This study explores the development and application of generative artificial intelligence (AI) for technological trend analysis and patent research automation. The research addresses the inefficiencies in traditional patent research, which is labour-intensive and costly, proposing a solution based on AI technologies such as machine learning, natural language processing (NLP), and vector database systems. The proposed solution incorporates MLOps and RAG frameworks for data collection, analysis, and integration, enabling the automation of patent data processing and keyword extraction through modified TF-IDF algorithms and semantic embeddings. The architecture includes tools for clustering patents by thematic and contextual similarities, significantly reducing the time required for research and enhancing accuracy. Experimental results demonstrate the effectiveness of the developed system, achieving significant improvements in the speed of generating patent studies (30–60 minutes) and the precision of information retrieval. The study highlights the transformative potential of generative AI in streamlining intellectual property analysis and fostering technological innovation.