CN111341456A - Method and device for generating diabetic foot knowledge map and readable storage medium - Google Patents
Method and device for generating diabetic foot knowledge map and readable storage medium Download PDFInfo
- Publication number
- CN111341456A CN111341456A CN202010110297.2A CN202010110297A CN111341456A CN 111341456 A CN111341456 A CN 111341456A CN 202010110297 A CN202010110297 A CN 202010110297A CN 111341456 A CN111341456 A CN 111341456A
- Authority
- CN
- China
- Prior art keywords
- disease
- knowledge
- diabetic foot
- entities
- map
- 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.)
- Granted
Links
- 208000008960 Diabetic foot Diseases 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 53
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 200
- 201000010099 disease Diseases 0.000 claims abstract description 199
- 238000012216 screening Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002457 bidirectional effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 3
- 239000013598 vector Substances 0.000 description 28
- 230000008569 process Effects 0.000 description 13
- 238000004891 communication Methods 0.000 description 9
- 230000009471 action Effects 0.000 description 7
- 206010012601 diabetes mellitus Diseases 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- NOESYZHRGYRDHS-UHFFFAOYSA-N insulin Chemical compound N1C(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(NC(=O)CN)C(C)CC)CSSCC(C(NC(CO)C(=O)NC(CC(C)C)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CCC(N)=O)C(=O)NC(CC(C)C)C(=O)NC(CCC(O)=O)C(=O)NC(CC(N)=O)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CSSCC(NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2C=CC(O)=CC=2)NC(=O)C(CC(C)C)NC(=O)C(C)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2NC=NC=2)NC(=O)C(CO)NC(=O)CNC2=O)C(=O)NCC(=O)NC(CCC(O)=O)C(=O)NC(CCCNC(N)=N)C(=O)NCC(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC(O)=CC=3)C(=O)NC(C(C)O)C(=O)N3C(CCC3)C(=O)NC(CCCCN)C(=O)NC(C)C(O)=O)C(=O)NC(CC(N)=O)C(O)=O)=O)NC(=O)C(C(C)CC)NC(=O)C(CO)NC(=O)C(C(C)O)NC(=O)C1CSSCC2NC(=O)C(CC(C)C)NC(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(N)CC=1C=CC=CC=1)C(C)C)CC1=CN=CN1 NOESYZHRGYRDHS-UHFFFAOYSA-N 0.000 description 6
- 238000007418 data mining Methods 0.000 description 4
- 230000037213 diet Effects 0.000 description 4
- 235000005911 diet Nutrition 0.000 description 4
- 229940079593 drug Drugs 0.000 description 4
- 239000003814 drug Substances 0.000 description 4
- 208000024891 symptom Diseases 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 102000004877 Insulin Human genes 0.000 description 3
- 108090001061 Insulin Proteins 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 229940125396 insulin Drugs 0.000 description 3
- 230000001225 therapeutic effect Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 229940088597 hormone Drugs 0.000 description 2
- 239000005556 hormone Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 230000010030 glucose lowering effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 208000017520 skin disease Diseases 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 229940126585 therapeutic drug Drugs 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application provides a method and a device for generating a knowledge graph of diabetic foot and a readable storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring disease corpus data of the relevant field of the diabetic foot; extracting a plurality of disease entities from the disease corpus data; acquiring attribute information of each disease entity, wherein the attribute information is used for representing characteristic information of each disease entity; constructing an incidence relation among a plurality of disease entities by utilizing the attribute information; creating a knowledge base of the diabetic foot based on the associative relationship; and associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot. According to the scheme, the knowledge base of the diabetic foot is established, and then the knowledge base is associated with the pre-established knowledge map framework, so that the knowledge map is generated, and when the knowledge map of the diabetic foot is established, the knowledge map can be established directly based on the knowledge map framework, so that the knowledge map can be established more quickly and more conveniently.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method and a device for generating a knowledge graph of diabetic foot and a readable storage medium.
Background
With the gradual combination of medical systems and the internet, medical systems have been vigorously developed by relying on the internet. As medical data becomes increasingly voluminous, and many valuable information resources are implicated, it is possible to mine these valuable information by analyzing the medical data.
The medical data has the characteristics of pattern polymorphism, incompleteness, timeliness, redundancy, privacy and the like, and challenges are formed in data mining work, especially unstructured data are difficult to analyze, so that data mining aiming at the structured medical data is a breakthrough of medical data mining.
The knowledge graph is structured data, and searching, predicting and other operations can be conveniently carried out by using the knowledge graph. The knowledge graph is combined with data mining, more and more attention is paid to people, in the medical field, a medical knowledge graph is constructed mainly by a doctor manually, however, the workload of manually constructing the knowledge graph is very large, and a large amount of human resources are consumed.
Disclosure of Invention
An embodiment of the present application aims to provide a method and an apparatus for generating a knowledge graph of diabetic foot, and a readable storage medium, so as to solve the problem of heavy workload in constructing the knowledge graph in the prior art.
In a first aspect, an embodiment of the present application provides a method for generating a knowledge map of a diabetic foot, the method including:
acquiring disease corpus data of the relevant field of the diabetic foot;
extracting a plurality of disease entities from the disease corpus data;
acquiring attribute information of each disease entity, wherein the attribute information is used for representing characteristic information of each disease entity;
constructing an incidence relation among the plurality of disease entities by using the attribute information;
creating a knowledge base of the diabetic foot based on the incidence relation;
and associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot.
In the implementation process, the knowledge base of the diabetic foot is constructed, and then the knowledge base is associated with the pre-established knowledge map framework, so that the knowledge map is generated, and the knowledge map of various diseases can be constructed directly based on the knowledge map framework, so that the knowledge map can be constructed more quickly and conveniently.
Optionally, the associating the knowledge base of the diabetic foot with a pre-created knowledge-graph framework to generate the knowledge graph of the diabetic foot includes:
and adding each knowledge point in the knowledge base of the diabetic foot to a corresponding node in the knowledge graph framework to generate the knowledge graph of the diabetic foot.
