CN111986742A - Method for constructing orthopedics knowledge graph - Google Patents
Method for constructing orthopedics knowledge graph Download PDFInfo
- Publication number
- CN111986742A CN111986742A CN202010641087.6A CN202010641087A CN111986742A CN 111986742 A CN111986742 A CN 111986742A CN 202010641087 A CN202010641087 A CN 202010641087A CN 111986742 A CN111986742 A CN 111986742A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- orthopedics
- orthopedic
- constructing
- relationship
- 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
- 230000000399 orthopedic effect Effects 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 3
- 230000005540 biological transmission Effects 0.000 abstract 1
- 201000010099 disease Diseases 0.000 description 7
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 7
- 208000003947 Knee Osteoarthritis Diseases 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 201000008482 osteoarthritis Diseases 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013150 knee replacement Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 206010072970 Meniscus injury Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011883 total knee arthroplasty Methods 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a method for constructing an orthopedics knowledge graph, which comprises the following steps: acquiring orthopedic clinical knowledge; structuring the orthopedic clinical knowledge to form structured data; expressing the structured data into a plurality of triples, each triplet representing a piece of knowledge; connecting all knowledge to form an orthopedics knowledge map; and storing the orthopedics knowledge graph. The method for constructing the orthopedics knowledge graph has high efficiency and low cost; is beneficial to the rapid and efficient transmission and communication of the orthopedics knowledge.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a method for constructing an orthopedics knowledge graph.
Background
Knowledge graph is a knowledge representation and management mode, and emphasizes semantic retrieval capability. In recent years, under the vigorous development of artificial intelligence, key problems related to the knowledge map, such as knowledge extraction, representation, fusion, reasoning, question answering and the like, are solved and broken through to a certain extent, and the knowledge map becomes a new hot point in the field of knowledge services and is widely concerned by scholars and industry at home and abroad.
The construction of the knowledge graph is the core of the application of the artificial intelligence technology in the specific industry field at present. With the development of science and technology, the speed of updating and extending knowledge in the orthopedic field is extremely high, wherein only a small amount of knowledge can be inquired and browsed through various encyclopedia websites, and the knowledge is unstructured and semi-structured data; most of the updated knowledge needs to be added to books and documents, and communication through the books and documents is inconvenient, and easily causes information lag.
If books, documents and various updated knowledge data in the orthopedics field can be displayed in the form of an orthopedics knowledge map, the method is not only beneficial to the communication of knowledge, but also beneficial to the development of the whole orthopedics subject.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a method for constructing an orthopedics knowledge graph.
According to one aspect of the present invention, there is provided a method of constructing an orthopedic knowledgemap, the method comprising the steps of:
acquiring orthopedic requirements and clinical knowledge;
structuring orthopedic requirements and clinical knowledge to form structured data;
expressing the structured data into a plurality of triples, each triplet representing a piece of knowledge;
connecting all knowledge to form an orthopedics knowledge map;
and storing the orthopedics knowledge graph.
According to a specific embodiment of the present invention, the triplets are composed of entities and relationships.
According to another embodiment of the invention, the entity comprises: classification labels, and/or label values.
According to a further embodiment of the invention, the tag value is determined by extraction by means of an SVM.
According to yet another embodiment of the invention, the relationship comprises:
classifying the hierarchical relationship between the labels;
the inclusion relationship of the tag and the tag value; and/or the presence of a gas in the gas,
the logical relationship of the tag value to the tag value.
According to yet another embodiment of the invention, there is a connection between entities that have a relationship with each other in the orthopedic knowledgegraph.
According to yet another embodiment of the invention, the entity is formed by a deep learning model.
According to yet another embodiment of the present invention, the orthopedic knowledge map is stored using a map database technique.
The method for constructing the orthopedics knowledge graph does not need to invest a large amount of labor and time, and is high in efficiency and low in cost; the constructed orthopedics knowledge map is beneficial to browsing, learning and exchanging orthopedics knowledge.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a method for constructing an orthopedic knowledgegraph in accordance with the present invention;
FIG. 2 is a diagram illustrating one embodiment of logical relationships represented as triples;
fig. 3 is a schematic diagram illustrating an embodiment of an orthopedics knowledge graph constructed by the method for constructing the orthopedics knowledge graph provided by the invention.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. It should be noted that the components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and procedures are omitted so as to not unnecessarily limit the invention.
Referring to fig. 1, the present invention claims a method for constructing an orthopedic knowledgegraph, the method comprising the steps of:
and step S101, acquiring orthopedic clinical knowledge. Documents, networks, books, clinical records and the like from various sources can be obtained. Preferably, the orthopedics clinical knowledge is stored in a text form.
And S102, structuring the orthopedic clinical knowledge to form structured data. When the orthopedics clinical knowledge is stored in a text form, the orthopedics clinical knowledge is structured on the original text storing the orthopedics clinical knowledge to form structured data. Because the obtained various orthopedic clinical knowledge are independent files, most of the orthopedic clinical knowledge are unstructured or semi-structured data; even if individual files have their own structure, there is no connection between these files. In order to make the data information more usable, it needs to be structured to form structured data.
