CN116959731A - Medical information processing method, device, equipment and storage medium - Google Patents
Medical information processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116959731A CN116959731A CN202211429239.1A CN202211429239A CN116959731A CN 116959731 A CN116959731 A CN 116959731A CN 202211429239 A CN202211429239 A CN 202211429239A CN 116959731 A CN116959731 A CN 116959731A
- Authority
- CN
- China
- Prior art keywords
- candidate
- resource
- resources
- subgraph
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 29
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000010586 diagram Methods 0.000 claims abstract description 197
- 239000011159 matrix material Substances 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 37
- 201000010099 disease Diseases 0.000 claims description 28
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 6
- 238000002560 therapeutic procedure Methods 0.000 claims 1
- 238000005065 mining Methods 0.000 abstract description 6
- 238000003745 diagnosis Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 206010020751 Hypersensitivity Diseases 0.000 description 2
- 208000026935 allergic disease Diseases 0.000 description 2
- 230000007815 allergy Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000002649 immunization Methods 0.000 description 2
- 230000003053 immunization Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007721 medicinal effect Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a medical information processing method, a medical information processing device, medical information processing equipment and a medical information storage medium; the method comprises the following steps: acquiring at least one first original structure diagram, wherein the first original structure diagram is used for describing the topological relation between resources; one such resource is used to describe one type of medical information; obtaining a first candidate structure subgraph comprising at least two resources from the first original structure chart; determining a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, wherein the type selection matrix is used for determining the first candidate structure sub-graph to obtain candidate resources added by the second candidate structure sub-graph; and if the second candidate structure subgraph meets the preset condition, determining a target structure chart based on the second candidate structure subgraph. According to the embodiment of the invention, the second candidate structure subgraph with stronger directivity can be obtained, the target structure chart with a relatively compact structure is obtained, and the focusing property of the mining result of medical information is improved.
Description
Technical Field
The present invention relates to, but not limited to, the technical field of medical applications or the technical field of big data, and in particular, to a medical information processing method, a device, equipment, and a storage medium.
Background
Medical records are records of medical activities such as examination, diagnosis, and/or treatment performed by medical staff on occurrence, development, and/or prognosis of a disease of a patient; the medical record has important effects on medical treatment, prevention, teaching, scientific research, hospital management and the like.
With the development of social informatization, electronic medical records have been developed. The advent of electronic medical records has led to explosive growth of integrable and/or available medical record data; and how to adopt a scientific and effective method to mine out valuable information hidden in medical record data has important significance for medical research.
Disclosure of Invention
In view of the above, embodiments of the present invention provide a medical information processing method, apparatus, device and storage medium, so as to at least solve the above-mentioned part of technical problems.
The technical scheme of the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a medical information processing method, including:
acquiring at least one first original structure diagram, wherein the first original structure diagram is used for describing the topological relation between resources; wherein one of the resources is used to describe one of the medical information;
Obtaining a first candidate structure subgraph comprising at least two resources from the first original structure chart;
determining a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, wherein the type selection matrix is used for determining the first candidate structure sub-graph to obtain candidate resources added by the second candidate structure sub-graph;
and if the second candidate structure subgraph meets the preset condition, determining a target structure chart based on the second candidate structure subgraph.
In the above scheme, the method includes:
determining the type selection matrix based on the first original structure diagram and the first candidate structure subgraph; the diagonal line elements in the model selection matrix are used for describing the first-order similarity of each resource; elements other than diagonal elements in the selection matrix are used to describe the second order similarity between the resource and the resource.
In the above scheme, the resource in the first candidate structure subgraph is a first resource; the resources in the type selection matrix comprise the first resources and the second resources;
the determining a second candidate structure subgraph based on the first candidate structure subgraph and the selection matrix includes:
Determining the second resource with the largest deflection degree as the candidate resource based on the deflection degree of each second resource in the model selection matrix; the bias is the sum of the second-order similarities between the second resource and the first resource, respectively;
the second candidate structural subgraph is determined based on the first candidate structural subgraph and the candidate resources.
In the above scheme, the method includes:
selecting the resources related to disease information and/or treatment information from the resources of the first original structure diagram to form a second original structure diagram;
the obtaining a first candidate structure subgraph including at least two resources from the first original structure chart includes:
obtaining the first candidate structure subgraph comprising at least two resources from the second original structure chart;
the determining the type selection matrix based on the first original structure diagram and the first candidate structure subgraph comprises the following steps:
and determining the model selection matrix based on the second original structure diagram and the first candidate structure subgraph.
In the above solution, the selecting the resource related to the disease information and/or the treatment information from the resources of the first primary structure chart, to form a second primary structure chart includes:
Acquiring the resources related to the disease information and/or the treatment information as third resources based on the resources in the first original structure diagram;
determining the third resource as a source node and a destination node with a connection relation with the source node, wherein the source node can reach the destination node in the first original structure diagram;
determining weight values of the source node and the destination node based on the number of resources passed by the source node to reach the destination node in the first original structure diagram;
and determining the second original structure diagram based on the connection relation between the source nodes and the destination nodes and the weight values of the source nodes and the destination nodes.
In the above scheme, the method includes:
determining the support degree of the second candidate structure subgraph;
and if the second candidate structure subgraph meets a predetermined condition, determining a target structure chart based on the second candidate structure subgraph, including:
and if the support degree of the second candidate structural subgraph is smaller than or equal to a first preset value, determining the target structural chart based on the second candidate structural subgraph.
In the above solution, the determining the support degree of the second candidate structural subgraph includes:
If the first original structure diagram contains all the resources contained in the second candidate structure diagram, determining that the first original structure diagram is a first similar structure diagram; determining the support degree of the second candidate structure subgraph according to the ratio of the number of the first similar structure graphs to the number of the first original structure graphs;
or alternatively, the process may be performed,
if the second original structure diagram contains all the resources contained in the second candidate structure diagram, determining that the second original structure diagram is a second similar structure diagram; and determining the support degree of the second candidate structure subgraph according to the ratio of the number of the second similar structure graphs to the number of the second original structure graphs.
