A healthcare‐oriented mobile question‐and‐answering system for smart cities. Issue 10 (1st July 2020)

• Record Type: Journal Article
• Authors: Xu, Yueshen; Jiang, Yan; Li, Rui; Gao, Honghao; Guo, Jin; Liu, Yaning; Hei, Lei; Wang, Yihao
• Is Part Of: Transactions on emerging telecommunications technologies. Volume 33:Issue 10(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-07-01
• Subjects: Telecommunication -- Periodicals; 384.05
• DOI: 10.1002/ett.4012
• Languages: English
• ISSNs: 2161-5748

Abstract

Abstract: Question‐and‐answering (QA) systems are popularly applied and deployed in many fields and industries, such as e‐commerce platforms, government departments, and educational industry. However, the requirement for QA systems in healthcare industry has still not been satisfied, especially the requirement for mobile QA systems. In this article, we develop a healthcare‐oriented mobile QA system for smart cities. The developed system is constructed with artificial intelligence and mobile computing techniques, including natural language processing, information retrieval, and service computing. To meet the strict requirement of healthcare‐oriented information systems, we design a series of models, algorithms, and computation methods. The designed QA system contains three modules, which are classifier, QA engine, and chatbots API. We study the performance of different classifiers, including neural network‐based classifier, support vector machine (SVM), and AdaBoost‐based classifier. The QA engine consists of two submodules, that is, semantic processing and answers retrieval. Semantic processing contains part‐of‐speech tagging and dependency parsing. The answers retrieval module contains index building and searching. We perform a series of experiments to evaluate the performance of our system and present the experimental results. The built mobile QA system has been applied in real‐world hospitals and communities and receives satisfied user experience. Abstract : 1. We develop a healthcare‐oriented mobile QA system for smart cities with information retrieval technique. 2. We study the performance of different classifiers, including neural network, SVM, and AdaBoost. 3. The built mobile QA system has been applied in real‐world hospitals and receives satisfied user experience.