Automatic Extraction Of Cognitive Model And Its Application In Solving Analytic Geometry Problem

With the development of science and technology,in recent years,people's enthusiasm for artificial intelligence can be described as full swing.Many areas have made a major breakthrough,for example: Google AlphaGo is a famous example that the machine beats the human race.The thing is a new benchmark in the field of artificial intelligence with epoch-making significance.Artificial intelligence has been widely used in speech recognition,face recognition,automatic driving,intelligent search,game theory,theorem proving and so on.In education and teaching,there have been a variety of teaching support systems.So far,the market has no real sense of intelligent products like people to answer the same questions,and give the problem steps.Based on this background,this paper studies and constructs the cognitive model based on rule flows and applies it to solving the geometric problems of plane analysis.It designs and implements a kind of intelligent answering system,which serves intelligent education and teaching well.The main contents of this paper include the following parts:(1)The Knowledge Representation of Primary Mathematics Concepts and Relations.The premise of the computer to solve the problem of primary mathematics is to be able to understand the concepts.This paper abstracts these concepts as "entities" and "relationships",and then expresses these entities and relationships as first-order predicate logic.In this way,the known conditions and conclusions of a question can be automatically converted,and then the system can be based on these known conditions and conclusions to solve the question.(2)The Knowledge Representation of Axioms and Theorems.In order to make a computer to answer questions like people,each step of calculation or reasoning must follow the corresponding mathematical logic,and these mathematical logic is elementary mathematics in the axioms,definitions,theorems and inferences.In this paper,all axioms and theorems are expressed as corresponding production rules.(3)Automatic Construction of Cognitive Models Based on Rule Flows.Running of rules in a rule library is out of order and uncertain.If extracting the rules running high frequently,after a certain splicing finishing,generating a lot of cognitive model chains stored in the cognitive model library for the next problem-solving use,the system has a sense of reasoning and purpose.(4)Design and Implementation of Solving System of Analytic Geometry Based on Cognitive Models.Because the cognitive models have the purpose of reasoning and reduce the matching of invalid rules,the solving system about analytic geometric based on cognitive models will improve in terms of efficiency.Based on the constructed cognitive reasoning model,a system for solving geometric problems is designed and implemented.Through a large number of experimental verification,the efficiency of solving the problems has been greatly improved and the system is with solving accuracy rate of up to 60%.