In the implementation process, each knowledge point is directly added into the knowledge graph framework, and the knowledge graph framework does not need to be created, so that the knowledge graph of the diabetic foot can be quickly generated.
Optionally, the extracting a plurality of disease entities from the disease corpus data includes:
extracting a plurality of initial disease entities from the disease corpus data;
and screening the plurality of initial disease entities to obtain the plurality of screened disease entities.
In the implementation process, a plurality of initial disease entities are screened to screen out entities which do not meet requirements, so that useless data which subsequently participate in the construction of the knowledge base are less, and the constructed knowledge base is more accurate.
Optionally, the screening the plurality of initial disease entities to obtain a remaining plurality of disease entities comprises:
counting the occurrence frequency of each initial disease entity in the disease corpus data;
deleting the initial disease entities with the occurrence frequency less than the preset frequency from the plurality of initial disease entities, and taking the obtained residual initial disease entities as the plurality of disease entities after screening.
In the implementation process, the initial disease entities with the occurrence frequency less than the preset frequency are deleted, so that some useless disease entities can be removed, and the remaining disease entities are useful disease entities.
Optionally, the extracting a plurality of disease entities from the disease corpus data includes:
and identifying a plurality of disease entities in the disease corpus data by adopting a bidirectional long-short term memory network-conditional random field BILSTM-CRF model.
In the implementation process, a BILSTM-CRF model is adopted to accurately and quickly identify a plurality of disease entities in the disease corpus data.
Optionally, after the generating the knowledge-map of the diabetic foot, the method further comprises:
obtaining synonyms of each disease entity and attribute information by using a synonym forest and a word2vec algorithm;
adding the synonym to the knowledge base of the diabetic foot.
In the implementation process, the synonym is obtained, so that the knowledge base of the diabetic foot can be expanded, and the knowledge points of the knowledge base are richer.
Optionally, after the generating the knowledge-map of the diabetic foot, the method further comprises:
the knowledge map of the diabetic foot is stored by using Neo4J and the MongoDB database, so that the data can be conveniently searched.
Optionally, after the generating the knowledge-map of the diabetic foot, the method further comprises:
acquiring query information which is input by a user and related to the diabetic foot;
searching disease knowledge information related to the query information from the knowledge graph of the diabetic foot based on the query information;
and outputting the disease knowledge information to the user.
In the implementation process, the knowledge graph is used for information search, so that the user can conveniently and rapidly inquire the disease knowledge by self.
In a second aspect, the present application provides a diabetes foot knowledge map generation apparatus, including:
the data acquisition module is used for acquiring disease corpus data in the field related to the diabetic foot;
an entity extraction module, configured to extract a plurality of disease entities from the disease corpus data;
the attribute acquisition module is used for acquiring attribute information of each disease entity, and the attribute information is used for representing the characteristic information of each disease entity;
the relationship construction module is used for constructing the incidence relationship among the disease entities by utilizing the attribute information;
a knowledge base acquisition module for creating a knowledge base of the diabetic foot based on the incidence relation;
and the knowledge map generation module is used for associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot.
Optionally, the knowledge graph generating module is configured to add each knowledge point in the knowledge base of the diabetic foot to a corresponding node in the knowledge graph framework, so as to generate the knowledge graph of the diabetic foot.
Optionally, the entity extracting module is configured to extract a plurality of initial disease entities from the disease corpus data; and screening the plurality of initial disease entities to obtain the plurality of screened disease entities.
Optionally, the entity extraction module is configured to count the number of times that each initial disease entity appears in the disease corpus data; deleting the initial disease entities with the occurrence frequency less than the preset frequency from the plurality of initial disease entities, and taking the obtained residual initial disease entities as the plurality of disease entities after screening.
Optionally, the entity extraction module is configured to identify a plurality of disease entities in the disease corpus data by using a bidirectional long-short term memory network-conditional random field BILSTM-CRF model.
Optionally, the apparatus further comprises:
the knowledge base expansion module is used for acquiring synonyms of all disease entities and attribute information by using a synonym forest and a word2vec algorithm; adding the synonym to the knowledge base of the diabetic foot.
Optionally, the apparatus further comprises:
a storage module for storing the knowledge graph of the diabetic foot using Neo4J and a mongodB database.
Optionally, the apparatus further comprises:
the information query module is used for acquiring query information which is input by a user and related to the diabetic foot; searching disease knowledge information related to the query information from the knowledge graph of the diabetic foot based on the query information; and outputting the disease knowledge information to the user.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method as provided in the first aspect are executed.
In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the method as provided in the first aspect.
Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic structural diagram of an electronic device for executing the method for generating a knowledge graph of a diabetic foot according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for generating a knowledge map of a diabetic foot according to an embodiment of the present application;
FIG. 3 is a diagram of a knowledge-graph architecture provided by an embodiment of the present application;
FIG. 4 is a first schematic diagram of a diabetic foot knowledge map provided in an embodiment of the present application;
FIG. 5 is a second schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 6 is a third schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 7 is a fourth schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 8 is a fifth schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 9 is a sixth schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 10 is a seventh schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 11 is an eighth schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
FIG. 12 is a complete schematic view of a diabetic foot knowledge map provided in accordance with an embodiment of the present application;
fig. 13 is a block diagram of a diabetes foot knowledge map generation apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The embodiment of the application provides a method for generating a knowledge graph of a diabetic foot, which comprises the steps of constructing a knowledge base aiming at the diabetic foot, and then associating the knowledge base of the diabetic foot with a pre-established knowledge graph framework to generate the knowledge graph of the diabetic foot.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device for executing the method for generating a knowledge graph of a diabetic foot according to an embodiment of the present application, where the electronic device may include: at least one processor 110, such as a CPU, at least one communication interface 120, at least one memory 130, and at least one communication bus 140. Wherein the communication bus 140 is used for realizing direct connection communication of these components. The communication interface 120 of the device in the embodiment of the present application is used for performing signaling or data communication with other node devices. The memory 130 may be a high-speed RAM memory or a non-volatile memory (e.g., at least one disk memory). Memory 130 may optionally be at least one memory device located remotely from the aforementioned processor. The memory 130 stores computer readable instructions, and when the computer readable instructions are executed by the processor 110, the electronic device executes the method process shown in fig. 2, for example, the memory 130 may be configured to store information such as the disease corpus data, the knowledge graph structure, and the generated knowledge graph of the diabetic foot, and the processor 110 may be configured to obtain the disease corpus data from the memory, and then extract the disease entity therefrom, generate the knowledge graph, and the like.