In a second aspect, an embodiment of the present invention provides a medical information processing apparatus, the apparatus including:
the system comprises an acquisition module, a first generation module and a second generation module, wherein the acquisition module is used for acquiring at least one first original structure diagram, and the first original structure diagram is used for describing the topological relation between resources; wherein one of the resources is used to describe one of the medical information;
the processing module is used for acquiring a first candidate structure subgraph comprising at least two resources from the first original structure chart;
The processing module is used for determining a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, wherein the type selection matrix is used for determining the first candidate structure sub-graph to obtain candidate resources added by the second candidate structure sub-graph;
and the determining module is used for determining a target structure diagram based on the second candidate structure diagram if the second candidate structure diagram meets the preset condition.
In a third aspect, embodiments of the present invention provide an apparatus comprising a processor and a memory for storing a computer program capable of running on the processor; the processor is used for realizing the medical information processing method according to any embodiment of the invention when running the computer program.
In a fourth aspect, embodiments of the present invention further provide a storage medium having computer executable instructions stored therein, where the computer executable instructions are executed by a processor to implement the medical information processing method according to any embodiment of the present invention.
In the embodiment of the invention, a terminal acquires at least one first original structure diagram, and acquires a first candidate structure subgraph comprising at least two resources from the first original structure diagram; and determining a second candidate structure sub-graph based on the first candidate structure sub-graph and the pattern selection matrix, and determining a target structure graph based on the second candidate structure sub-graph if the second candidate structure sub-graph meets a predetermined condition. The selection matrix can be a candidate resource added by determining the first candidate structural subgraph to obtain the second candidate structural subgraph, so that the node increasing direction can be limited through the selection matrix, and the second candidate structural subgraph with stronger directivity can be obtained; therefore, a target structure diagram with a relatively compact second candidate structure sub-diagram structure can provide a more directional data base in the field of medical application, and the focusing performance of mining results of medical information is improved.
Drawings
Fig. 1 is a flow chart of a medical information processing method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a first original structure diagram according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of another first primary structure provided in an embodiment of the present invention.
Fig. 4 is a flowchart of another medical information processing method according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of still another first original structure diagram according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a second original structure diagram according to an embodiment of the present invention.
Fig. 7 is a flowchart of another medical information processing method according to an embodiment of the present invention.
Fig. 8 is a schematic structural diagram of a medical information processing apparatus according to an embodiment of the present invention;
fig. 9 is a schematic hardware structure of an apparatus according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the following description, suffixes such as "module", "component", or "unit" for representing elements are used only for facilitating the description of the present invention, and have no specific meaning per se. Thus, "module," "component," or "unit" may be used in combination. In addition, in the following description, a prefix such as "first" or "second" for identifying information is used only for facilitating the description of the present invention, and is not of specific significance in itself. In addition, in the following description, "a plurality" means two or more; "plurality of" means two or more.
As shown in fig. 1, an embodiment of the present invention provides a medical information processing method, including the following steps:
step S11: acquiring at least one first original structure diagram, wherein the first original structure diagram is used for describing the topological relation between resources; wherein one of the resources is used to describe one of the medical information;
step S13: obtaining a first candidate structure subgraph comprising at least two resources from the first original structure chart;
step S15: determining a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, wherein the type selection matrix is used for determining the first candidate structure sub-graph to obtain candidate resources added by the second candidate structure sub-graph;
step S17: and if the second candidate structure subgraph meets the preset condition, determining a target structure chart based on the second candidate structure subgraph.
The medical information processing method provided by the embodiment of the invention can be executed by the terminal; the terminal may be any kind of mobile terminal or fixed terminal. For example, the terminal may be, but is not limited to being, at least one of: a cell phone, a computer, a server, a medical device, an industrial device, and/or a wearable device, etc.
Here, the resource may be any kind of medical information or a data structure related to any kind of medical information; for example, the resource may be, but is not limited to, the following medical information or data structures related to medical information: disease information, treatment information, management information, payment information, and workflow information. Here, the resource may be a minimum data unit.
Illustratively, the resources included in the first original structure diagram, the first candidate structure subgraph, the second candidate structure subgraph, and the second original structure diagram referred to below may each be two or more.
In one embodiment, in the plurality of first primary structure diagrams acquired in step S11, at least a portion of resources of any two of the first primary structure diagrams are different, and/or medical information described by at least a portion of resources of any two of the first primary structure diagrams are different.
Illustratively, the fast medical interoperation resource (Fast Healthcare Interoperability Resources, FHIR) decouples the medical information into a resource; the FHIR Release 4 issues 145 resources altogether, one resource corresponding to each data structure of medical information. For example, a physical sign record (Observation) resource defines a data structure describing symptom information; treatment planning (CarePLan) resources define data structures, etc. describing treatment plans.
For example, various types of medical information may be associated with one or more resources; for example, as shown in table 1 below, the disease information may be associated with, but is not limited to, resources of at least one of: an allergy (allergy) resource, a diagnostic record (Condition) resource, a sign record (Observation) resource, a diagnostic report (diagnostic report) resource, a questionnaire response (query response) resource, a family history (family history) resource, an Immunization (Immunization) resource, and a risk assessment (riskassembly) resource; the treatment information may be associated with, but is not limited to, resources of at least one of: medical application (medical request) resources, service application (ServiceRequest) resources, nutritional order (nutrition order) resources, procedure (Procedure) resources, device application (DeviceRequest) resources, and treatment plan (carelan) resources. Here, "paraphrased" in table 1 is used to represent the meaning described by each resource; for example, family history resources, describing family history; as another example, a service application resource is used to describe checking and/or inspecting prescriptions.
TABLE 1
It will be appreciated that each of the elements in table 1 above are independent and are illustratively listed in the same table, but do not represent that all elements in the table must exist simultaneously as shown in the table. Wherein the value of each element is independent of any other element value in table 1. It will be appreciated by those skilled in the art that the values of each of the elements of Table 1 are a separate embodiment.
The above description of resources is merely an example, and is not limited to the kind, number, etc. of resources.
Here, the first original structure diagram, the first candidate structure diagram, the second candidate structure diagram, the target structure diagram, and the second original structure diagram described below may be any structure diagram describing a connection relationship or a topology relationship between resources. The connection relationship or topology relationship may be used to indicate that resources are associated with each other.
The first primary structure may be, for example, a structure having a connection relationship between resources. For example, as shown in fig. 2, the first primary structure diagram may include a physical sign record 1 resource, a patient resource, a service request resource, a visit event resource, a diagnosis record resource, and a physical sign record 2 resource; the first original structure diagram further includes observing a connection relationship between the resource and the patient resource, a connection relationship between the service application resource and the patient resource, and the like.
