LAUSR

Talent assessment attracts the attention of researchers because of its important influence on business management issues. The traditional talent evaluation model has high sample selection cost and large calculation volume ratio, so it has become an urgent problem to be solved. Based on the nonlinear hierarchical optimization neural network, this article improves the corresponding talent evaluation index system and builds a talent evaluation model on the basis of demonstrating the feasibility of using a nonlinear hierarchical optimization neural network for talent evaluation. This article conducts an empirical analysis on the talent evaluation model of the talent evaluation team members and designs a prototype system of the talent evaluation index system based on the nonlinear hierarchical optimization neural network. In the simulation process, MATLAB software is used to complete the program realization of the model, and the accuracy and feasibility of the model are verified by combining the case. Through the evaluation and research of the implementation personnel of the case enterprise, the enterprise talent evaluation based on the nonlinear hierarchical optimization neural network is demonstrated. The empirical results show that it is feasible and accurate to use the nonlinear hierarchical optimization neural network to evaluate the talent evaluation team. The comprehensive prediction accuracy rate of T-1 year is 88.5%, and the comprehensive prediction accuracy rate of T-2 year was 83.45%, which effectively promoted the evaluation of enterprise talents.