Industry process field knowledge graph construction method and device

Abstract

The invention discloses an industry process field knowledge graph construction method, which comprises the steps of obtaining an open data source of a certain industry process field, and establishingan original data database; according to the structured and semi-structured data, constructing a knowledge graph data layer; combining expert knowledge and industry research, establishing a knowledge graph mode layer, and establishing a mapping relationship between the knowledge graph mode layer and a data layer; taking the constructed knowledge graph data layer as a sample library, extracting entities, relationships and entity attribute information contained in the unstructured data by using a self-supervised learning method, and supplementing the knowledge graph data layer according to the established mapping relationship between the knowledge graph data layer and the mode layer; and performing knowledge fusion and knowledge reasoning on the knowledge graph data layer to obtain a domain knowledge graph. The domain concept system construction efficiency is improved, a reference is provided for multi-industry process domain knowledge graph construction, and a support can be provided forenterprise process optimization and upgrading.

Description

technical field [0001] The invention belongs to the technical field of building a knowledge map database, and in particular relates to a method and device for building a knowledge map in the industrial process field, and is especially suitable for the process of the cement industry. Background technique [0002] The construction process of the traditional technology database and expert database in the field of industrial technology is too labor-dependent, and the cost is high, so it is difficult to establish a technology library in the field of multi-industry technology. In practical applications, the traditional technology database is a semi-structured data, and when solving the actual problems faced by industry enterprises, manual decision-making is still required. [0003] In the construction of knowledge graphs in traditional professional fields, domain experts and crowdsourcing are generally used to manually construct ontology to describe the conceptual hierarchy of pro...

AI Technical Summary

Problems solved by technology

[0003] In the construction of knowledge graphs in traditional professional fields, domain experts and crowdsourcing are generally used to manually construct ontology to describe the conceptual hierarchy of professional fields. However, the manual method has a huge workload and requires high experts, so it is difficult to apply in large quantities. Construction of professional field knowledge graph

At the same time, the artificially constructed conceptual hierarchy system and human intervention in knowledge information make it difficult to fully summarize all knowledge information in the field, which may easily cause loss of knowledge information

On the other hand, it is easy to cause knowledge redundancy in a certain aspect

Images