基于深度学习模型的智能化科室导诊
Intelligent department guidance based on deep learning model
顾君杰 1王蓓 1李晓禹 2邹俊忠1
作者信息
- 1. 华东理工大学信息科学与工程学院,上海 200237
- 2. 清影医疗科技(深圳)有限公司 研发部,广东 深圳 518083
- 折叠
摘要
为减轻科室导诊人员的工作负荷,对智能化科室导诊的实现方法进行研究.区别于现有的导诊方式,提出一种少参数轻量化的多级科室导诊模型.结合ALBERT预训练解决现有算法参数量过大的问题,并关联多个相关科室,建立ALBERT预训练与Bi-GRU结合的多标签分类模型.通过在互联网医院问诊数据集上的测试,与单科室分类模型对比,验证了该多科室分类模型的预测结果具备可靠性和有效性,能够较好辅助科室导诊工作.
Abstract
To reduce the workload of traditional department guidance,the intelligent department guidance method was studied.Different from the existing intelligent guidance methods,a multi-department guidance model with fewer parameters was pro-posed.ALBERT pre-training was implemented to solve the problem of large number of parameters in existing algorithms.A multi-department classification model combining ALBERT pre-training and BI-GRU was constructed.Based on the evaluation using collected consultation data set and the comparison with single-department classification model,it is verified that the presen-ted multi-department model is more reliable and effective,it can better assist the department guidance work.
关键词
科室导诊/多标签/文本预训练/双向门控循环单元/文本分类/深度学习/自然语言处理Key words
department guidance/multi-label/text pre-training/Bi-GRU(bidirectional gated recurrent unit)/text classifica-tion/deep learning/natural language processing引用本文复制引用
基金项目
国家自然科学基金面上基金项目(61773164)
出版年
2024
NETL
NSTL
万方数据