Auxiliary disease inference system based on knowledge graph and self-adaptive mechanism
A technology of knowledge graph and reasoning system, applied in the field of auxiliary disease reasoning system, can solve the problems of low accuracy and efficiency of disease reasoning, not considering the imbalance of disease symptom input, etc., to improve interpretability, reduce impact, improve The effect of accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0053] Considering that the current disease reasoning assistance system or device relying on the deep learning model uses a large number of diseases with different symptoms to input the deep learning model, and then trains the deep learning model, the deep learning model will be affected by the input imbalance during training, and the clinical symptoms are similar In many cases, the interpretability of deep learning is not strong, resulting in a decline in the accuracy of disease reasoning, and a single deep learning model needs to process the entire input data set, and the model processing burden is relatively large. The embodiment of the present invention proposes A disease reasoning system based on knowledge graph and adaptive mechanism, using the knowledge graph of the triple as the data structure, based on the TransE translation model and naive Bayesian classifier to establish disease reasoning Model, based on the data set division, train the disease inference model, find...
Embodiment 2
[0095] Such as Figure 5 As shown, the present invention also proposes a disease reasoning device based on a knowledge map and an adaptive mechanism, including a memory 106, a processor 107, and a computer program stored on the memory 106 and operable on the processor 107, the processor 107 When executing a computer program, realize:
[0096] Construct a knowledge map with the structure of triples , determine the training data set composed of several triples ; determine the test composed of data set;
[0097] Based on the TransE translation model and Naive Bayesian classifier, construct a disease inference model; divide the training data set, and divide the test data set; use the training data set to train the disease inference model, and determine the division of the training data set, the TransE in the disease inference model The number n of translation models, the number m of naive Bayesian classifiers, and the boundary value M; take the divided test data set as the inp...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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