Title: Innovative methods for intellectual property protection in the automotive industry driven by artificial intelligence and deep learning

Authors: Yahong Xu; Kewei Ji; Yakun Xu; Mengyao Chen

Addresses: College of Intellectual Property, Hubei University of Automotive Technology, Shiyan, Hubei, China ' Design School, Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, China ' College of Civil Engineering & Architecture, China Three Gorges University, Yichang, Hubei, China ' Law School, Dong-A University, Busan, South Korea

Abstract: The rapid advancement of Artificial Intelligence (AI) in the automotive sector has introduced complex challenges to Intellectual Property (IP) protection, particularly due to the proliferation of deep learning technologies. This study adopts an innovative interdisciplinary approach - encompassing law, technology and economics - to comprehensively address these multifaceted issues. A hybrid model combining Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) with an attention mechanism (CNN-RNN-AM) is developed. The CNN-RNN-AM model integrates the convolutional and sequential processing capabilities of CNN and RNN with the adaptive focus provided by attention mechanisms. Fine-tuned algorithms for convolutional and recurrent operations, as well as attention-based optimisation, enhance the model's capacity for data analysis and feature extraction. A multimodal data fusion strategy is employed to integrate diverse sources, including patent documentation. The neural architecture is optimised using residual connections and bi-directional memory networks, thereby improving feature representation and model robustness.

Keywords: artificial intelligence; automotive industry; deep learning; intellectual property; attention mechanism.

DOI: 10.1504/IJCAT.2025.149868

International Journal of Computer Applications in Technology, 2025 Vol.77 No.1/2, pp.102 - 116

Received: 06 Mar 2025
Accepted: 04 Jun 2025
Published online: 14 Nov 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article