基于知识图谱的儿童疾病推理模型

Children’s Disease Reasoning Model Based on Knowledge Graph

为提高儿童多种疾病推理的准确率,提出以知识图谱为数据基础并结合推理机的儿童疾病推理算法。通过Neo4j构建知识图谱对数据进行储存和应用,而推理机以TransE推理机为基础,并结合朴素贝叶斯分类器来提升推理机处理不同疾病含有同种症状的问题的能力,再通过建立的自适应机制来降低不同疾病的症状数不同对推理机的影响。实验结果表明,所提出算法在疾病推理的精确率,召回率和F1值上均有所提升,说明该方法提高了儿童多种疾病推理的准确率。

To improve the accuracy of children’s multiple diseases reasoning, a children’s disease reasoning algorithm based on the knowledge graph and the reasoning machine is proposed. A knowledge graph is constructed by Neo4j to store and apply the data, and the inference engine is based on the TransE inference engine, and the Naive Bayes Classifier is combined to improve the ability to deal with problems with the same symptoms in different diseases, and an adaptive mechanism is established to reduce the impact of different symptoms of different diseases on the reasoning machine. The experimental results show that the proposed algorithm improves the precision, recall and F1 value of disease reasoning, indicating that this method improves the accuracy of children’s multiple disease reasoning.