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

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.