PageRank talent mining algorithm of power system based on cognitive load and DPCNN

Abstract

PageRank talent mining in power system is an effective means for enterprises to recruit talents, which can correctly recommend talents in practical applications. At present, the mining evaluation index system is not perfect, and the consistency coefficient between the evaluation results and the actual situation is low in practical applications. Therefore, PageRank talent mining algorithm in power system based on cognitive load and dilated convolutional neural network (DPCNN) is proposed. The cognitive load and DPCNN are used to establish a talent capability evaluation system, calculate the index weight value, construct the PageRank talent capability evaluation model of the power system according to the corresponding weight of the index, determine the membership range of the index, calculate the comprehensive score of the appraiser's ability, and determine the ability level of the appraiser, thus realizing the PageRank talent mining algorithm of the power system. The experimental results show that the algorithm has high accuracy and objectivity, good encryption effect, cannot crack the attack node, the prediction error and the prediction relative error are closest to the standard value, the maximum error is 0.51, the maximum relative error is 0.82, and can achieve the accurate prediction of talent demand.