The second primary structure may be, for example, a structure having a topological relationship between resources. For example, the first primary structure may be as shown in fig. 3, and the first primary structure may be a topology structure; the topology map "1", "2", "3", "4", "5" and "6" may each indicate a resource, for example, may be used to indicate a physical sign record 1 resource, a patient resource, a diagnostic record resource, a visit event resource, a service application resource and a physical sign record 2 resource, as in fig. 2. The arrow in the first candidate structure subgraph may be used to describe a resource-to-resource connection relationship; for example, an arrow between "1" and "2" is used to describe that the resources indicated by "1" and "2" are associated.
In one embodiment, the first primary structure map, the first candidate structure map, the second candidate structure map, the target structure map, and the second primary structure map may each be a directed structure map. For example, as shown in fig. 2 and 3, the arrows connecting the resources are directional; the arrow between "1" and "2" in fig. 3 is used to describe that the resource indicated by "1" is reachable by the resource indicated by "2".
In one embodiment, step S13 includes: any at least two resources are obtained from the first original structure diagram to form a first candidate structure sub-diagram.
Illustratively, as shown in the first original structure diagram of FIG. 3, resources "1" and "2" may be selected therefrom to form a first candidate structure subgraph.
In one embodiment, the method comprises: a selection matrix is determined. Here, the terminal may determine the selection matrix based on the correlation between the resources, or the terminal may determine the selection matrix based on the history structure map; alternatively, the terminal may determine the selection matrix based on the first original structural diagram. Here, only the diagonal elements in the determined selection matrix are used to describe the relevance of each resource itself, and the elements other than the diagonal elements in the selection matrix are used to describe the relevance between the resources. The association may be represented by a weight value.
Illustratively, the first original structure includes resource "1", resource "2", resource "3", resource "4", resource "5" and resource "6"; the selection matrix may be as follows:the diagonal elements are "≡", and are used for indicating the relevance of the resources "1", the resources "2", the resources "3", the resources "4", the resources "5" and the resources "6" respectively. Elements other than diagonal elements are used to refer to the resource-to-resource association; for example, row 1, column 2 elements are used to indicate an association between resource "1" and resource "2", with resource "1" directly connected to resource "2"; then the weight value of the association between resource "1" and resource "2" may be determined to be 1. For another example, the elements in row 3 and column 5 are used to indicate the association between resource "3" and resource "5", and one resource is required to be passed from resource "3" to resource "5"; it can be determined that the weight value of the association between the resource "1" and the resource "5" is +.>For another example, the element of row 5 and column 1 is used to indicate the association between resource "6" and resource "1", and resource "6" is not connectable to resource "1", then the weight of the association between resource "6" and resource "1" may be determined to be 0.
In one embodiment, the resource included in the first candidate structure subgraph is a first resource; the resources in the candidate matrix comprise a first resource and a second resource; the candidate matrix is used for selecting a second resource with the strongest association with the first candidate structural subgraph from the second resources as a candidate resource.
In the example where the first original structure diagram includes resource "1", resource "2", resource "3", resource "4", resource "5" and resource "6", if the first candidate structure subgraph is determinedFor the structure diagram determined by resource "1" and resource "2", the selection matrix is used to determine candidate resources among resource "3", resource "4", resource "5" and resource "6". The weight values due to the relevance of the resource '3' to the resource '1' and the resource '2' are respectivelyAnd->The weight values of the association of resource "4" with resource "1" and resource "2" are 1 and +.>The weight values of the associations of resource "5" with resource "1" and resource "2", respectively, are +.>And 1, the weight values of the associations of resource "6" with resource "1" and resource "2", respectively, are 1 and +.>Thus determining resource "4" as a candidate resource.
In the embodiment of the present invention, step S15 may be repeatedly performed, so as to continuously obtain a new first candidate structure sub-graph and a second candidate structure sub-graph, until the obtained second candidate structure sub-graph meets a predetermined condition, and then determine the target structure diagram based on the second candidate structure sub-graph. For example, when step S15 is repeatedly performed, it may be: after the step S15 is executed for the first time, a first second candidate structure sub-graph is obtained; taking the first second candidate structure subgraph as a first candidate structure subgraph for executing the step S15 for the second time; and so on, taking the ith second candidate structural subgraph obtained after the ith-1 st execution of the step S15 as the first candidate structural subgraph for the ith execution of the step S15; where i is an integer greater than 1.
In one embodiment, the second candidate structure sub-graph satisfying the predetermined condition in step S17 may be, but is not limited to being, at least one of:
the support degree of the second candidate structure subgraph is smaller than or equal to a first preset value;
the number of resources contained in the second candidate structure subgraph is greater than or equal to a second predetermined value.
In one embodiment, the method comprises: determining the support degree of the second candidate structure subgraph;
the step S17 includes: and if the support degree of the second candidate structural subgraph is smaller than or equal to a first preset value, determining the target structural chart based on the second candidate structural subgraph.
In one embodiment, the determining the support of the second candidate structure sub-graph includes:
if the first original structure diagram contains all the resources contained in the second candidate structure diagram, determining that the first original structure diagram is a first similar structure diagram;
and determining the support degree of the second candidate structure subgraph according to the ratio of the number of the first similar structure graphs to the number of the first original structure graphs.
Here, if the first primary structure diagram includes resources "1", "2", "3" and "4", and the second candidate structure diagram includes resources "1" and "2"; all resources contained in the second candidate structure subgraph are contained in the first original structure map, which is the first similar structure map. Alternatively, if the first original structure diagram includes resources "1", "2", "3", and "4", and the second candidate structure diagram includes resources "1", "4", and "5"; all resources contained in the second candidate structure subgraph are not contained in the first original structure graph, which is not the first similar structure graph.
Here, the support degree may be a ratio of the number of the first similar structure drawings to the number of the first original structure drawings; or the support may be: a value different from a ratio of the number of the first similar structural drawings to the number of the first original structural drawings by a predetermined value.
Here, the first predetermined value and the second predetermined value may be both determined by the terminal based on the user input operation, or determined based on historical experience information or set in advance. The first predetermined value may be 90% or 80% or 70% or the like. The second predetermined value may be 100, 200 or 1000 or 10000 or the like.
