System and method for constructing enterprise knowledge graph

Abstract

The invention relates to a system and method for constructing an enterprise knowledge graph, belongs to the technical field of knowledge graphs, and solves the problems that data of various structuretypes cannot be effectively integrated and associated and the value mining difficulty of the data is high in the prior art. The system comprises an atlas creation module used for creating a knowledgemap card; a map design module used for defining entities and relationships in a knowledge map; a data configuration module used for configuring a basic data source by an import data sub-module,a datasource configuration sub-module and a knowledge extraction sub-module, wherein the knowledge extraction sub-module is used for performing structured processing on unstructured data and providing the structured data as one of basic data sources for the graph construction module; a map construction module used for constructing the knowledge map based on the knowledge map Schema by utilizing the basic data source; and a rule design module used for realizing rule configuration and rule reasoning in the knowledge map. The problem that enterprise data is difficult to manage is solved.

Description

technical field [0001] The present invention relates to the technical field of knowledge graphs, in particular to a system and method for building enterprise knowledge graphs. Background technique [0002] In the era of digital economy, enterprises have a large amount of structured, semi-structured and unstructured (hereinafter referred to as unstructured document data) and other types of data (heterogeneous), and these data are usually stored in different locations ( multiple sources). Fragmentation and lack of relevance of multi-source heterogeneous data can easily lead to problems such as "information islands" and the inability of data to be transformed into knowledge, which in turn affects the depth of data value mining. The data itself needs to be understood and analyzed before it can be effectively used, and building a knowledge map is an important way to "extract" data and then "refine" effective knowledge. [0003] As one of the application fields of artificial int...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned analysis, the embodiment of the present invention aims to provide a system and method for building an enterprise knowledge map to solve the problem that the existing database and analysis and mining technology tools have weak processing capabilities for unstructured and semi-structured data, which leads to various The data of this type of structure cannot be effectively integrated and correlated, and the value mining of data is difficult

Images