Knowledge graph architecture construction and application method and system and medium

Abstract

The invention provides a knowledge graph architecture construction and application method and system and a medium. The method comprises the steps: 1, completing knowledge modeling by defining entitiesin the academic field and constructing an ontology of an academic knowledge graph; 2, carrying out entity alignment, that is, for each entity in the heterogeneous data source knowledge base, the sameentity belonging to the real world is found out; 3, enriching the knowledge graph by utilizing a rule-based knowledge graph reasoning method; step 4, evaluating several most advanced methods of knowledge graph architecture-AceKG embedded knowledge; and step 5, evaluating several most advanced methods of knowledge graph architecture-AceKG network representation learning. According to the method, pure academic information is provided, a large-scale reference data set is provided for researchers, a basis is provided for evaluating knowledge embedding and network representation learning methods,and a knowledge graph framework is provided for enriching the proposed knowledge graph framework.

Description

technical field [0001] The present invention relates to the technical field of academic data mining, in particular to a construction and application method, system and medium of a knowledge graph architecture. In particular, it involves AceKg, a large-scale knowledge graph for academic data mining. Background technique [0002] A knowledge graph is a structured semantic knowledge base for describing concepts in the physical world and their interrelationships in a symbolic form. Its basic unit is the "entity-relationship-entity" triplet, as well as entities and their related attribute-value pairs. Entities are connected to each other through relationships to form a networked knowledge structure. [0003] In the middle of the 20th century, Price et al. proposed the method of using citation networks to study the context of contemporary scientific development, and proposed the concept of knowledge graph for the first time. In 1977, the concept of knowledge engineering was prop...

AI Technical Summary

Problems solved by technology

[0007] However, there are some limitations in existing databases or knowledge graphs

First of all, most of the existing results provide homogeneous academic graphs, while the relationship between different types of entities is still lost

Second, some databases focus on only one specific research domain, limiting projects aimed at discovering cross-domain knowledge

Third, synonyms and ambiguities are also limitations of knowledge mining

[0009] Patent document CN110347844A (application number: 201910633602.3) discloses a space target knowledge graph construction system, including a text information collection and processing module, a document information collection and processing module, a knowledge graph construction module, and a knowledge graph display module; Highly specific, professional, and difficult to obtain directly, by obtaining relevant information on space targets such as news, microblogs, and academic journals, using data mining methods to study space target intelligence hidden behind massive information, and intuitively display space target attributes Information, analyze the relationship between space targets, and use software technology to integrate two types of knowledge graphs to build a space target knowledge graph system

Images