In one embodiment, determining a target structure diagram based on the second candidate structure subgraph in step S17 includes:
determining a second candidate structure subgraph meeting the preset condition as the target structure chart;
or alternatively, the process may be performed,
and determining a first candidate structure sub-graph corresponding to the second candidate structure sub-graph meeting the preset condition as the target structure graph.
Illustratively, a calculation formula for determining the support degree of the second candidate structural subgraph is provided:wherein G-SUP (G) i ) For the support of the second candidate structure subgraph, |{ G i |g∈G i The number of first similar structure diagrams; the |g| is the number of the first original structure drawing.
In the embodiment of the invention, a terminal acquires at least one first original structure diagram, and acquires a first candidate structure subgraph comprising at least two resources from the first original structure diagram; and determining a second candidate structure sub-graph based on the first candidate structure sub-graph and the pattern selection matrix, and determining a target structure graph based on the second candidate structure sub-graph if the second candidate structure sub-graph meets a predetermined condition. The selection matrix can be a candidate resource added by determining the first candidate structural subgraph to obtain the second candidate structural subgraph, so that the node increasing direction can be limited through the selection matrix, and the second candidate structural subgraph with stronger directivity can be obtained; therefore, a target structure diagram with a relatively compact second candidate structure sub-diagram structure can provide a more directional data base in the field of medical application, and the focusing performance of mining results of medical information is improved.
In the embodiment of the invention, if the preset condition is that the support degree is smaller than or equal to the first preset value, determining a target structure diagram based on the second candidate structure diagram; therefore, a relatively large or maximum frequent subgraph can be mined as a target structure diagram, and the relatively large or maximum frequent subgraph can fit a disease course mining target in content, and the compactness and focusing performance of the structure can be further ensured; the thus obtained target structure diagram can provide important data support and thinking guidance for the medical application field.
In some embodiments, as shown in fig. 4, the method includes:
step S14: determining the type selection matrix based on the first original structure diagram and the first candidate structure subgraph; the diagonal line elements in the model selection matrix are used for describing the first-order similarity of each resource; elements other than diagonal elements in the selection matrix are used to describe the second order similarity between the resource and the resource.
In one embodiment, the first order similarity may be determined based on a sum of the ingress and egress of the resource; the second order similarity refers to a first order similarity determination of a resource with an adjacent resource. Here, the adjacent resource of one resource refers to a resource directly connected to the resource in the structure diagram; for example, as shown in FIG. 3, the resource indicated by "1" may be a contiguous resource to the resource indicated by "2".
In another embodiment, the first-order similarity may be determined based on a sum of the weights of the resource and the first contiguous resource and the weights of the resource and the second contiguous resource; the second order similarity may be determined based on a weight value of the resource and the first contiguous resource or based on a weight value of the resource and the second contiguous resource; wherein the first contiguous resource is a contiguous resource that enters the resource and the second contiguous resource is a contiguous resource that leaves the resource. Illustratively, as shown in FIG. 4, the resource indicated by "2" is a second contiguous resource of the resource indicated by "1"; the resource indicated by "4" is the first contiguous resource of the resource indicated by "1".
In the embodiment of the invention, the selection matrix with a compact structure can be determined by determining that the diagonal elements in the selection matrix are the first-order similarity of each resource and the elements other than the diagonal elements are the second-order similarity of the resources, so that the candidate resources which can be increased are the resources which enable the structure diagram to be more compact.
In some embodiments, the resource in the first candidate structure subgraph is a first resource; the resources in the type selection matrix comprise the first resources and the second resources;
In the step S15, a second candidate structure subgraph is determined based on the first candidate structure subgraph and the selection matrix, including:
determining the second resource with the largest deflection degree as the candidate resource based on the deflection degree of each second resource in the model selection matrix; the bias is the sum of the second-order similarities between the second resource and the first resource, respectively;
the second candidate structural subgraph is determined based on the first candidate structural subgraph and the candidate resources.
Here, the second order similarity may be a sum of weight values of the resource-to-resource associations.
In the embodiment of the invention, the second resource with the largest bias degree can be selected as the candidate resource, so that the increased candidate resource can be the resource which enables the structure diagram to be relatively compact, thereby being beneficial to determining the second candidate structure subgraph with a more compact structure.
Of course, in other embodiments, it may also be that the second resource with the second greatest bias is determined as the candidate resource, or that one second resource with the first few ranks is determined as the candidate resource; it can also be determined to some extent that the structure diagram is relatively compact in resources.
In some embodiments, the method comprises:
selecting the resources related to disease information and/or treatment information from the resources of the first original structure diagram to form a second original structure diagram;
the step S13 includes:
and acquiring the first candidate structural subgraphs comprising at least two resources from the second original structural diagram.
Illustratively, the first primary structure includes 10 resources; the 10 resources are resources related to disease information, treatment information or payment information, etc., wherein 5 resources are resources related to disease information or treatment information; the terminal may determine that the structure of the resource structure in 5 is the second original structure.
In some embodiments, the selecting the resource related to the disease information and/or the treatment information from the resources of the first primary structure chart forms a second primary structure chart, including:
acquiring the resources related to the disease information and/or the treatment information as third resources based on the resources in the first original structure diagram;
determining the third resource as a source node and a destination node with a connection relation with the source node, wherein the source node can reach the destination node in the first original structure diagram;
Determining weight values of the source node and the destination node based on the number of resources passed by the source node to reach the destination node in the first original structure diagram;
and determining the second original structure diagram based on the connection relation between the source nodes and the destination nodes and the weight values of the source nodes and the destination nodes.
Here, the resource related to the disease information and/or the treatment information is a third resource; the third resource may be divided into a source node and a destination node. Here, the source node and the destination node may be any one of the third resources; the same third resource may be both the source node and the destination node.
For example, as shown in fig. 2 and 3, the first primary structure diagram may include resources corresponding to "1", "2", "3", "4", "5", and "6", respectively, where "1", "2", "3", "4", "5", and "6" correspond to a physical sign record resource, a patient resource, a diagnosis record resource, a visit event resource, a service application resource, and a physical sign record resource, respectively. Wherein, "1", "3", "5" and "6" may be resources related to disease information or treatment information, and "2" and "4" are resources unrelated to disease information or treatment information; as shown in fig. 5, resources "1", "3", "5" and "6" related to disease information or treatment information are marked in the first original structure diagram. The terminal may reconnect reserved resources according to the reachability and shortest path principles of "1", "3", "5" and "6" in the first primary structure diagram, and the connection manner may be as shown in fig. 6.
