Research On Intelligent Question Answering Technology Based On EAV Relational Model

Currently,most of the resource information on the World Wide Web(WWW)can easily be read by humans.However,the information and services on the WWW to be understood and invoked by the software,the transition from the current WWW to the Semantic Web must be completed.Large amounts of data on the WWW are still stored in relational databases,so the semantics of large amounts of data cannot be precisely defined.As a data specification of semantic web data,ontology datasets define the semantics of data and are committed to promoting data sharing between various systems.At the same time,with the rapid development of artificial intelligence and deep learning,many intelligent systems have been designed and developed.Howerer,in the field of e-commerce,a large number of customer service systems are still mainly relies on manual service.In order to reduce business costs,and to intelligently understand user needs and provide round-the-clock online customer service consulting services,intelligent question and answer systems are gradually being valued and developed.This paper investigates the technical status of the intelligent question answering system.Based on the analysis of the EAV(Entity-Attribute-Value)relational model,an algorithm for automatically generating ontology data sets is designed and implemented,and experimental verification is performed.On the basis of the algorithm implementation,an emotion-driven context-aware ontology semantic intelligent question answering system was developed.The question answering system realizes the functions of sentiment analysis,semantic understanding and query,user preference calculation,content recommendation and data visualization.The main work of this paper is as follows:(1)Analyze the performance of previous work and existing tools and methods on the EAV relational database,and explain their limitations.In order to overcome these shortcomings,corresponding mapping rules and a rule-based automatic ontology algorithm based on the EAV model are designed.(2)Investigate the current situation that the semantic question answering system lacks context-related functions,and design a semantic understanding method that combines context and a user preference calculation method that integrates user emotions in the context,access frequency and time interval factors.(3)For the current situation of insufficient user interaction and experience in the semantic question answering system,the content recommendation function based on user preferences and data visualization function are designed to help users get relevant content.The experimental results show that the EAV model automatic ontology construction algorithm proposed in this paper works well,and the designed semantic question answering system has a high degree of intelligence and effectively improves the user experience,which has a good application prospect.