<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Based on knowledge mapping, this paper designs the application architecture of the scientific and technological knowledge management system for the power grid industry and proposes the design of key modules such as knowledge extraction, knowledge fusion and cross-checking. In terms of knowledge fusion, this paper proposes the functional design of conflict detection, entity alignment based on deep learning, data fusion based on linking and cross-validation based on confidence assessment. In terms of cross-truth, this paper investigates the credibility calculation of candidate message sets, the representation of candidate message sets, and the construction of logic rules for cross-truth models. Finally, this paper evaluates the system’s term extraction, concept recognition, and performance. The results show that the average elapsed time for each function of graph visualization, keyword search, keyword search, advanced search, and advanced search in the knowledge management system to be executed 20 times is 1.33s, 1.27s, 3.14s, 1.47s, and 3.26s, respectively, and the average response time is only 2.1s. Therefore, the knowledge management system for grid industry science and technology presented in this paper is effective.</p>
</abstract>

Based on knowledge mapping, this paper designs the application architecture of the scientific and technological knowledge management system for the power grid industry and proposes the design of key modules such as knowledge extraction, knowledge fusion and cross-checking. In terms of knowledge fusion, this paper proposes the functional design of conflict detection, entity alignment based on deep learning, data fusion based on linking and cross-validation based on confidence assessment. In terms of cross-truth, this paper investigates the credibility calculation of candidate message sets, the representation of candidate message sets, and the construction of logic rules for cross-truth models. Finally, this paper evaluates the system’s term extraction, concept recognition, and performance. The results show that the average elapsed time for each function of graph visualization, keyword search, keyword search, advanced search, and advanced search in the knowledge management system to be executed 20 times is 1.33s, 1.27s, 3.14s, 1.47s, and 3.26s, respectively, and the average response time is only 2.1s. Therefore, the knowledge management system for grid industry science and technology presented in this paper is effective.

Utilizing Knowledge Graph to Build a Scientific and Technological Knowledge Management System for Grid Industry

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Based on knowledge mapping, this paper designs the application architecture of the scientific and technological knowledge management system for the power grid...

Utilizing Knowledge Graph to Build a Scientific and Technological Knowledge Management System for Grid Industry

Published Online: Nov 08, 2023

Page range: -

Received: Jan 19, 2023

Accepted: May 19, 2023

DOI: https://doi.org/10.2478/amns.2023.2.01064

Keywords
Knowledge mapping, Knowledge extraction, Cross-checking, Grid industry, Scientific and technological knowledge management

© 2023 Yuzhong Zhou et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Utilizing Knowledge Graph to Build a Scientific and Technological Knowledge Management System for Grid Industry

Published Online: Nov 08, 2023

Page range: -

Received: Jan 19, 2023

Accepted: May 19, 2023

DOI: https://doi.org/10.2478/amns.2023.2.01064

KeywordsKnowledge mapping, Knowledge extraction, Cross-checking, Grid industry, Scientific and technological knowledge management

© 2023 Yuzhong Zhou et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Keywords
Knowledge mapping, Knowledge extraction, Cross-checking, Grid industry, Scientific and technological knowledge management