The connection mode based on fig. 6 may be: if the source node can reach the destination node, adding a directed edge from the source node to the destination node; giving a weight value to the directed edge; the weight value may be determined based on the resources through which the source node reaches the destination node. As shown in fig. 5, for example, if the destination node reached by the source node is itself, the weight value of the source node is determined to be ≡infinity; for another example, if the source node "1" reaches the destination node "3" in the first original structure diagram without going through other resources, that is, going through 0 resources, it is determined that the weight value from the source node "1" to the destination node "3" is 1; for another example, if the source node "3" needs to pass through 2 resources when reaching the destination node "1" in the first original structure diagram, it is determined that the weight value from the source node "3" to the destination node "1" isFor another example, if the source node "5" needs to pass through 3 resources when reaching the destination node "3" in the first original structure diagram, it is determined that the weight value from the source node "3" to the destination node "1" is ∈>Here, the equivalent adjacency matrix of the second original structure after the weight is given can be shown as the following matrix: />Wherein, each diagonal element is the weight value of each resource and is the source node and the destination node at the same time; elements other than diagonal elements are resources (i.e. sources Node) to the contiguous resource (i.e., destination node).
Thus, in the embodiment of the invention, some resources irrelevant to the disease information and/or the treatment information can be removed from the first original structural diagram, and the resource information relevant to the disease information and/or the treatment information is reserved; and the connection relation of the resources in the second original structure diagram is determined through the connection relation of the reserved resources in the first original structure diagram, so that the first original structure diagram can be simplified to obtain an equivalent second original structure diagram, and the subsequent simplified determination of the type selection matrix and the calculation of the target structure diagram are facilitated.
In the embodiment of the invention, the obtained equivalent adjacency matrix of the second original structure chart is determined based on the weight value determined by the reserved resources of the disease information and/or the treatment information, which are connected in the first original structure chart, so that the topology information of the first original structure chart can be reserved.
In some embodiments, the determining the type-selection matrix in step S15 based on the first original structure diagram and the first candidate structure subgraph includes:
and determining the model selection matrix based on the second original structure diagram and the first candidate structure subgraph.
In the above example of the second original structure diagram including the resources "1", "3", "5" and "6", the equivalent adjacency matrix of the second original structure diagram isA first candidate structure subgraph of which the resources comprise resources '1' and '3' can be selected from the second original structure chart; the equivalent adjacency matrix of the second candidate structure subgraph pair isFrom the equivalent adjacent matrix M adj2 The selection matrix can be determined to be +.>Wherein, diagonal line elements in the selection matrixA prime is used for describing the first-order similarity of each resource; elements other than diagonal elements in the selection matrix are used to describe the second order similarity between the resource and the resource. Here, the diagonal elements of the 1 st row and 1 st column in the selection matrix are used to describe the first-order similarity of the resource "1", and based on the second original structure diagram (as shown in fig. 6) and the equivalent adjacent matrix, the weight values of the resource "1" and the second adjacent resources "3", "5" and "6" apart from the resource "1" are respectively 1 and>is->And the weight values of the resource "1" and the first adjacent resource "3", "5" entering the resource "1" are +.>The first-order similarity of the description resource "1" of the 1 st row and 1 st column is +.>Here, the elements of the 1 st row and 2 nd column of the selection matrix are used to describe the second order similarity of the resource "1" to the resource "2", which may be the first order similarity +. >And elements of the selection matrix 2 nd row 1 st column are used to describe the second order similarity of the resource "2" to the resource "1", which may be the first order similarity +.>
The corresponding matrix selection part of the first candidate structure sub-graph isThe second resource included in the model selection matrix is resource '5' and '6';calculating the bias of the second resources may be +.>Where m is the number of resources of the first candidate structure sub-graph, D i Is the bias of the ith resource. The terminal can determine the bias of resource "5->Determining bias D for resource "6 6 ＝M select (6,1)+M select (6, 3) =0+0=0. The terminal determines the maximum deflection V next ＝max i D i The method comprises the steps of carrying out a first treatment on the surface of the Here, if the largest bias among the bias of the second resources "5" and "6" is the bias of the second resource "5", the second resource "5" is determined as the candidate resource. The terminal may determine a second candidate structural subgraph based on the first candidate structural subgraph and candidate resource "5".
The embodiment of the invention is based on the second original structure diagram and the first candidate structure diagram, and the type selection matrix is determined, so that the second candidate structure diagram determined based on the candidate matrix can reduce the resources with weak correlation on the premise of reserving the topology information of the original first original structure diagram to a certain extent, thereby greatly simplifying the calculation on the basis of a relatively complete data model.
In some embodiments, the determining the support of the second candidate structure sub-graph includes:
if the second original structure diagram contains all the resources contained in the second candidate structure diagram, determining that the second original structure diagram is a second similar structure diagram;
and determining the support degree of the second candidate structure subgraph according to the ratio of the number of the second similar structure graphs to the number of the second original structure graphs.
Here, if the second original structure diagram includes resources "1", "2", "5", and "6", and the second candidate structure diagram includes resources "1" and "3"; the second original structure map includes all the resources included in the second candidate structure map, and the second original structure map is a second similar structure map. Alternatively, if the second original structure diagram includes resources "1", "3", "5", and "6", and the second candidate structure diagram includes resources "1", "3", and "4"; the second original structure diagram does not contain all the resources contained in the second candidate structure sub-diagram and is not the second similar structure diagram.
Here, the support degree may be a ratio of the number of the second similar structure drawings to the number of the second original structure drawings; or the support may be: a value different from a ratio of the number of second similar structural drawings to the number of second original structural drawings by a predetermined value.
In the embodiment of the invention, the selection matrix and the first candidate structure subgraph are determined based on the second original structure chart, so that the second original structure chart can be determined as a comparison sample; the relatively accurate support degree can also be determined based on the support degree of the candidate structure diagram subgraph determined by the second original structure diagram.
To further explain any embodiment of the present invention, a specific embodiment is provided below.