It will be appreciated that the configuration shown in fig. 1 is merely illustrative and that the electronic device may also include more or fewer components than shown in fig. 1 or have a different configuration than shown in fig. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.
Referring to fig. 2, fig. 2 is a flowchart of a method for generating a knowledge graph of a diabetic foot according to an embodiment of the present application, the method including the following steps:
step S110: disease corpus data in the field related to diabetic foot is obtained.
The disease corpus data may be data of a disease domain in which the diabetic foot is located, diet data of a diet domain corresponding to the diabetic foot, medical data of each hospital for the diabetic foot, relevant research data of the diabetic foot, and the like, and when the diabetic foot is diabetic, the disease corpus data may include symptom data, therapeutic drug data, diet data, and the like of the diabetic foot.
In addition, the disease corpus data may be obtained by crawling a crawler tool from a network, may be obtained from a medical database, or may be obtained in other manners, which is not particularly limited in the embodiment of the present application.
Step S120: extracting a plurality of disease entities from the disease corpus data.
An entity refers to something which is distinguishable and independent, and is an abstraction of an objective individual, and the entity is the most basic element in a knowledge graph, and different relationships exist among different entities. Disease entities are entities extracted from a corpus of diseases, which may include drugs, diseases, symptoms, pictures, therapeutic effects, diet, and the like. Therefore, the names of the disease entities can be identified from the disease corpus data to extract the respective disease entities therefrom.
Step S130: and acquiring attribute information of each disease entity, wherein the attribute information is used for characterizing the characteristic information of each disease entity.
The attribute information may be characteristic information characterizing each entity, for example, for "insulin" as a certain entity, the attribute information may be information such as "white crystalline powder" and "blood sugar-lowering hormone", so that the attribute information of each entity can be obtained for each entity.
The training corpus can be generated through automatic extraction based on semi-structured data of encyclopedic websites and used for training entity attribute labeling models, such as neural network models, and then the training corpus is applied to extraction of attribute information of entities of unstructured data, so that the attribute information of each entity can be obtained.
The attribute information may include an attribute and an attribute value, where the attribute is a blood glucose lowering hormone, the attribute value may be a specific value capable of lowering blood glucose, and the attribute value is used to perform specific mathematical description on the attribute. The attributes and the attribute values are used as the construction basis of the incidence relation between the entities, so that the relation between the entities can be enriched.
Step S140: and constructing the incidence relation among the plurality of disease entities by using the attribute information.
The attribute may be used to abstract the relationship between entities, such as associating entities with the same or similar attribute information, or associating a plurality of disease entities based on the attribute information, so as to construct an association relationship between the plurality of disease entities.
Step S150: creating a knowledge base of the diabetic foot based on the incidence relation.
The disease entities can be related through the association relationship, so that a network knowledge structure can be formed, and the knowledge structure can be used as a knowledge base of the diabetic foot.
Step S160: and associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot.
The knowledge base stores a plurality of knowledge points, the knowledge points comprise each entity and attribute information corresponding to each entity, and the knowledge map framework is used for constructing a knowledge map which is a structural description of the knowledge map, so that the knowledge base and the knowledge map framework can be associated according to the association relation, and the knowledge map of the diabetic foot can be generated.
In the implementation process, the knowledge base of the diabetic foot is constructed, and then the knowledge base is associated with the pre-established knowledge map framework, so that the knowledge map is generated, and the knowledge map of the diabetic foot can be constructed directly based on the knowledge map framework when constructed, so that the knowledge map can be constructed more quickly and conveniently.
The knowledge-graph architecture is described first below.
The knowledge graph architecture provided in the embodiment of the application can be constructed based on a knowledge base architecture of a known network, in the knowledge base architecture of the known network, entities are embodied through nodes, and the entities with the association relationship can be connected through connecting lines by utilizing the association relationship among the entities. In the embodiment of the application, the attributes are independent from the knowledge base architecture of the known network and serve as independent nodes, so that the entities can be associated through the attributes. And simultaneously, the attributes and the attribute values are separated, so that one attribute can be associated with a plurality of attribute values, one attribute value can also correspond to a plurality of attributes to form a many-to-many relationship, and only the connecting line needs to be changed when the relationship between the attributes and the attribute values is operated. Finally integrating the knowledge base architecture of the knowledge network into four structures of events, entities, attributes and attribute values by simple deletion, wherein the root node is a virtual node, and the whole knowledge graph architecture is shown in fig. 3.
After the above-mentioned knowledge graph framework is constructed, in order to generate the knowledge graph of the diabetic foot, each knowledge point in the knowledge base of the diabetic foot may be associated with a corresponding node in the knowledge graph framework to generate the knowledge graph of the diabetic foot.
It is understood that the knowledge-graph framework includes a plurality of nodes for describing entities and attribute information, for example, in fig. 3, event nodes include two major categories of static state and action, where the static state includes two major subclasses of state and relation, and the pain characteristic of the diabetic foot is located under the node of the disease class of the subclass of the state class as the disease state, so that the pain entity can be obtained from the knowledge base of the diabetic foot and added under the corresponding node in the knowledge-graph framework to realize the association with the knowledge-graph framework, as shown in fig. 4.
