1. This paper proposes a knowledge graph based Q.A. system to address the issues of unbalanced medical resources, increasing medical needs, and chaotic online medical question-and-answer jobs in China.
2. The knowledge graph is constructed using top-down and bottom-up methods, with 44,000 knowledge entities of 7 types and 300,000 entities of 11 kinds stored in the Neo4j graph database.
3. The mainstream implementation methods of the Q.A. system include Semantic Parsing, Information Extraction, and Vector Modeling.
The article is overall reliable and trustworthy as it provides detailed information about the proposed knowledge graph based Q&A system for medical purposes in China. It also provides an overview of the construction methods used for the knowledge graph as well as the mainstream implementation methods for the Q&A system. Furthermore, it cites relevant sources such as [1]-[4] to support its claims which adds to its credibility.
However, there are some potential biases that should be noted when reading this article such as its focus on China’s manual medical interrogation system which may lead to a one-sided reporting of other countries’ systems or lack thereof. Additionally, there may be missing points of consideration or evidence for some of the claims made in this article which could lead to unsupported claims or unexplored counterarguments being presented without proper context or explanation. Finally, there is no mention of possible risks associated with this system which should be noted before implementing it in practice.