As shown in fig. 7, an embodiment of the present invention provides a medical information processing method, which is executed by a terminal, including the steps of:
step S21: the terminal acquires at least one first original structure diagram;
here, the terminal may model the medical information using FHIR to create a first primary structure map for each patient; the first primary structure may be a physical sign record 1 resource, a patient resource, a diagnostic record resource, a visit event resource, a service application resource, and a physical sign record 2 resource as shown in fig. 2. The terminal converts the first original structure diagram into a topology model as shown in fig. 3, and the physical sign record 1 resource, the patient resource, the diagnosis record resource, the visit event resource, the service application resource and the physical sign record 2 resource are indicated by "1", "2", "3", "4", "5" and "6" in fig. 3, respectively. The resource-to-resource connection relationship in FIG. 2 is the association of a resource with a Reference to a resource.
Step S22: the terminal selects the resources related to the disease information and/or the treatment information from the resources of the first original structure diagram to form a second original structure diagram;
here, the terminal selects resources related to the disease information and/or the treatment information from the physical sign record 1 resource, the patient resource, the diagnosis record resource, the visit event resource, the service application resource and the physical sign record 2 resource in the first original structure chart: sign record 1 resource, diagnosis record resource, service application resource, and sign record 2 resource; the second original structure diagram for obtaining the physical sign record 1 resource, the diagnosis record resource, the service application resource and the physical sign record 2 resource can be shown in fig. 6. Here, in the second original structure diagram, if the source node can reach the destination node, a directed edge is added from the source node to the destination node; the weighted value is given to the directed edge.
The terminal may determine, based on the equivalent adjacency matrix that can determine the second original block diagram, that:
step S23: the terminal determines a type selection matrix and determines added candidate resources;
here, the method of determining the added candidate resources may be regarded as a bias node growth method.
Here, the terminal determines, based on the second original structure diagram, that the first candidate structure diagram is a structure diagram including resources "1" and "3"; equivalent adjacency matrix M based on second original structure diagram of terminal adj2 Determining the selection matrix asThe diagonal line elements in the model selection matrix are used for describing the first-order similarity of each resource; elements other than diagonal elements in the selection matrix are used to describe the second order similarity between the resource and the resource. From a selection matrix M select It can be seen that resources "5" and "6" are two alternative directions of node growth, namelyThe resources "5" and "6" may be selected as candidate resources in the second candidate structure sub-graph. Assuming that the mining objective is a structure-tight subgraph, then it is necessary to rely on M select Selecting the resource which is more tightly coupled with the first candidate structure sub-graph from the resources of '5' and '6', wherein the selection can still be determined according to the maximum bias degree: v (V) next ＝max i D i The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Where m is the number of resources of the first candidate structure sub-graph, D i Is the bias of the ith resource. Here, resource "5" may be determined as a candidate resource, i.e., resource "5" is the direction in which the node is growing in need.
Step S24: and the terminal determines a second candidate structure subgraph according to the first candidate structure subgraph and the candidate resources.
Step S25: the terminal determines the support degree of the second candidate structure subgraph;
here, the terminal determines the degree of support of the second candidate structure sub-graph Wherein G' -SUP (G) i ) For the support of the second candidate structural subgraph, |{ G' i |g∈G' i The number of second phase structure diagrams; and the I G' I is the number of the second original structure diagram.
Step S26: the terminal determines whether the support degree of the second candidate structure subgraph is smaller than or equal to a first preset value, if not, the step S27 is executed; if yes, go to step S28;
here, the terminal determines the first predetermined value as G-SUP min The method comprises the steps of carrying out a first treatment on the surface of the If G' -SUP (G) i )≤G-SUP min Step S27 is performed, otherwise step S28 is performed.
Step S27: the terminal determines the second candidate structure subgraph as a first candidate structure subgraph;
here, the terminal takes the second candidate structure subgraph as the first candidate structure subgraph that needs to increase candidate resources next time.
Step S28: the terminal determines a target structure diagram based on the second candidate structure subgraph.
Here, the terminal may use the second candidate structure subgraph when the support degree is less than or equal to a predetermined value as the target structure chart. Or determining the structure diagram of the last added candidate resource (namely the first candidate structure diagram corresponding to the second candidate structure diagram) as a target structure diagram by using the second candidate structure diagram; the target structure diagram at this time is the maximum frequent subgraph including the largest number of resources. The maximum frequent subgraph can be attached to a disease course mining target in content, and compactness and focusing of the structure can be guaranteed.
In the embodiment of the invention, resources irrelevant to disease information and/or treatment information can be removed, the topological relation of the original treatment information is reserved to a certain extent through the equivalent adjacent matrix, and a relatively more complete data model can be provided for the excavation of a subsequent target structure diagram while the calculation is simplified.
In the embodiment of the invention, a selection matrix limiting direction of resource growth limitation can be defined, and the deflection capability of the second candidate structure subgraph can be controlled; resources that are more tightly coupled to the first candidate structure sub-graph may be selected to be added to the second candidate structure sub-graph by selecting the most biased resources as candidate nodes. Therefore, the structure diagram of the target structure for excavation can be biased to a structure compact topology, and the focusing property of the excavation structure is improved.
In addition, the invention can also realize the conversion of the equivalent topological structure (namely, the conversion from the first original structural diagram to the equivalent second original structural diagram) and the special node growth mode (namely, the control of the candidate resource with the maximum deflection or relatively larger deflection is the resource which is needed to be increased for transforming the first candidate structural sub-diagram to the second candidate structural sub-diagram), thereby realizing the effective fusion of the two.
It should be noted here that: the following description of the information processing apparatus item is similar to the above description of the medical information processing method item, and description of beneficial effects of the same method is omitted. For technical details not disclosed in the embodiments of the information processing apparatus of the present invention, please refer to the description of the embodiments of the medical information processing method of the present invention.
As shown in fig. 8, an embodiment of the present invention provides a medical information processing apparatus including:
an obtaining module 41, configured to obtain at least one first primary structure diagram, where the first primary structure diagram is used to describe a topological relation between resources; wherein one of the resources is used to describe one of the medical information;
a processing module 42, configured to obtain a first candidate structure sub-graph that includes at least two kinds of resources from the first original structure diagram;
the processing module 42 is configured to determine a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, where the type selection matrix is used to determine that the first candidate structure sub-graph obtains candidate resources added by the second candidate structure sub-graph;
and the determining module 43 is configured to determine a target structure diagram based on the second candidate structure diagram if the second candidate structure diagram meets a predetermined condition.
