摘要：In the Internet era, the dependence on mobile phone information  is   a crucial issue, and  psychological perception and personalized and precise push have a significant impact on this field. The introduction of this rational and planned behavior, combined with the theoretical framework of structural equation modeling (SEM) and artificial neural networks (ANNs), is a sophisticated analytical tool for exploring the key factors influencing information-dependent green food safety. The key factors influencing the dependence of green food safety information were investigated. The survey covered 630 participants between the ages of 17 and 70 in Guangdong Province, China. Studies have shown that perceived risk,regulation,price,volatility,    innovation,and expectation confirmation significantly affect the perceived usefulness of green food information, and thus the satisfaction with green food. The study also highlights the significant impact of users' degree of expectation confirmation on satisfaction and perceived usefulness of green food. Model path analysis showed that expected confirmation and perceived usefulness explained 61% and 74% of the variance in   financial   sustain   ability, respectively. The application of deep ANN multilayer perceptron improved the prediction accuracy of perceived usefulness, with a training accuracy of 87.54% and a test accuracy of 90.34%, which further deepened the understanding of the mechanism relying on green food safety information. This study provides strong support for a deeper understanding of the relationship between consumer behavior and green food safety information dependence, which is helpful to promote enterprises and market camps to formulate product or service promotion strategies more effectively, and provide a solid theoretical and empirical foundation for green food safety and personalized and precise push in the future, so as to enhance information dependence.

关键词：Green food;dependence on safety information;consumer psychological perception;personalized and precise push;artificial neural network