Human-machine Hybrid Intelligent Evaluation System for Power Grid based on Data-driven

Improving the efficiency of resource input and output, realizing precise investment, precise resource allocation, and promoting the high-quality development of power grids are important trends in current power grid investment and construction. After rigorously analyzing the key points of the whole process of power grid investment, this paper constructs a set of index system covering the whole process before, during and after the event. Further, the Pearson correlation coefficient is used to analyze the correlation of the index data and calculate the correlation adjustment factor to weaken the final objective weight. This paper proposes a quantitative method based on distribution fitting to quantify the index data to eliminate the subjective influence of manual scoring. The objective weights are calculated by using the entropy weight method and the coefficient of variation method, and the data reliability adjustment factor is innovatively taken into account in the weight setting, and finally the comprehensive evaluation ranking of the power grid is obtained. The case verifies the correctness and effectiveness of the evaluation system proposed in this paper, which can provide references for the planning and decision-making of power grid investment.