摘要
随着国内学术期刊的发展,传统的检索方式已不能满足用户的检索需求,如何快速高效地从中检索出用户需要的信息是学术期刊APP检索面临的关键问题。为解决上述问题,本文提出一种智能交互式检索框架,利用深度学习和相关反馈技术来分析数据,发现检索对象内在特征及其相互联系,增强检索的准确性。智能交互式检索模型聚焦于用户和系统之间的交互行为,充分考虑用户的情境感知和交互行为,实验验证该模型可有效提高检索效率。
With the development of domestic academic journals, the traditional search methods can no longer meet the user’s search needs. How to quickly and efficiently retrieve the information required by users is a key issue for academic journals APP retrieval. In order to solve the above problems, this paper proposes an intelligent interactive retrieval framework, which uses deep learning and related feedback techniques to analyze the data, finds the intrinsic features of the retrieval objects and their connections, and enhances the accuracy of retrieval. The intelligent interactive retrieval model focuses on the interaction between the user and the system, fully considers the user’s situational awareness and interaction behavior, and experimentally verifies that the model can effectively improve the retrieval efficiency.
作者
徐彤阳
邓颖慧
XU TongYang;DENG YingHui(Faculty of Information Management Shanxi University of Finance and Economics, Taiyuan 030006, China;National Science Library, Chinese Academy of Science, Beijing 100190, China)
出处
《数字图书馆论坛》
CSSCI
2019年第6期39-45,共7页
Digital Library Forum
基金
2017年度山西省哲学社会科学课题“山西智库建设中文献情报资源服务平台构建研究”(编号:晋规办字[2017]2号)
山西财经大学教学改革创新项目“新媒体时代基于元素养的信息检索课程教学模式探讨”(编号:2019218)资助
关键词
人工智能
交互式检索
深度学习
相关反馈
Artificial Intelligence
Interactive Retrieval
Deep Learning
Related Feedback
