Construction And Application Of Domain Knowledge Graph With Knowledge Discovery

Domain Knowledge Graph construction is a process of discovering,analyzing,and extracting diversified relationships among data based on the diverse data of related domain knowledge systems,and effectively displaying them in a visual manner.In recent years,the Domain Knowledge Graph has been rapidly developed and gradually penetrated into many practical applications.The construction of domain knowledge for colleges and universities is one of the important applications,but there are still many problems,for example,the depth and breadth of curriculum knowledge extraction in the Domain Knowledge Graph for colleges and universities is insufficient,the specific manifestations include the failure to systematically extract the tacit ideological and political elements in the curriculum,the failure to fully discover and expand the common principles and similar applications between different courses in the same field,which indicate an important research direction for the construction of professional knowledge in colleges and universities.This paper takes the Knowledge Graph construction in the field of software engineering as the research object,in view of the above problems,the specific research work is as follows:(1)Research on domain tacit knowledge discovery algorithm.Aiming at the problem that it is difficult to effectively analyze and extract the ideological and political knowledge contained in professional courses in software engineering courses,the Apriori algorithm based on LDA model and co-occurrence frequency statistics is proposed.The algorithm uses the LDA model to obtain the subject words on the basis of the relevant literature,and then introduces the co-occurrence frequency statistical matrix combined with the Apriori algorithm to realize the discovery of the tacit knowledge of the domain,which serves the curriculum ideological and political construction.(2)Research on domain common knowledge discovery algorithm.Aiming at the problem that the knowledge of different courses in the field of software engineering cannot be fully integrated and expanded,this paper proposes a WLDA-Apriori algorithm,which uses separately the LDA model and the Apriori algorithm based on the text data of the knowledge principles and applications of related textbooks to find the common principles between courses and similar applications integrating into the Domain Knowledge Graph.In this algorithm,the LDA model is easy to ignore the word meaning and the lack or error of the knowledge association.The Word2 vec model is introduced and combined with the cosine similarity,through calculation and comparison,so as to obtain the common knowledge between courses,and the obstacle of knowledge expansion caused by knowledge island of learners is solved.(3)Domain Knowledge Graph construction with knowledge discovery.In order to realize the construction of the Knowledge Graph in the field of software engineering,this paper first based on the university curriculum architecture and curriculum knowledge structure,taking data structure courses and C language programming courses as the research objects,designing a specific ontology,constructing the domain curriculum Knowledge Graph,and then Based on the algorithmic research results of tacit knowledge discovery and common knowledge discovery,the domain curriculum Knowledge Graph is supplemented and expanded,and finally the knowledge discovery results are stored and presented through Neo4 j.(4)Design and implementation of domain knowledge query system with knowledge discovery.Aiming at the current status of immature research on application systems for the current domain tacit knowledge and common knowledge query,this paper is based on the Domain Knowledge Graph with knowledge discovery and the We Chat applet as a platform,this paper develops and implements a domain knowledge query system with knowledge discovery,and provides a convenient query tool for domain learners to visualize the tacit knowledge and common knowledge of the curriculum.Starting from the theory of domain knowledge graph,this paper discovers tacit ideological and political knowledge and solves the problem of mining and presenting ideological and political elements in the curriculum,so as to serve the ideological and political construction of courses.At the same time,it discovers the common knowledge of different courses and realizes the knowledge connection between courses,thereby dredging the learning navigation path and reducing the learning cost of learners.