Intelligent Dependency Cracking Path Based on Technology Acceptance Model (TAM) and Convolutional Neural Network (CNN) Analysis Model

Most of the existing dependency cracking methods are based on traditional models, which have low computational efficiency and are difficult to meet the needs of practical applications. To this end, this paper proposes an intelligent dependency cracking path generation method based on Technology Acceptance Model (TAM) and Convolutional Neural Network (CNN). TAM theory provides a reasonable theoretical basis for path generation, and the CNN model can effectively extract high-level features of input data, thereby significantly improving algorithm performance. Through actual verification and comparative analysis, the advantages of this method in path generation efficiency and user experience are evaluated. Experimental results show that the intelligent dependency cracking model based on TAM and CNN reduces the path generation time by 2–3 seconds compared with traditional methods, showing high computational efficiency. In addition, a long-term use test on 40 volunteers showed that more than 66% of the respondents spoke highly of the model, especially its overall functional design, interactivity and reliability