Web-based domain knowledge map construction system and method

Abstract

The invention discloses a Web-based domain knowledge map construction system and method. The system comprises a knowledge modeling subsystem, a data and entity link subsystem, a human assisted labeling subsystem and a knowledge visualization subsystem, wherein the knowledge modeling subsystem is sued for obtaining an original knowledge model according to a preset data resource, and receiving an operation instruction of an operation interface so as to construct a data mode of a knowledge map to obtain a knowledge model; the data and entity link subsystem is used for extracting knowledges according to multiple types of data and storing the extracted knowledges into the knowledge map; the human assisted labeling subsystem is used for receiving a user labeling instruction so as to change the knowledge map according to the user labeling instruction; and the knowledge visualization subsystem is used for visually displaying the knowledge model, a dynamic link between the knowledge model and an entity and the changed knowledge map. The system is capable of simply and conveniently completing the work such as knowledge modeling, knowledge obtaining and knowledge visualization, so that the domain knowledge map construction difficulty is greatly reduced and benefit is brought to enhance the accuracy of domain knowledge maps.

Description

technical field [0001] The present invention relates to the technical field of knowledge map construction, in particular to a system and method for building a domain knowledge map based on the Web (World Wide Web, global wide area network). Background technique [0002] A domain knowledge graph is a semantic network constructed by extracting entities and semantic relationships between entities from specific resources in a specific domain. The knowledge system it contains is usually highly domain-specific and professional. However, the current research results on the construction of domain knowledge graphs at home and abroad are mainly about the key technologies of natural language processing in knowledge graphs, including entity recognition, relationship recognition, entity linking, knowledge fusion, knowledge computing, etc. In the actual process of building domain knowledge graphs, in order to ensure accuracy, supervision and intervention by domain experts is often require...

AI Technical Summary

Problems solved by technology

[0005] However, the main problem of the domain knowledge graph construction system in related technologies is that the data modeling part of most domain knowledge graphs is automatically generated and expanded based on network content, and the accuracy of the data model is difficult to guarantee. It is urgent to introduce Expert assisted editing and manual supervision

However, for experts in the field of non-artificial intelligence, the natural language processing technology involved in the construction of knowledge graphs is difficult to understand, and the threshold for technical implementation is relatively high, which has greatly restricted the popularization and application of domain knowledge graphs, and needs to be solved. solve

Images