In some embodiments, the apparatus comprises:
the processing module 42 is configured to determine the type selection matrix based on the first original structure diagram and the first candidate structure subgraph; the diagonal line elements in the model selection matrix are used for describing the first-order similarity of each resource; elements other than diagonal elements in the selection matrix are used to describe the second order similarity between the resource and the resource.
In some embodiments, the resource in the first candidate structure subgraph is a first resource; the resources in the type selection matrix comprise the first resources and the second resources;
the processing module 42 is configured to determine, based on the bias degree of each of the second resources in the selection matrix, the second resource with the largest bias degree as the candidate resource; the bias is the sum of the second-order similarities between the second resource and the first resource, respectively;
the second candidate structural subgraph is determined based on the first candidate structural subgraph and the candidate resources.
In some embodiments, the obtaining module 41 is configured to select the resources related to disease information and/or treatment information from the resources of the first primary structure chart, to form a second primary structure chart;
The processing module 42 is configured to obtain the first candidate structure subgraph including at least two kinds of resources from the second original structure chart;
the processing module 42 is further configured to determine the selection matrix based on the second original structure diagram and the first candidate structure subgraph.
In some embodiments, the processing module 42 is configured to perform the steps of:
acquiring the resources related to the disease information and/or the treatment information as third resources based on the resources in the first original structure diagram;
determining the third resource as a source node and a destination node with a connection relation with the source node, wherein the source node can reach the destination node in the first original structure diagram;
determining weight values of the source node and the destination node based on the number of resources passed by the source node to reach the destination node in the first original structure diagram;
and determining the second original structure diagram based on the connection relation between the source nodes and the destination nodes and the weight values of the source nodes and the destination nodes.
In some embodiments, the processing module 42 is configured to determine a support level of the second candidate structure sub-graph;
The determining module 43 is configured to determine the target structure diagram based on the second candidate structure diagram if the support degree of the second candidate structure diagram is less than or equal to a first predetermined value.
In some embodiments, the processing module 42 is configured to determine that the first original structure diagram is a first similar structure diagram if the first original structure diagram includes all the resources included in the second candidate structure diagram;
the processing module 42 is further configured to determine the support degree of the second candidate structure subgraph according to a ratio of the number of the first similar structure graphs to the number of the first original structure graphs.
In some embodiments, the processing module 42 is configured to determine that the second original structure diagram is a second similar structure diagram if the second original structure diagram includes all the resources included in the second candidate structure diagram;
the processing module 42 is further configured to determine the support degree of the second candidate structure subgraph according to a ratio of the number of the second similar structure graphs to the number of the second original structure graphs.
As shown in fig. 9, an embodiment of the present invention also provides an apparatus comprising a processor 61 and a memory 62 for storing a computer program capable of running on the processor 61; wherein the processor 61 is configured to implement the medical information processing method according to any embodiment of the present invention when running a computer program.
In some embodiments, the memory in embodiments of the invention may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM). The memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
And the processor may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
In some embodiments, the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (Application Specific Integrated Circuits, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing devices (DSP devices, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units designed to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques described herein may be implemented with modules (e.g., procedures, functions, and so on) that perform the functions described herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
Still another embodiment of the present invention provides a computer-readable storage medium storing an executable program which, when executed by a processor, can implement the steps of the medical information processing method of any embodiment of the present invention.
In some embodiments, the computer storage medium may include: a U-disk, a removable hard disk, a Read Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It should be noted that: the technical schemes described in the embodiments of the present invention may be arbitrarily combined without any collision.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A medical information processing method, characterized in that the method comprises:
acquiring at least one first original structure diagram, wherein the first original structure diagram is used for describing the topological relation between resources; wherein one of the resources is used to describe one of the medical information;
obtaining a first candidate structure subgraph comprising at least two resources from the first original structure chart;
Determining a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, wherein the type selection matrix is used for determining the first candidate structure sub-graph to obtain candidate resources added by the second candidate structure sub-graph;
and if the second candidate structure subgraph meets the preset condition, determining a target structure chart based on the second candidate structure subgraph.
2. The method according to claim 1, characterized in that the method comprises:
determining the type selection matrix based on the first original structure diagram and the first candidate structure subgraph; the diagonal line elements in the model selection matrix are used for describing the first-order similarity of each resource; elements other than diagonal elements in the selection matrix are used to describe the second order similarity between the resource and the resource.
3. The method of claim 2, wherein the resource in the first candidate structure subgraph is a first resource; the resources in the type selection matrix comprise the first resources and the second resources;
the determining a second candidate structure subgraph based on the first candidate structure subgraph and the selection matrix includes:
determining the second resource with the largest deflection degree as the candidate resource based on the deflection degree of each second resource in the model selection matrix; the bias is the sum of the second-order similarities between the second resource and the first resource, respectively;
The second candidate structural subgraph is determined based on the first candidate structural subgraph and the candidate resources.
4. The method according to claim 2, characterized in that the method comprises:
selecting the resources related to disease information and/or treatment information from the resources of the first original structure diagram to form a second original structure diagram;
the obtaining a first candidate structure subgraph including at least two resources from the first original structure chart includes:
obtaining the first candidate structure subgraph comprising at least two resources from the second original structure chart;
the determining the type selection matrix based on the first original structure diagram and the first candidate structure subgraph comprises the following steps:
and determining the model selection matrix based on the second original structure diagram and the first candidate structure subgraph.
5. The method of claim 4, wherein said selecting said resource associated with disease information and/or therapy information from said resources of said first primary structure map comprises:
acquiring the resources related to the disease information and/or the treatment information as third resources based on the resources in the first original structure diagram;
Determining the third resource as a source node and a destination node with a connection relation with the source node, wherein the source node can reach the destination node in the first original structure diagram;
determining weight values of the source node and the destination node based on the number of resources passed by the source node to reach the destination node in the first original structure diagram;
and determining the second original structure diagram based on the connection relation between the source nodes and the destination nodes and the weight values of the source nodes and the destination nodes.
6. The method according to claim 1 or 4, characterized in that the method comprises:
determining the support degree of the second candidate structure subgraph;
and if the second candidate structure subgraph meets a predetermined condition, determining a target structure chart based on the second candidate structure subgraph, including:
and if the support degree of the second candidate structural subgraph is smaller than or equal to a first preset value, determining the target structural chart based on the second candidate structural subgraph.
