Research On The Construction Of High School Mathematics Knowledge Graph Based On Deep Learning

With the gradual development of Internet technology,"Internet + education" has become a hot research topic in the field of education.Through the analysis of the existing network learning resources,it can be found that the network learning resources do not have a high correlation,sequence,so that students can not obtain good and accurate knowledge.In order to solve the above problems,this paper proposes to use knowledge graph to construct corresponding learning resources.Aiming at the imperfection of knowledge map in education field,this paper constructs a knowledge map of senior high school mathematics based on the traditional knowledge map construction method.This paper mainly completes the following aspects:1.Construction of mathematics knowledge map in senior high school.In the aspect of mathematics,the existing geometry knowledge map of senior high school is not constructed according to the concept of curriculum standards,so it does not satisfy the cultivation of the core quality of senior high school mathematics and does not adapt to the actual needs of senior high school mathematics teaching.In view of the above problems,this paper adopts the idea of "five-step method" to construct the high school mathematics knowledge ontology according to the general high school mathematics curriculum standard,and then constructs the high school mathematics knowledge map based on the constructed high school mathematics knowledge ontology.2.Construction of a case study of mathematics knowledge atlas in senior high school.The teaching plan of high school mathematics on the network teaching platform is extracted by crawler technology.Based on the data,named entity recognition and relation extraction are carried out by information extraction technology.Bi LSTM-Attention-CRF model is proposed for named entity recognition.In relation extraction,this paper proposes the Bert-Bilst M-attention model for relation extraction.And through comparative experiments,it is verified that the model used in this paper can better identify related entities and relationships compared with other basic models.By using the above two models,entities and relationships in mathematical teaching plans can be identified.Finally,the entity obtained by knowledge fusion is utilized to construct a case of senior high school mathematical knowledge atlas.3.Design and implementation of knowledge map construction tool for senior high school mathematics.Based on the construction process of senior high school mathematics knowledge map,this paper designs and implements the tool of senior high school mathematics knowledge map construction.The tool includes user management module,entity recognition module,relationship extraction module,entity and relationship management module,knowledge graph display module.The high school mathematics subject knowledge map constructed in this paper has very important research significance.The building tool of high school mathematics knowledge map designed on the basis of the building process of high school mathematics knowledge map can help students better learn high school mathematics and better understand the complex relationship between high school mathematics knowledge points.It is an important means and tool to improve students' mathematics learning.