Step S103, expressing the structured data into a plurality of triples, wherein each triplet represents a piece of knowledge. The triplets are composed of entities and relationships.
The entities are formed by a deep learning model. The entity includes: classification label, label and/or label value.
If there is no hierarchical relationship between tags and no business logic connection between tags, there is a lack of guidance and criteria when tagging structured data. The result of this is that some structured data have more labels and richer semantics; and the quantity of labels on some structured data is small, and the semantics is deficient. This imbalance of labels can reduce the accuracy and usability of the final formed orthopedic knowledgemap.
In order to avoid the above problems, the relationships in the triplets of the present invention include the following: classifying the hierarchical relationship between the labels; the inclusion relationship of the tag and the tag value; and/or a logical relationship of the tag value to the tag value.
The following illustrates the three relationships:
1. the hierarchical relationships are represented as triplets: the hierarchical relationship, such as "device type is a medium", can be expressed as: media, including, device type.
2. The relationship of the tags and tag values constitutes a triplet: if "the device type includes the value CT", the relationship can be expressed as: the device type includes a value, CT.
3. The logical relationships are represented as triplets: the logical relationship of "total knee arthroplasty for treating the advanced stage of knee osteoarthritis" can be expressed as follows: total knee replacement, treatment, late knee osteoarthritis, as shown in fig. 2.
And step S104, connecting all knowledge to form a knowledge graph. Because each triple represents a piece of knowledge, we connect several triples together, that is, connect knowledge together, i.e., form a knowledge graph.
It should be noted, however, that in the knowledge-graph, not every two entities will have a connection, and only two entities will have the relationship described in step S103. Preferably, there is a hierarchical or logical relationship between the two entities that will be connected.
And step S105, storing the knowledge graph. Preferably, the orthopedics knowledge graph is stored by adopting a graph database technology.
The construction process of an orthopedics knowledge graph is shown in the form of a specific embodiment.
Because the method is applied to the field of orthopedics, unified tags are needed when the orthopedics requirements and clinical knowledge are acquired and structured and then structured data are expressed as triples.
Firstly, the classification label, the label and the label value and the relation between the entities are determined, and the process is as follows:
in the field of orthopedic image application, there are three main categories of classification labels: "patient information", "disease stage" and "medium".
Under the classification label, the specific information of the label is obtained. For example: under the "patient information" class, a "patient ID" tag is required; under the "disease stage" category, attention needs to be paid to "disease" and "surgery" labels; under "media", attention is paid to the type of "photographing device".
Next, adding a specific tag value to each tag, for example, adding tag values such as "camera shooting", "CT" and the like under "shooting device"; the label values of meniscus injury, knee osteoarthritis and the like are increased under the label of disease.
For the sake of distinction, every addition of one entity: a classification label (e.g., "stage of disease"), a label (e.g., "disease"), or a label value (e.g., "meniscal damage") is set to an ID.
Preferably, an automatic numbering rule (e.g. increasing number from 1) is used to distinguish these entities. For example, the value corresponding to the "patient ID" tag is determined by the automatic numbering rule, so that the value is irrelevant to the personal information (such as name, hospital number, medical insurance information, etc.) of the patient, and the purpose of protecting the privacy of the patient can be achieved.
The logical relationships that exist in the individual label values are then listed according to clinical knowledge. For example, the value of the "Total Knee replacement" label for "surgery" is linked to the value of the "disease" label for "osteoarthritis of the knee". Fig. 3 is a schematic diagram of one embodiment of the orthopedics knowledge graph, as shown in fig. 3.
Preferably, in the process of constructing the orthopedics knowledge graph, a larger-scale corpus is adopted for calculation and analysis to obtain entities and the relationship between the entities. The method has the advantages of high standardization degree, time saving, high efficiency and accuracy. In addition, in the process of labeling the structured data, whether the entity in the triple needs to be labeled with a specific label or not can be automatically judged by means of an image deep learning model, so that the labeling efficiency can be further improved.
The method for constructing the orthopedics knowledge graph provided by the invention has the advantages of low cost and high efficiency.
Although the present invention has been described in detail with respect to the exemplary embodiments and advantages thereof, it should be understood that various changes, substitutions, and alterations can be made hereto without departing from the spirit and scope of the invention as defined by the appended claims. For other examples, one of ordinary skill in the art will readily appreciate that the order of the process steps may be varied while maintaining the scope of the present invention.
Moreover, the scope of the present application is not intended to be limited to the particular embodiments of the process, machine, manufacture, composition of matter, means, methods and steps described in the specification. As one of ordinary skill in the art will readily appreciate from the disclosure of the present invention, processes, machines, manufacture, compositions of matter, means, methods, or steps, presently existing or later to be developed, that perform substantially the same function or achieve substantially the same result as the corresponding embodiments described herein may be utilized according to the present invention. Accordingly, the appended claims are intended to include within their scope such processes, machines, manufacture, compositions of matter, means, methods, or steps.