7. The method of claim 6, wherein the determining the support of the second candidate structure sub-graph comprises:
If the first original structure diagram contains all the resources contained in the second candidate structure diagram, determining that the first original structure diagram is a first similar structure diagram; determining the support degree of the second candidate structure subgraph according to the ratio of the number of the first similar structure graphs to the number of the first original structure graphs;
or alternatively, the process may be performed,
if the second original structure diagram contains all the resources contained in the second candidate structure diagram, determining that the second original structure diagram is a second similar structure diagram; and determining the support degree of the second candidate structure subgraph according to the ratio of the number of the second similar structure graphs to the number of the second original structure graphs.
8. A medical information processing apparatus, characterized in that the apparatus comprises:
the system comprises an acquisition module, a first generation module and a second generation module, wherein the acquisition module is used for acquiring at least one first original structure diagram, and the first original structure diagram is used for describing the topological relation between resources; wherein one of the resources is used to describe one of the medical information;
the processing module is used for acquiring a first candidate structure subgraph comprising at least two resources from the first original structure chart;
The processing module is used for determining a second candidate structure sub-graph based on the first candidate structure sub-graph and a type selection matrix, wherein the type selection matrix is used for determining the first candidate structure sub-graph to obtain candidate resources added by the second candidate structure sub-graph;
and the determining module is used for determining a target structure diagram based on the second candidate structure diagram if the second candidate structure diagram meets the preset condition.
9. An apparatus comprising a processor and a memory for storing a computer program capable of running on the processor; wherein the processor is adapted to implement the medical information processing method of any one of claims 1 to 7 when the computer program is run.
10. A computer storage medium having computer-executable instructions stored therein, wherein the computer-executable instructions are executed by a processor to implement the medical information processing method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211429239.1A CN116959731A (en) | 2022-11-15 | 2022-11-15 | Medical information processing method, device, equipment and storage medium |
| PCT/CN2023/123804 WO2024104005A1 (en) | 2022-11-15 | 2023-10-10 | Medical information processing method and apparatus, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211429239.1A CN116959731A (en) | 2022-11-15 | 2022-11-15 | Medical information processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116959731A true CN116959731A (en) | 2023-10-27 |
Family
ID=88455353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211429239.1A Pending CN116959731A (en) | 2022-11-15 | 2022-11-15 | Medical information processing method, device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116959731A (en) |
| WO (1) | WO2024104005A1 (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750263B (en) * | 2012-05-31 | 2014-10-22 | 常州工学院 | Method for simplifying hyperlink network chart data of Internet |
| CN104239126B (en) * | 2013-06-19 | 2018-03-13 | 华为技术有限公司 | The minimal cut acquisition methods and equipment of a kind of digraph |
| CN104516995A (en) * | 2013-09-29 | 2015-04-15 | 华为技术有限公司 | Network-flow graph reduction method and device |
| CN106682514B (en) * | 2016-12-15 | 2020-07-28 | 哈尔滨工程大学 | System calling sequence feature pattern set generation method based on subgraph mining |
| US11803184B2 (en) * | 2018-12-18 | 2023-10-31 | Motional Ad Llc | Methods for generating maps using hyper-graph data structures |
| CN114283099A (en) * | 2020-09-21 | 2022-04-05 | 华为技术有限公司 | Method, system and device for processing graph |
| US11228505B1 (en) * | 2021-01-29 | 2022-01-18 | Fujitsu Limited | Explanation of graph-based predictions using network motif analysis |
| CN113326404A (en) * | 2021-06-25 | 2021-08-31 | 深圳前海微众银行股份有限公司 | Data flow graph processing method, device, equipment and storage medium |
| CN113609345B (en) * | 2021-09-30 | 2021-12-10 | 腾讯科技（深圳）有限公司 | Target object association method and device, computing equipment and storage medium |
| CN114239198B (en) * | 2021-12-06 | 2023-03-10 | 国网湖北省电力有限公司电力科学研究院 | Power grid subgraph division method and device based on parallel optimization |
-
2022
- 2022-11-15 CN CN202211429239.1A patent/CN116959731A/en active Pending
-
2023
- 2023-10-10 WO PCT/CN2023/123804 patent/WO2024104005A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024104005A1 (en) | 2024-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20090083275A1 (en) | Method, Apparatus and Computer Program Product for Performing a Visual Search Using Grid-Based Feature Organization | |
| TWI478558B (en) | Method, apparatus and computer program product for providing analysis and visualization of content items association | |
| EP3579153A1 (en) | Learned model provision method and learned model provision device | |
| ES2709827T3 (en) | Identity authentication using human biological characteristics | |
| Mantsyzov et al. | Contact-based ligand-clustering approach for the identification of active compounds in virtual screening | |
| CN109785919B (en) | Noun matching method, noun matching device, noun matching equipment and computer readable storage medium | |
| US20190103173A1 (en) | Techniques for managing access of user devices to third-party resources | |
| US20120135757A1 (en) | Method of sharing mobile sensor, apparatus for verifying integrity, and mobile sensor sharing system | |
| KR20190030023A (en) | Apparatus for recommending user's privacy control and method for the same | |
| CN112527923A (en) | Unstructured data storage method and device, computer equipment and storage medium | |
| Silverbush et al. | Optimally orienting physical networks | |
| CN105117489B (en) | Database management method and device and electronic equipment | |
| CN112528090A (en) | Graph data storage method and storage device | |
| KR20150112789A (en) | Method for sharing data of electronic device and electronic device thereof | |
| JP2017021655A (en) | Software analysis system, software analysis method and software analysis program | |
| CN111601380A (en) | Position location method, device and equipment based on position fingerprint and storage medium | |
| Mahin et al. | A crowd enabled approach for processing nearest neighbor and range queries in incomplete databases with accuracy guarantee | |
| CN110717050A (en) | Method and device for accessing knowledge map database | |
| Geppert et al. | Advances in 2D fingerprint similarity searching | |
| CN116959731A (en) | Medical information processing method, device, equipment and storage medium | |
| Hu et al. | ALDPI: adaptively learning importance of multi-scale topologies and multi-modality similarities for drug–protein interaction prediction | |
| CN112446048A (en) | Data sharing method, system, terminal and storage medium based on block chain | |
| CN111221853A (en) | Medicine list abnormity detection method and device, computer equipment and storage medium | |
| US9292704B2 (en) | Information processing device for detecting an illegal stored document, illegal stored document detection method and recording medium | |
| US20150339602A1 (en) | System and method for modeling health care costs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |