A dynamic interactive consensus deviation correction system driven by hybrid intelligence and its application to NEV policies

Countries worldwide continue to introduce policies to accelerate the development of the new energy vehicle (NEV) industry. However, during implementation, NEV policies often face target deviations due to complex real-world circumstances, leading to limited adoption and unintended negative consequences. While human intelligence has struggled to effectively assess and correct these deviations, machine reasoning and judgment offer significant potential to complement human intelligence. Despite this, previous research on NEV policies has inadequately explored the evaluation and correction of policy deviations, particularly via the use of emerging machine intelligence from artificial intelligence (AI) and big data. Studies suggest that machines can contribute to the challenging task of identifying NEV policy deviations through informed inference and feedback. This work proposes the integration of human and machine intelligence to address these deviations. Specifically, a dynamic interactive consensus system driven by hybrid intelligence is designed to correct NEV policy deviations. This system, based on the consensus-reaching process (CRP), uses a two-stage algorithm that includes deviation identification metrics and correction feedback iteration. Additionally, it leverages machine learning (ML) to extract hybrid intelligence judgments from online comments and text data, providing necessary information and parameters for deviation correction. An experimental analysis demonstrates the effectiveness of the proposed system and highlights the complementary benefits of combining human and machine intelligence.