International Journal of Networked and Distributed Computing

<Previous Article In Issue
Next Article In Issue>
Volume 8, Issue 3, June 2020, Pages 162 - 170

Research on Intelligent Question and Answering Based on a Pet Knowledge Map

Authors
Yuan Liu1, *, Wen Zhang2, Qi Yuan1, 3, Jie Zhang2
1School of Artificial Intelligence and Computer Science, Jiangnan University, No. 1800 Lihu Road, Wuxi 214122, China
2School of Design, Jiangnan University, No. 1800 Lihu Road, Wuxi 214122, China
3Department of Industrial Design, Eindhoven University of Technology, Eindhoven, Netherlands
*Corresponding author. Email: lyuan1800@sina.com
Corresponding Author
Yuan Liu
Received 1 March 2020, Accepted 10 April 2020, Available Online 21 May 2020.
DOI
10.2991/ijndc.k.200515.004How to use a DOI?
Keywords
Pet; knowledge map; intelligent Q&A
Abstract

This paper proposes a framework for constructing pet knowledge maps. The schema concept layer is designed and built top-down, and the data layer is constructed from knowledge extracted from semi-structured and unstructured data. In the aspect of entity extraction of unstructured data, a symptom-named entity recognition method combining a Conditional Random Field (CRF) and a pet symptom dictionary is proposed. The method uses a symptom dictionary to identify text and obtain semantic category information. The CRF combines semantic information to recognize and extract symptom entities. Experimental results show the effectiveness of the method. This paper proposes a framework for an intelligent question answering system based on a pet knowledge map. By constructing a named entity dictionary, the problem is abstracted, and the problem is classified by a naive Bayesian text classifier. Through the results of the text classifier, the intent of the natural language question is determined, and the corresponding word order map is matched. The word order map is converted into an OrientDB SQL-like query statement, which is queried in the graph database in which the knowledge map is stored. The example shows that the constructed pet knowledge map and the intelligent question answering system based on the pet knowledge map works well.

Copyright
© 2020 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

<Previous Article In Issue
Next Article In Issue>
Journal
International Journal of Networked and Distributed Computing
Volume-Issue
8 - 3
Pages
162 - 170
Publication Date
2020/05/21
ISSN (Online)
2211-7946
ISSN (Print)
2211-7938
DOI
10.2991/ijndc.k.200515.004How to use a DOI?
Copyright
© 2020 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

risenwbib
TY  - JOUR
AU  - Yuan Liu
AU  - Wen Zhang
AU  - Qi Yuan
AU  - Jie Zhang
PY  - 2020
DA  - 2020/05/21
TI  - Research on Intelligent Question and Answering Based on a Pet Knowledge Map
JO  - International Journal of Networked and Distributed Computing
SP  - 162
EP  - 170
VL  - 8
IS  - 3
SN  - 2211-7946
UR  - https://doi.org/10.2991/ijndc.k.200515.004
DO  - 10.2991/ijndc.k.200515.004
ID  - Liu2020
ER  -