Disease knowledge map construction method and platform system, device, and storage medium

A technology of knowledge graph and construction method, applied in the field of equipment, storage medium, disease knowledge graph construction method and its systems, can solve problems such as single data source and knowledge conflict, and achieve the effect of improving construction efficiency and quality

Inactive Publication Date: 2019-01-25
长沙瀚云信息科技有限公司
View PDF6 Cites 74 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The data source of this patent is too single, and the focus of this patent is to use the completed medical knowledge map to diagnose patients, and there is a problem of knowledge conflict in the process of information learning

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Disease knowledge map construction method and platform system, device, and storage medium
  • Disease knowledge map construction method and platform system, device, and storage medium
  • Disease knowledge map construction method and platform system, device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] A disease knowledge map construction method, such as figure 1 shown, including the following steps:

[0040] A. Information extraction: extract or learn entities, attributes, and the relationship between entities from multi-source databases to form ontological knowledge expressions;

[0041] B. Knowledge fusion: integrate knowledge to eliminate contradictions and ambiguities;

[0042] C. Knowledge processing: the fused knowledge is added to the knowledge base after quality evaluation.

[0043] Further, as figure 2 As shown, after step C, it also includes: D, update of the knowledge map.

[0044] Such as Figure 7 As shown, E1, start map construction; E2, enter the disease database; E3, select the specific disease to be constructed knowledge map; E4, algorithm to build the prototype of disease knowledge map; E5, manually confirm the disease knowledge map; E6, expert review knowledge Map construction quality; E7, judging whether the review is passed; yes, end map cons...

Embodiment 2

[0046] A method for constructing a disease knowledge graph in this embodiment, the basic steps are similar to the technical solution in embodiment 1, wherein the multi-source databases described in step A in embodiment 1 are open link databases and encyclopedias. The learning or extraction steps of entities in step A include: A101, entity extraction or learning, the specific content is as follows:

[0047] Related data sources for knowledge map construction, including structured data, semi-structured data, and unstructured data. Strictly speaking, the open link data and open knowledge base described in the present invention are semi-structured databases, and these data are usually stored in a graph-form data structure. The most well-known ones are YAGO, DBPedia, and Freebase. These data sources usually have high coverage, and also have a considerable amount of data in specific fields; therefore, they can be used for the construction of general knowledge graphs and industry kno...

Embodiment 3

[0085] A method for constructing a disease knowledge map in this embodiment, the basic steps are similar to the technical solutions of embodiments 1 and 2, wherein the learning or extraction of entities in step A further includes: A103, learning and integrating hyponymy relationships, including from Extract hyponymy from open link dataset, extract hyponym from encyclopedia, CRF-based open hyponym learning and classification tree integration.

[0086] A1031. Extract the hyponymy relationship from the open link data set

[0087] In the open link data set, the upper and lower relationship is described by a clear mechanism, so it can be obtained by direct parsing, and corresponding rules can be written for each data set.

[0088] A1032, extract the hyponymy relationship from the encyclopedia

[0089] Encyclopedia describes two kinds of hyponymy relationships, one is between categories, and the other is between categories and articles. The former corresponds to the hierarchical re...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a disease knowledge map construction method and a system, a device and a storage medium thereof, belonging to the technical field of disease knowledge maps. The disease knowledge map construction method comprises the following steps: extracting or learning entity, attributes and relationships among entities from a multi-source database to form ontological knowledge representation; B. knowledge fusion: integrate knowledge to eliminate contradictions and ambiguity; C. Knowledge processing: After quality assessment, the fused knowledge is added to the knowledge base. It also includes disease knowledge mapping platform system, equipment and storage medium. Aiming at the problems existing in the prior art, it extracts entities, attributes and their relationships from multiple data sources, and fuses and processes them, so as to quickly construct a normalized and standardized disease knowledge map.

Description

technical field [0001] The present invention relates to the technical field of disease knowledge graphs, in particular to a method for constructing a disease knowledge graph and its system, equipment, and storage medium. Background technique [0002] The predecessor of the knowledge graph is the Semantic Web, which absorbs the concepts of the Semantic Web and Ontology in terms of knowledge organization and expression, making it easier for knowledge to be exchanged, circulated, and processed between computers and between computers and people. Specifically, a knowledge graph consists of a schema graph, a data graph, and the relationship between the two: the schema graph describes the conceptual level of the human knowledge domain, emphasizing the formal expression of concepts and concept relationships, and the nodes in the schema graph are concept Entity, edge is the semantic relationship between concepts, such as part-of; data graph describes the physical world level, emphasi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/36G06N5/02G16H70/20
CPCG06N5/022G16H70/20
Inventor 蒋小云
Owner 长沙瀚云信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap