摘要
针对医疗护理领域知识复杂性强、数据量大以及对准确度要求较高的问题,该研究提出一种基于卷积神经网络的医疗护理学实体关系抽取方法,实现对护理学语义关系的细粒度文本挖掘。该研究构建了医疗护理学语料标注系统,通过将医疗语料转化为向量特征矩阵,实现了对医疗语料的自动过滤和标注。通过向神经网络模型嵌入所构建的医疗关系语料库,一定程度上提高了模型疾病分类的准确度。在医疗护理学数据集上的实验表明,基于卷积神经网络的模型在指标精确度、召回率、F1值可达到89.78%、87.59%、89.77%。综上所述,该研究提出的基于卷积神经网络的医疗护理学实体关系抽取方法能够有效地抽取医疗语料数据中的实体关系,优于传统的实体关系抽取模型。
Aiming at the problems of strong knowledge complexity,large amount of data and high accuracy of alignment in the field of medical and nursing,this study proposes a convolutional neural network based method for extracting medical and nursing entity relations to realize fine-grained text mining of semantic relations in nursing.this study constructs a medical and nursing corpus labeling system,which can automatically filter and label medical corpus by converting medical corpus into vector feature matrix.By embedding the medical relationship corpus constructed in this study into the neural network model,the accuracy of disease classification of the model is improved to a certain extent.experiments on medical nursing data sets show that the model based on convolutional neural network can achieve 89.78%,87.59%,and 89.77% in index accuracy,recall,and F1.To sum up,the medical nursing entity relation extraction method based on convolutional neural network proposed in this study can effectively extract entity relations from medical corpus data,which is superior to the traditional entity relation extraction model.
作者
曹茂俊
胡喆
CAO Maojun;HU Zhe(School of Computer and Information Technology,Northeast Petroleum University,Daqing 163000,China)
出处
《电子设计工程》
2024年第8期18-22,共5页
Electronic Design Engineering
基金
黑龙江省自然科学基金(LH2019F004)。
关键词
实体关系抽取
卷积神经网络
医疗护理学
词向量
知识图谱
entity relationship extraction
Convolutional Neural Network
medical nursing
word vector
knowledge graph
