 2019-10-18 | 苏州工业职业技术学院 | 有时间约束的非连通知识图谱查询方法 |
US20200135314A1 (en) * | 2018-10-29 | 2020-04-30 | Pharmazam, LLC | Personalized medication management and alert system and method |
CN111192654A (zh) * | 2019-12-30 | 2020-05-22 | 北京左医健康技术有限公司 | 基于知识图谱的用药指导查询方法及装置 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180144424A1 (en) * | 2016-11-18 | 2018-05-24 | Yen4Ken, Inc. | Method and system for content processing to query multiple healthcare-related knowledge graphs |
CN108052547B (zh) * | 2017-11-27 | 2019-09-27 | 华中科技大学 | 基于问句和知识图结构分析的自然语言问答方法及*** |
-
2020
- 2020-05-29 CN CN202010474272.0A patent/CN113742443A/zh active Pending
-
2021
- 2021-04-09 WO PCT/CN2021/086133 patent/WO2021238436A1/zh active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108090179A (zh) * | 2017-12-15 | 2018-05-29 | 北京海致星图科技有限公司 | 一种Spark并发子图查询的方法 |
US20200135314A1 (en) * | 2018-10-29 | 2020-04-30 | Pharmazam, LLC | Personalized medication management and alert system and method |
CN109918489A (zh) * | 2019-02-28 | 2019-06-21 | 上海乐言信息科技有限公司 | 一种多策略融合的知识问答方法和*** |
CN110347846A (zh) * | 2019-07-15 | 2019-10-18 | 苏州工业职业技术学院 | 有时间约束的非连通知识图谱查询方法 |
CN111192654A (zh) * | 2019-12-30 | 2020-05-22 | 北京左医健康技术有限公司 | 基于知识图谱的用药指导查询方法及装置 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114255885A (zh) * | 2021-12-14 | 2022-03-29 | 浙江创邻科技有限公司 | 一种基于图数据的新药研发管理***及方法 |
Also Published As
Publication number | Publication date |
---|---|
CN113742443A (zh) | 2021-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021238436A1 (zh) | 多药共用查询方法、移动终端及存储介质 | |
WO2020147758A1 (zh) | 药品的推荐方法、装置、介质和电子设备 | |
US8290923B2 (en) | Performing large scale structured search allowing partial schema changes without system downtime | |
US20070005621A1 (en) | Information system using healthcare ontology | |
US11495330B2 (en) | Neurological data processing | |
EP2989561A1 (en) | Database management system | |
CN115497631A (zh) | 一种临床科研大数据分析*** | |
Wong et al. | Interactive visualization for information analysis in medical diagnosis | |
Zhou et al. | Clinical decision support system for hypertension medication based on knowledge graph | |
Rojas et al. | Characterization of drug use patterns using process mining and temporal abstraction digital phenotyping | |
Liu et al. | Controlled vocabularies in OODBs: Modeling issues and implementation | |
Baglioni et al. | A new framework for distilling higher quality information from health data via social network analysis | |
Gotz et al. | Multifaceted visual analytics for healthcare applications | |
Liu et al. | PatientEG dataset: bringing event graph model with temporal relations to electronic medical records | |
Giménez-Solano et al. | Definition and validation of SNOMED CT subsets using the expression constraint language | |
JP6868860B2 (ja) | 知識管理システム | |
US7657417B2 (en) | Method, system and machine readable medium for publishing documents using an ontological modeling system | |
Malik et al. | An integrated modular approach for visual analytic systems in electronic health records | |
Zolotarev et al. | Analysis of the impact of economic sanctions on health research and publication activities of scientists from Iran | |
Pocco et al. | Exploring scientific literature by textual and image content using DRIFT | |
Karozos et al. | Integrating clinical data from hospital databases. | |
Jiang et al. | A Proposed Method of Literature Analysis Based on Natural Language Processing and Network Analysis | |
Rajabi et al. | Building a disease knowledge graph | |
Zakharchenko et al. | Auditing of SNOMED CT's Hierarchical Structure using the National Drug File-Reference Terminology | |
Xiong et al. | Study on taboo knowledge map of Chinese patent medicine compatibility |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21811915 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21811915 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 23/06/2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21811915 Country of ref document: EP Kind code of ref document: A1 |