Medical knowledge map fusion method and device based on multiple data sources
A medical knowledge, multi-data source technology, applied in the field of medical knowledge graph fusion, can solve the problem of difficulty in integrating medical knowledge graphs from different data sources, and achieve the effect of strong expression ability
Active Publication Date: 2022-05-31
BEIJING NUODAO COGNITIVE MEDICAL TECH CO LTD
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Embodiments of the present invention provide a medical knowledge map fusion method and device based on multiple data sources, to solve or at least partially solve the defect in the prior art that it is difficult to realize the fusion of medical knowledge maps from different data sources
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044] The knowledge graph may include multiple groups of "entity-relationship-entity" RDF (Resource Description
[0048] Preferably, the classic translation model TransE can be used. TransE is an entity- and relationship-based distributed
[0052]
[0058] Each reference vector obtained based on the reference knowledge graph can be formed into an initial reference vector set.
[0060] According to the reference vector set, two-way supervision training can be performed on each of the first initial vectors and each of the second initial vectors,
[0067] Specifically, when performing bidirectional supervision training, first determine the pre-fusion entity pair.
[0070] There is a relationship, which means that in the reference knowledge graph, there is an instance including two entities in the pre-fused entity pair.
[0083] Specifically, the difference between the first distance and the second distance obtained according to the same pair of pre-fused entities is calculated.
[0...
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
Login to View More Abstract
Embodiments of the present invention provide a medical knowledge map fusion method and device based on multiple data sources. Among them, the method includes: performing knowledge representation learning based on the first medical knowledge map and the second medical knowledge map respectively, and obtaining each first initial vector and each second initial vector; based on the pre-acquired reference vector set, each first initial vector and each second initial vector are mapped to the reference vector space, and each first mapping vector and each second mapping vector are obtained; according to each first mapping vector and each second mapping vector, the first medical knowledge map and the second medical knowledge The knowledge in the map is fused to obtain the fused medical knowledge map. The multi-data source-based medical knowledge map fusion method and device provided by the embodiments of the present invention, based on the knowledge representation learning method, can obtain a fused medical knowledge map with stronger internal logic and expressive ability by utilizing the internal logic of the knowledge map. Knowledge graph.
Description
Method and device for medical knowledge graph fusion based on multiple data sources technical field The present invention relates to computer technology field, more particularly, relate to a kind of medical knowledge graph based on multiple data sources Fusion method and apparatus. Background technique [0002] With the development of the mobile Internet, the data generated by it is also growing explosively, and more and more data are scattered on the Internet. More and more knowledge metadata. However, due to the multi-source and heterogeneity of content on the Internet, the organizational structure is loose, and the big data environment The interconnection of knowledge under the Internet has brought great challenges. Therefore, according to the principles of knowledge organization in the big data environment, it is necessary to start from a new perspective. angle to explore the knowledge interconnection method that not only conforms to the development and changes o...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/36G06F16/28G16H70/00G06N5/04
CPCG06F16/367G06F16/288G16H70/00G06N5/04
Inventor 周永杰高飞王则远刘静
Owner BEIJING NUODAO COGNITIVE MEDICAL TECH CO LTD