After adding the knowledge points to the knowledge-graph framework, new nodes can be generated, such as node pain, which includes the degree of the attribute pain, so that the node pain can be associated with the attribute middle degree attribute, thereby associating the event with the attribute, as shown in fig. 5.
All entities related to the diabetic foot are added under the disease state node, and can be expanded by a word2vec algorithm subsequently, and the nodes under the disease state node can also be classified, such as diabetic foot disease state, skin disease state and the like.
Action classes include both real and general classes, action classes being the motives that cause changes in relationships and states, i.e., changes in the nodes of action classes can cause changes in associations between entity nodes, where therapeutic measures "osteotomies" on diabetic feet can be added below the treatment nodes under the real class, as illustrated in fig. 6, where all subsequent therapeutic measures on diabetic feet or other diseases can be added below this node.
The entity node is a description of the objective world, and can include three subclasses of everything, time and space, wherein the diabetes foot is under the class of child node diseases of everything, as shown in fig. 7, and all subsequent information about the disease class can be filled under the disease node.
If the information related to the diabetic foot is excessive, in order to prevent the secondary node of the diabetes from being too bloated, the diabetic foot may be separated as a separate business database, and the separated diabetic foot database may be associated as a value range of the diabetic foot node, as shown in fig. 8.
The insulin, as a drug for treating the diabetic foot, is located under the drug node under the material node, and the treatment means and the treatment drugs of the attributes of the treatment node in the diabetic foot library can be associated with the osteotomy node in the event and the insulin node in the entity node, respectively, as shown in fig. 9.
Any object comprises a plurality of attributes, the exclusive or between the objects is determined by the attributes, and no object is determined by the attributes, wherein the attributes comprise appearance, measurement, characteristics, relations and states, the attribute of the symptom pain degree of the diabetic foot is related to the node of the child nodes of the attribute nodes, as shown in fig. 10, and other attributes can be added at the corresponding nodes.
The attributes are represented by attribute values, the attribute value nodes and the attribute node categories correspond to one another and include appearance values, brightness values, characteristic values, relationship values and state values, the attribute values exist as value domain relationships of the attributes, the attribute of the degree of diabetic foot is associated to the corresponding degree value node in the attribute values, and as shown in fig. 11, the attribute values corresponding to the subsequent attributes are added to the nodes corresponding to the attribute values.
In this way, each knowledge point in the knowledge base of the diabetic foot may be added to a corresponding node in the knowledge graph framework in the above manner, and then the corresponding nodes are associated through value ranges according to the association relationship between each disease entity, so that the knowledge graph of the diabetic foot may be generated, as shown in fig. 12.
Because the knowledge base of the diabetic foot is created based on the association relationship among the entities, and the knowledge base comprises the association relationship among the entities, when the knowledge map of the diabetic foot is generated, the relevant nodes in the knowledge map framework can be associated through the association relationship, and the knowledge map of the diabetic foot can be generated quickly.
It should be noted that, for different diseases, the knowledge graph of the disease can be generated according to the above manner, and the basic knowledge graph architecture is not changed, so that the association relationship between the disease entities can be more intuitively embodied by the knowledge graph architecture, and the information to be queried can be quickly obtained when information search is performed.
As an implementation mode, as the data in the disease corpus data is more, the number of extracted disease entities is larger, and some disease entities may not have actual effects, the disease entities can be screened to reduce the data amount participating in the construction of the knowledge graph and improve the construction efficiency. For example, a plurality of initial disease entities may be extracted from the disease corpus data, and then the plurality of initial disease entities may be screened to obtain a plurality of screened disease entities.
For example, undesirable disease entities of a plurality of initial disease entities may be deleted, or entities that are not disease-related entities may be deleted, or disease entities that appear less frequently in the disease corpus data may also be deleted.
In the implementation process of deleting the disease entities with the smaller occurrence frequency, the occurrence frequency of each initial disease entity in the disease corpus data may be counted first, then the initial disease entities with the occurrence frequency less than the preset frequency are deleted from the plurality of initial disease entities, and the obtained remaining initial disease entities are used as the plurality of screened disease entities.
The preset times can be flexibly set according to actual requirements, namely a plurality of initial disease entities with the occurrence times larger than or equal to the preset times are used as a plurality of screened disease entities, which shows that the disease entities have more occurrence times in the disease corpus data and are possibly more frequent entities in the disease field, so that useless data participating in the construction of the knowledge base are reduced, and the efficiency of creating the knowledge base is improved.
As an embodiment, in order to facilitate rapid extraction of a plurality of disease entities from the disease corpus data, as an embodiment, a Bidirectional Long short term Memory-Conditional Random Field (BILSTM-CRF) model may be used to identify a plurality of disease entities in the disease corpus data.
Among them, the BILSTM-CRF model generally comprises three parts: the method comprises the steps of word representation, context word representation and decoding, wherein the word representation represents each word by using a compact vector, a pre-trained word vector is recorded, the context word representation represents that a meaningful vector representation needs to be provided for each word in a context, a BILSTM model is used for obtaining the vector representation of the word in the context, and the decoding is used for predicting an entity label.
The word vector represents: for each word, a vector needs to be constructed to obtain the meaning of the word and some features useful for entity recognition, the vector is formed by stacking Glove trained word vectors and vectors extracting features from texts, one option is to use manually extracted features, such as feature dictionaries, etc., and another better option is to use some neural network to automatically extract features, in the embodiment of the present application, bilst, of course, other recurrent neural networks, etc. can be used.
Each word that makes up a word is represented by a vector, for each word, the bilst is used, and the final states are stacked to obtain a fixed-length vector, and then the word vector and the word vector are merged to obtain the final vector representation of the word.
After obtaining the final vector representation of each word, the sequence of word vectors is subjected to BILSTM, in which the hidden state at each point in time, not just the final state, can be used to input m word vectors, obtaining m vectors of hidden states, the word vectors only containing word-level information, and the vectors of hidden states taking into account the context, so that a context representation of the word can be obtained.
