An Automatic Model Table Entity Alignment Framework for SG-CIM Model
Fangjun Li, Runzhen Yan, Rui Su, Yating Wang, Xueyang Liu, Kehui Xu · 2022
SG-CIM model is a kind of unified data model for power grids designed based on the business scenarios and data requirements of the national grid. The model is mainly composed of three different types of model tables, which are mainly designed manually based on the business requirements of the grid. Therefore, to apply the SG-CIM model to the national grid business scenarios, it is necessary to achieve the unification of physical, logical and standard tables in the SG-CIM public data model. In order to reach the above goal, an effective entity alignment unification method needs to be found to achieve the task of unification of different knowledge maps. In this paper, we propose an automatic model table entity alignment framework for SG-CIM model entities. This entity alignment framework can effectively calculate the similarity and association degree between model table entities, thus helping to realize the comparison and alignment of entities between different knowledge maps. In addition, the entity alignment model base framework proposed in this paper also enriches the number of triplet entities used for alignment by using inference rules for triplet entities, which improves the learning effect of the framework proposed in this paper for triplet entities. In this paper, relevant experiments are designed to demonstrate that this model table entity alignment framework outperforms traditional entity alignment methods on actual graph data.