Knowledge graph

which is a rapidly developing technology

provides strong support in business and engineering. Knowledge graph plays an important role in recommendations and decision-making

while in the electric power industry

there would be more possibilities for knowledge graph to be utilized. However

as a complex cause-and-effect network

the electric power domain knowledge graph has massive nodes

heterogeneous edges

and sparse structures. Thus

it requires human effort to process data

while quality and accuracy cannot be guaranteed. We propose a novel graph computing-based knowledge reasoning method that takes into account the sparsity of the electric power domain knowledge graph to solve the aforementioned problems and achieve improved accuracy of graph classification and knowledge reasoning tasks. The Haar basis is constructed to realize fast calculation

while the multi-scale network structure is introduced to assure classification accuracy and generalization. We evaluate the proposed algorithm on the NCI-1

CEPRI_UHVP

and CEPRI_EQUIP databases. Simulation results demonstrate its superior performance in terms of accuracy and loss.