In the decoding stage, the hidden state vector corresponding to each word is used for final prediction, a fully connected neural network can be used to obtain the score of each entity, and then the sequence with the highest score is found.
In addition, the BILSTM-CRF model can be trained in advance, and a plurality of disease entities in the disease corpus data can be identified by utilizing the trained model, so that the plurality of disease entities can be rapidly acquired from the disease corpus data.
As an embodiment, after the knowledge base of the diabetic foot is generated, synonyms of each disease entity and attribute information may be obtained by using synonym forest and word2vec algorithm, and then the synonyms are added to the knowledge base of the diabetic foot in order to expand the knowledge base.
The synonym forest is used for classifying synonyms of words, after synonyms of all knowledge points in a knowledge base of the diabetic foot are obtained, the synonyms can be added into corresponding nodes in a knowledge graph framework, and if symptom pain exists in the synonym forest, pain, hot and spicy, pain, tenderness, pain and hidden pain exist in the synonym forest, and therefore the synonym forest can be used as attribute values of synonym attributes of the pain to be stored through a cypher grammar.
The word2vec algorithm is a word vector algorithm, is a tool for converting words into vector forms, can simplify the processing of text contents into vector operation in a vector space, calculates the similarity on the vector space to represent the similarity on text semantics, and can calculate related words of each node in a knowledge graph through the word2vec algorithm, so that the related words of the nodes can be added into a knowledge base to fill the knowledge base.
For example, the word vector of the existing wikipedia training can be utilized, and the word vector can also be obtained by utilizing a word2vec tool based on the corpus of the medical field. And traversing nodes in the knowledge base, counting words with similarity greater than a threshold value with the nodes by using word2vec, and storing the words as attribute values of the nodes so as to expand the knowledge base. If the node "pain" is calculated by using word2vec that the word with the similarity larger than 0.8 has "pain" or "pain", the two words can be stored in the knowledge base as the attribute value of the attribute of the synonym of the node "pain" by using the cypher grammar.
In the implementation process, the synonym is obtained, so that the knowledge base of the diabetic foot can be expanded, and the knowledge points of the knowledge base are richer.
In addition, to facilitate the storage of the knowledge-maps, Neo4J and the MongoDB database may also be used to store the knowledge-maps of the diabetic foot.
Neo4J is an image database, Neo4J is a raw image calculation engine, and data stored and used by the engine are processed by using raw image structure data all the time, so that the performance of the knowledge map can be improved by using the Neo 4J-based image database to store the knowledge map, data can be stored quickly, real-time response can be realized, and the efficiency of anomaly detection on the knowledge map can be improved.
However, if there are too many attributes under the nodes in the knowledge graph or the data types unsupported by Neo4J are searched, the performance of the knowledge graph is affected, so Neo4J combined with MongoDB can be used for storing the knowledge graph. MongoDB can hold a plurality of modeless data as a document type database, the data is easily stored as a tree structure, but the tree can only express the dependency relationship from top to bottom, and redundant data which is embedded for a plurality of times always appears in the tree storage structure, so that the difficulty of updating the data is increased, the consistency of the data is difficult to ensure, if the redundant data is removed, and then the data with the mutual relationship is associated by a graph structure, the data redundancy problem is solved, the association relationship among the data becomes more visual, so that the related relationship part can be saved by Neo4J, the instantiated node information is saved by the MongoDB, the form is simpler, the problems of data redundancy and consistency are avoided, and the efficiency of data searching can be improved.
In addition, the knowledge graph of the diabetic foot can be applied to multiple aspects, such as semantic search, personalized recommendation, intelligent question answering and intelligent diagnosis guidance, and the application of the knowledge graph in an intelligent diagnosis guidance scene is simply introduced below.
As one implementation mode, inquiry information which is input by a user and related to the diabetic foot is obtained, disease knowledge information which is related to the inquiry information is searched from a knowledge graph of the diabetic foot based on the inquiry information, and then the disease knowledge information is output to the user.
The method includes the steps that a user can input query information for querying the diabetic foot on a terminal interface, after the query information is obtained by the electronic device, semantic understanding or analysis is carried out on the query information, disease knowledge information relevant to the query information is searched from a knowledge graph and output to the user, so that the user can consult to obtain some relevant knowledge of the diabetic foot, such as some simple diseases or emergency diseases, and the user can carry out emergency treatment on the diseases based on the output disease knowledge information.
In the implementation process, the knowledge graph is used for information search, so that the user can conveniently and rapidly inquire the disease knowledge by self.
Referring to fig. 13, fig. 13 is a block diagram of a diabetes foot knowledge graph generating apparatus 200 according to an embodiment of the present application, where the apparatus 200 may be a module, a program segment, or code on an electronic device. It should be understood that the apparatus 200 corresponds to the above-mentioned embodiment of the method of fig. 2, and can perform various steps related to the embodiment of the method of fig. 2, and the specific functions of the apparatus 200 can be referred to the above description, and the detailed description is appropriately omitted here to avoid redundancy.
Optionally, the apparatus 200 comprises:
the data acquisition module 210 is configured to acquire corpus data of diseases in the field related to diabetic foot;
an entity extraction module 220, configured to extract a plurality of disease entities from the disease corpus data;
an attribute obtaining module 230, configured to obtain attribute information of each disease entity, where the attribute information is used to characterize feature information of each disease entity;
a relationship construction module 240, configured to construct an association relationship between the disease entities by using the attribute information;
a knowledge base acquisition module 250 configured to create a knowledge base of the diabetic foot based on the association relationship;
a knowledge map generation module 260, configured to associate the knowledge base of the diabetic foot with a pre-created knowledge map framework, and generate a knowledge map of the diabetic foot.