Claims (8)
1. A method of constructing an orthopedic knowledgemap, the method comprising the steps of:
acquiring orthopedic clinical knowledge;
structuring the orthopedic clinical knowledge to form structured data;
expressing the structured data into a plurality of triples, each triplet representing a piece of knowledge;
connecting all knowledge to form an orthopedics knowledge map;
and storing the orthopedics knowledge graph.
2. The method of claim 1, wherein the triples are comprised of entities and relationships.
3. The method of claim 2, wherein the entity comprises: classification labels, and/or label values.
4. The method of claim 3, wherein the tag value is determined by extraction using an SVM.
5. The method of claim 2, wherein the relationship comprises:
classifying the hierarchical relationship between the labels;
the inclusion relationship of the tag and the tag value; and/or the presence of a gas in the gas,
the logical relationship of the tag value to the tag value.
6. The method of claim 5, wherein there are connections between entities that have relationships with each other in the orthopedic knowledgegraph.
7. The method of claim 2, wherein the entity is formed by a deep learning model.
8. The method of claim 1, wherein the orthopedic knowledgemaps are stored using graph database technology.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010641087.6A CN111986742A (en) | 2020-07-06 | 2020-07-06 | Method for constructing orthopedics knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010641087.6A CN111986742A (en) | 2020-07-06 | 2020-07-06 | Method for constructing orthopedics knowledge graph |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111986742A true CN111986742A (en) | 2020-11-24 |
Family
ID=73439021
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010641087.6A Pending CN111986742A (en) | 2020-07-06 | 2020-07-06 | Method for constructing orthopedics knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111986742A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107657063A (en) * | 2017-10-30 | 2018-02-02 | 合肥工业大学 | The construction method and device of medical knowledge collection of illustrative plates |
CN109508383A (en) * | 2018-10-30 | 2019-03-22 | 北京国双科技有限公司 | The construction method and device of knowledge mapping |
CN109559822A (en) * | 2018-11-12 | 2019-04-02 | 平安科技(深圳)有限公司 | Intelligent first visit method, apparatus, computer equipment and storage medium |
CN110704631A (en) * | 2019-08-16 | 2020-01-17 | 北京紫冬认知科技有限公司 | Construction method and device of medical knowledge map |
-
2020
- 2020-07-06 CN CN202010641087.6A patent/CN111986742A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107657063A (en) * | 2017-10-30 | 2018-02-02 | 合肥工业大学 | The construction method and device of medical knowledge collection of illustrative plates |
CN109508383A (en) * | 2018-10-30 | 2019-03-22 | 北京国双科技有限公司 | The construction method and device of knowledge mapping |
CN109559822A (en) * | 2018-11-12 | 2019-04-02 | 平安科技(深圳)有限公司 | Intelligent first visit method, apparatus, computer equipment and storage medium |
CN110704631A (en) * | 2019-08-16 | 2020-01-17 | 北京紫冬认知科技有限公司 | Construction method and device of medical knowledge map |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
McAllister et al. | Mapping a discipline: a guide to using VOSviewer for bibliometric and visual analysis | |
US7103609B2 (en) | System and method for analyzing usage patterns in information aggregates | |
US7257569B2 (en) | System and method for determining community overlap | |
US20090083231A1 (en) | System and method for analyzing electronic data records | |
CN106663101A (en) | Ontology mapping method and apparatus | |
CN110033837A (en) | The method for generating user's portrait and knowledge mapping based on electronic health record | |
CN104769588B (en) | Queue identifying system | |
US9594755B2 (en) | Electronic document repository system | |
CN103425740A (en) | IOT (Internet Of Things) faced material information retrieval method based on semantic clustering | |
Chu et al. | Knowledge representation and retrieval using conceptual graphs and free text document self-organisation techniques | |
CN111984805A (en) | Method for establishing orthopedics cloud image database based on orthopedics knowledge graph | |
CN103309879A (en) | Method and device for managing marks in WORD document | |
Duong et al. | A hybrid method for integrating multiple ontologies | |
Diallo | Efficient building of local repository of distributed ontologies | |
Sharma et al. | Developing corporate taxonomies for knowledge auditability-a framework for good practices | |
Shepherd | Challenges in health informatics | |
CN111986742A (en) | Method for constructing orthopedics knowledge graph | |
Bermudez-Edo et al. | Managing technological knowledge of patents: HCOntology, a semantic approach | |
Diallo et al. | Process of building a vocabulary for the infection domain | |
KR101097195B1 (en) | A terminology editing system based on the reference terminology | |
CN116737945B (en) | Mapping method for EMR knowledge map of patient | |
Li et al. | Unlocking our Behavioral Knowledge Inheritance through Ontology Learning: A Design Framework, an Instantiation, and a Randomized Experiment | |
CN113205881B (en) | OpenEHR prototype and template automatic generation method based on thought guide graph | |
Toh et al. | Building an ontological framework for healthcare: The case of the health cluster | |
Koutela | Data analysis from the Greek National Catalogue of Services with the use of KNIME |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201124 |
|
RJ01 | Rejection of invention patent application after publication |