AI identification of satisfaction of multiple decision-making schemes integrating PageRank algorithm and BAS algorithm

In multiple decision-making schemes, only the limited resource consumption can be considered to construct a satisfaction evaluation model, which leads to low accuracy of satisfaction evaluation. Therefore, an AI identification method for satisfaction of multiple decision-making schemes that integrates PageRank algorithm and BAS algorithm is proposed. Importance evaluation information is represented by binary, importance evaluation scale operation rules are defined, and the individual importance perception of decision makers is aggregated into group perception to obtain the importance matrix of multiple decision-making schemes. Based on PageRank algorithm, the scheme dependency weight factor and associated influence weight factor are introduced, and the sorting algorithm is improved by combining the scheme content similarity to reduce the number of schemes that are irrelevant to the decision topic. According to the importance matrix, the sorting of multiple decision-making schemes is determined. Based on BAS algorithm, the crowding index is defined, and the competition mechanism is introduced to eliminate similar individuals, and the population size is dynamically adjusted. Considering the limited resources, an evaluation model with maximum satisfaction and limited resource consumption is constructed. AI recognition is used to calculate the language deviation variance matrix, evaluate the satisfaction of the sorting results of multiple decision-making schemes, and realize the effective evaluation of the satisfaction of multiple decision-making schemes. The experimental results show that the average recall rate of the design method is 0.80, and the recall rate of most feature indicators exceeds 0.84. The satisfaction precision rate reaches 0.87 when evaluated 300 times. The satisfaction evaluation is highly accurate and can more effectively identify solutions that meet user needs.