Optionally, the knowledge-graph generating module 260 is configured to add each knowledge point in the knowledge base of the diabetic foot to a corresponding node in the knowledge-graph framework, so as to generate the knowledge graph of the diabetic foot.
Optionally, the entity extracting module 220 is configured to extract a plurality of initial disease entities from the disease corpus data; and screening the plurality of initial disease entities to obtain the plurality of screened disease entities.
Optionally, the entity extracting module 220 is configured to count the number of times that each initial disease entity appears in the disease corpus data; deleting the initial disease entities with the occurrence frequency less than the preset frequency from the plurality of initial disease entities, and taking the obtained residual initial disease entities as the plurality of disease entities after screening.
Optionally, the entity extraction module 220 is configured to identify a plurality of disease entities in the disease corpus data by using a bidirectional long-short term memory network-conditional random field bilst-CRF model.
Optionally, the apparatus 200 further includes:
the knowledge base expansion module is used for acquiring synonyms of all disease entities and attribute information by using a synonym forest and a word2vec algorithm; adding the synonym to the knowledge base of the diabetic foot.
Optionally, the apparatus 200 further includes:
a storage module for storing the knowledge graph of the diabetic foot using Neo4J and a mongodB database.
Optionally, the apparatus 200 further includes:
the information query module is used for acquiring query information which is input by a user and related to the diabetic foot; searching disease knowledge information related to the query information from the knowledge graph of the diabetic foot based on the query information; and outputting the disease knowledge information to the user.
The embodiment of the present application provides a readable storage medium, and when being executed by a processor, the computer program performs the method process performed by the electronic device in the method embodiment shown in fig. 2.
The present embodiments disclose a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments, for example, comprising: acquiring disease corpus data of the relevant field of the diabetic foot; extracting a plurality of disease entities from the disease corpus data; acquiring attribute information of each disease entity, wherein the attribute information is used for representing characteristic information of each disease entity; constructing an incidence relation among the plurality of disease entities by using the attribute information; creating a knowledge base of the diabetic foot based on the incidence relation; and associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot.
In summary, the embodiments of the present application provide a method, an apparatus, and a readable storage medium for generating a knowledge graph of a diabetic foot, in which a knowledge base of the diabetic foot is constructed, and then the knowledge base is associated with a pre-created knowledge graph framework, so as to generate the knowledge graph, so that when the knowledge graph of the diabetic foot is constructed, the construction can be directly performed based on the knowledge graph framework, and thus, the knowledge graph can be constructed more quickly and more conveniently.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for generating a diabetic foot knowledge map, the method comprising:
acquiring disease corpus data of the relevant field of the diabetic foot;
extracting a plurality of disease entities from the disease corpus data;
acquiring attribute information of each disease entity, wherein the attribute information is used for representing characteristic information of each disease entity;
constructing an incidence relation among the plurality of disease entities by using the attribute information;
creating a knowledge base of the diabetic foot based on the incidence relation;
and associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot.
2. The method of claim 1, wherein associating the knowledge base of the diabetic foot with a pre-created knowledge-graph framework to generate the knowledge graph of the diabetic foot comprises:
and adding each knowledge point in the knowledge base of the diabetic foot to a corresponding node in the knowledge graph framework to generate the knowledge graph of the diabetic foot.
3. The method according to claim 1, wherein said extracting a plurality of disease entities from said disease corpus data comprises:
extracting a plurality of initial disease entities from the disease corpus data;
and screening the plurality of initial disease entities to obtain the plurality of screened disease entities.
4. The method of claim 3, wherein said screening said plurality of initial disease entities for a remaining plurality of disease entities comprises:
counting the occurrence frequency of each initial disease entity in the disease corpus data;
deleting the initial disease entities with the occurrence frequency less than the preset frequency from the plurality of initial disease entities, and taking the obtained residual initial disease entities as the plurality of disease entities after screening.
5. The method according to claim 1, wherein said extracting a plurality of disease entities from said disease corpus data comprises:
and identifying a plurality of disease entities in the disease corpus data by adopting a bidirectional long-short term memory network-conditional random field BILSTM-CRF model.
6. The method of claim 1, wherein after generating the knowledge-map of the diabetic foot, further comprising:
obtaining synonyms of each disease entity and attribute information by using a synonym forest and a word2vec algorithm;
adding the synonym to the knowledge base of the diabetic foot.
7. The method of claim 1, wherein after generating the knowledge-map of the diabetic foot, further comprising:
the knowledge map of the diabetic foot was stored using Neo4J and the MongoDB database.
8. The method of any one of claims 1-7, wherein after generating the knowledge-map of the diabetic foot, further comprising:
acquiring query information which is input by a user and related to the diabetic foot;
searching disease knowledge information related to the query information from the knowledge graph of the diabetic foot based on the query information;
and outputting the disease knowledge information to the user.
9. A diabetic foot knowledge map generation apparatus, the apparatus comprising:
the data acquisition module is used for acquiring disease corpus data in the field related to the diabetic foot;
an entity extraction module, configured to extract a plurality of disease entities from the disease corpus data;
the attribute acquisition module is used for acquiring attribute information of each disease entity, and the attribute information is used for representing the characteristic information of each disease entity;
the relationship construction module is used for constructing the incidence relationship among the disease entities by utilizing the attribute information;
a knowledge base acquisition module for creating a knowledge base of the diabetic foot based on the incidence relation;
and the knowledge map generation module is used for associating the knowledge base of the diabetic foot with a pre-established knowledge map framework to generate the knowledge map of the diabetic foot.
10. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010110297.2A CN111341456B (en) | 2020-02-21 | 2020-02-21 | Method and device for generating diabetic foot knowledge graph and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010110297.2A CN111341456B (en) | 2020-02-21 | 2020-02-21 | Method and device for generating diabetic foot knowledge graph and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111341456A true CN111341456A (en) | 2020-06-26 |
| CN111341456B CN111341456B (en) | 2024-02-23 |
Family
ID=71186964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010110297.2A Active CN111341456B (en) | 2020-02-21 | 2020-02-21 | Method and device for generating diabetic foot knowledge graph and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111341456B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112002411A (en) * | 2020-08-20 | 2020-11-27 | 杭州电子科技大学 | Cardiovascular and cerebrovascular disease knowledge map question-answering method based on electronic medical record |
| CN112466463A (en) * | 2020-12-10 | 2021-03-09 | 求臻医学科技（北京）有限公司 | Intelligent answering system based on tumor accurate diagnosis and treatment knowledge graph |
| CN112635071A (en) * | 2020-12-25 | 2021-04-09 | 中国矿业大学 | Diabetes knowledge map construction method integrating traditional Chinese and western medicine knowledge |
| CN112966053A (en) * | 2020-09-18 | 2021-06-15 | 青岛海洋科学与技术国家实验室发展中心 | Knowledge graph-based marine field expert database construction method and device |
| CN113204626A (en) * | 2021-04-30 | 2021-08-03 | 平安科技（深圳）有限公司 | Interaction method, device, terminal and storage medium based on knowledge graph |
| CN113704394A (en) * | 2021-06-29 | 2021-11-26 | 中国科学院微生物研究所 | Coronavirus information searching and coronavirus information presenting methods and devices |
| CN113704492A (en) * | 2021-08-26 | 2021-11-26 | 山东大学 | Construction method and system of elderly care data knowledge graph |
| CN113779178A (en) * | 2021-09-13 | 2021-12-10 | 国网电子商务有限公司 | Data storage method and device based on knowledge graph |
| CN114758749A (en) * | 2022-03-23 | 2022-07-15 | 清华大学 | Nutritional diet management map creation method and device based on gestation period |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104094266A (en) * | 2011-11-07 | 2014-10-08 | 独创系统公司 | Methods and systems for identification of causal genomic variants |
| CN106021281A (en) * | 2016-04-29 | 2016-10-12 | 京东方科技集团股份有限公司 | Method for establishing medical knowledge graph, device for same and query method for same |
| EP3223180A1 (en) * | 2016-03-24 | 2017-09-27 | Fujitsu Limited | A system and a method for assessing patient risk using open data and clinician input |
| US20180137249A1 (en) * | 2016-11-14 | 2018-05-17 | International Business Machines Corporation | Extending Medical Condition Base Cartridges Based on SME Knowledge Extensions |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
| CN109543047A (en) * | 2018-11-21 | 2019-03-29 | 焦点科技股份有限公司 | A kind of knowledge mapping construction method based on medical field website |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
| CN109635121A (en) * | 2018-11-07 | 2019-04-16 | 平安科技（深圳）有限公司 | Medical knowledge map creation method and relevant apparatus |
| CN109766445A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | A kind of knowledge mapping construction method and data processing equipment |
| CN109830303A (en) * | 2019-02-01 | 2019-05-31 | 上海众恒信息产业股份有限公司 | Clinical data mining analysis and aid decision-making method based on internet integration medical platform |
| CN110222201A (en) * | 2019-06-26 | 2019-09-10 | 中国医学科学院医学信息研究所 | A kind of disease that calls for specialized treatment knowledge mapping construction method and device |
| CN110289101A (en) * | 2019-07-02 | 2019-09-27 | 京东方科技集团股份有限公司 | A kind of computer equipment, system and readable storage medium storing program for executing |
| CN110532360A (en) * | 2019-07-19 | 2019-12-03 | 平安科技（深圳）有限公司 | Medical field knowledge mapping question and answer processing method, device, equipment and storage medium |
| WO2020007224A1 (en) * | 2018-07-06 | 2020-01-09 | 中兴通讯股份有限公司 | Knowledge graph construction and smart response method and apparatus, device, and storage medium |
| CN110688488A (en) * | 2018-06-20 | 2020-01-14 | 南京网感至察信息科技有限公司 | Universal knowledge graph cloud service system |
| EP3608795A1 (en) * | 2018-08-08 | 2020-02-12 | Beijing Baidu Netcom Science and Technology Co., Ltd. | Method and apparatus for generating knowledge graph, device and computer readable storage medium |
| CN110807091A (en) * | 2019-03-01 | 2020-02-18 | 王涵 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011069782A1 (en) * | 2009-12-10 | 2011-06-16 | International Business Machines Corporation | A method and a system for plug and play support of computer architectures |
| GB2590185B (en) * | 2018-04-23 | 2022-09-28 | Seer Inc | Systems and methods for complex biomolecule sampling and biomarker discovery |
-
2020
- 2020-02-21 CN CN202010110297.2A patent/CN111341456B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104094266A (en) * | 2011-11-07 | 2014-10-08 | 独创系统公司 | Methods and systems for identification of causal genomic variants |
| EP3223180A1 (en) * | 2016-03-24 | 2017-09-27 | Fujitsu Limited | A system and a method for assessing patient risk using open data and clinician input |
| CN106021281A (en) * | 2016-04-29 | 2016-10-12 | 京东方科技集团股份有限公司 | Method for establishing medical knowledge graph, device for same and query method for same |
| US20180137249A1 (en) * | 2016-11-14 | 2018-05-17 | International Business Machines Corporation | Extending Medical Condition Base Cartridges Based on SME Knowledge Extensions |
| CN110688488A (en) * | 2018-06-20 | 2020-01-14 | 南京网感至察信息科技有限公司 | Universal knowledge graph cloud service system |
| WO2020007224A1 (en) * | 2018-07-06 | 2020-01-09 | 中兴通讯股份有限公司 | Knowledge graph construction and smart response method and apparatus, device, and storage medium |
| EP3608795A1 (en) * | 2018-08-08 | 2020-02-12 | Beijing Baidu Netcom Science and Technology Co., Ltd. | Method and apparatus for generating knowledge graph, device and computer readable storage medium |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109346169A (en) * | 2018-10-17 | 2019-02-15 | 长沙瀚云信息科技有限公司 | A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium |
| CN109635121A (en) * | 2018-11-07 | 2019-04-16 | 平安科技（深圳）有限公司 | Medical knowledge map creation method and relevant apparatus |
| CN109543047A (en) * | 2018-11-21 | 2019-03-29 | 焦点科技股份有限公司 | A kind of knowledge mapping construction method based on medical field website |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
| CN109766445A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | A kind of knowledge mapping construction method and data processing equipment |
| CN109830303A (en) * | 2019-02-01 | 2019-05-31 | 上海众恒信息产业股份有限公司 | Clinical data mining analysis and aid decision-making method based on internet integration medical platform |
| CN110807091A (en) * | 2019-03-01 | 2020-02-18 | 王涵 | Hotel intelligent question-answer recommendation and decision support analysis method and system |
| CN110222201A (en) * | 2019-06-26 | 2019-09-10 | 中国医学科学院医学信息研究所 | A kind of disease that calls for specialized treatment knowledge mapping construction method and device |
| CN110289101A (en) * | 2019-07-02 | 2019-09-27 | 京东方科技集团股份有限公司 | A kind of computer equipment, system and readable storage medium storing program for executing |
| CN110532360A (en) * | 2019-07-19 | 2019-12-03 | 平安科技（深圳）有限公司 | Medical field knowledge mapping question and answer processing method, device, equipment and storage medium |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112002411A (en) * | 2020-08-20 | 2020-11-27 | 杭州电子科技大学 | Cardiovascular and cerebrovascular disease knowledge map question-answering method based on electronic medical record |
| CN112966053B (en) * | 2020-09-18 | 2023-04-18 | 青岛海洋科学与技术国家实验室发展中心 | Knowledge graph-based marine field expert database construction method and device |
| CN112966053A (en) * | 2020-09-18 | 2021-06-15 | 青岛海洋科学与技术国家实验室发展中心 | Knowledge graph-based marine field expert database construction method and device |
| CN112466463A (en) * | 2020-12-10 | 2021-03-09 | 求臻医学科技（北京）有限公司 | Intelligent answering system based on tumor accurate diagnosis and treatment knowledge graph |
| CN112466463B (en) * | 2020-12-10 | 2023-08-18 | 求臻医学科技(浙江)有限公司 | Intelligent answering system based on tumor accurate diagnosis and treatment knowledge graph |
| CN112635071A (en) * | 2020-12-25 | 2021-04-09 | 中国矿业大学 | Diabetes knowledge map construction method integrating traditional Chinese and western medicine knowledge |
| CN112635071B (en) * | 2020-12-25 | 2024-03-01 | 中国矿业大学 | Diabetes knowledge graph construction method integrating Chinese and Western medicine knowledge |
| CN113204626A (en) * | 2021-04-30 | 2021-08-03 | 平安科技（深圳）有限公司 | Interaction method, device, terminal and storage medium based on knowledge graph |
| CN113704394A (en) * | 2021-06-29 | 2021-11-26 | 中国科学院微生物研究所 | Coronavirus information searching and coronavirus information presenting methods and devices |
| CN113704492A (en) * | 2021-08-26 | 2021-11-26 | 山东大学 | Construction method and system of elderly care data knowledge graph |
| CN113704492B (en) * | 2021-08-26 | 2024-02-27 | 山东大学 | Construction method and system of elderly care data knowledge graph |
| CN113779178A (en) * | 2021-09-13 | 2021-12-10 | 国网电子商务有限公司 | Data storage method and device based on knowledge graph |
| CN114758749A (en) * | 2022-03-23 | 2022-07-15 | 清华大学 | Nutritional diet management map creation method and device based on gestation period |
| CN114758749B (en) * | 2022-03-23 | 2023-08-25 | 清华大学 | Nutritional diet management map creation method and device based on gestation period |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111341456B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111341456B (en) | Method and device for generating diabetic foot knowledge graph and readable storage medium | |
| US9558264B2 (en) | Identifying and displaying relationships between candidate answers | |
| US20190035505A1 (en) | Intelligent triage server, terminal and system based on medical knowledge base (mkb) | |
| CN113707297B (en) | Medical data processing method, device, equipment and storage medium | |
| US8700589B2 (en) | System for linking medical terms for a medical knowledge base | |
| CN110275894B (en) | Knowledge graph updating method and device, electronic equipment and storage medium | |
| US9621601B2 (en) | User collaboration for answer generation in question and answer system | |
| CN112528660B (en) | Method, apparatus, device, storage medium and program product for processing text | |
| Zhang et al. | Extracting databases from dark data with deepdive | |
| US20070005621A1 (en) | Information system using healthcare ontology | |
| US20210034919A1 (en) | Method and apparatus for establishing image set for image recognition, network device, and storage medium | |
| Ferrari et al. | Pragmatic ambiguity detection in natural language requirements | |
| WO2015093540A1 (en) | Phrase pair gathering device and computer program therefor | |
| JP2007317188A (en) | Data intelligent processing system and its method | |
| CN111460095B (en) | Question-answering processing method and device, electronic equipment and storage medium | |
| CN110612522B (en) | Establishment of solid model | |
| Batra et al. | Organizing standardized electronic healthcare records data for mining | |
| WO2015093539A1 (en) | Complex predicate template gathering device, and computer program therefor | |
| CN111930962A (en) | Document data value evaluation method and device, electronic equipment and storage medium | |
| CN116682553A (en) | Diagnosis recommendation system integrating knowledge and patient representation | |
| CN113779272A (en) | Data processing method, device and equipment based on knowledge graph and storage medium | |
| CN114610902A (en) | Poultry disease diagnosis system based on knowledge graph | |
| JP2016505973A (en) | User interface for predictive model generation | |
| CN113392220B (en) | Knowledge graph generation method and device, computer equipment and storage medium | |
| CN113434697A (en) | Event element extraction method, computer device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |