Design And Implementation Of Intelligent Question Answering System For Internet Of Things Experts

In recent years,the Internet has been applied to all aspects of life.At the same time,a large amount of data has been generated on the Internet.Due to the emergence of search engine technology,people are accustomed to obtaining various types of information from the Internet.The question-and-answer system as a next-generation search engine allows users to ask questions and return precise answers in natural language.This paper completes the design of intelligent question answering system by analyzing the search method of search engine and the mainstream way of traditional search engine.This system uses a keyword-based FQA question answering strategy and a knowledge base-based KBQA question answering strategy,and completes user's information query.The main work of the intelligent question answering system has the following three aspects:1)The IoT expertise data collection strategy based on the keyword-based FQA question and answer section was designed and the construction of the frequently question database was completed.The keyword-index method is used to quickly locate the problem for the frequently question libraries.At the same time,the topic keywords are used for matching to extract topic keywords and to determine candidate questions for user's questions.Finally,through the Word2 Vec training model,the candidate questions and the optimal question answer pairs are selected,and the answers are returned to the user.2)The KBQA question and answer part which based on knowledge base was designed.The crawling strategy is used to collect the data and analyze the collected data to build an ontology library for IoT expertise.Design a new problem-solving strategy for the data form of the knowledge base,parse the term concept entity and question template for the user question;match the term concept entity and the question template with the instance name,class name and attribute name in the ontology.Based on the obtained matching items,the executable query statement is constructed,and the data in the professional domain ontology is queried to obtain an answer and returned to the user.3)A statistical-based question and answer recommendation method was designed.When the user enters the question,the content-based method will adopt to accurately locate the user's problem to the common question and the keyword-based extension to the related question,which is recommended to the user as a candidate question.A method based on statistical recommendation is adopted for the common problem of the user,andthe problem that the user may be interested in is recommended to the user according to the browsing content of the user.Based on the above two question and answer strategies,the realization of the object-oriented knowledge and answer system for the Internet of Things was completed.The system has a query knowledge such as catalogue knowledge base,natural language query and related problem recommendation,which can well meet the individual needs of users,and at the same time,the system shows that the system achieves the expected design goals.