AI-Based Patent Novelty Checker and Prior-Art Analysis Using Transformer Embeddings and FAISS

The proposed AI-Based Patent Novelty Checker and Prior-Art Analysis System provides an intelligent and efficient approach for evaluating patent novelty using semantic search and Artificial Intelligence. By integrating transformer-based embeddings, FAISS vector indexing, Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs), the system accurately retrieves similar patents, calculates novelty scores, identifies technical similarities, and generates automated patent analysis reports. The proposed solution reduces manual effort, improves search accuracy, and supports researchers, inventors, startups, and patent professionals in making informed patent filing decisions.

[1] A. M. Villa and M. Wirz, "A Sequential Patent Search Approach Combining Semantics and Artificial Intelligence to Identify Initial State-of-the-Art Documents," World Patent Information, vol. 68, p. 102096, 2022.   [2] Y. Maehara, Y. Osabe, et al., "Macro Analysis of Decarbonization-Related Patent Technologies by Patent Domain-Specific BERT," World Patent Information, vol. 69, p. 102112, 2022.   [3] L. Siddharth, G. Li, and J. Luo, "Enhancing Patent Retrieval Using Text and Knowledge Graph Embeddings: A Technical Note," arXiv preprint arXiv:2211.01976, 2022.   [4] K. Vowinckel and V. D. Hähnke, "SEARCHFORMER: Semantic Patent Embeddings by Siamese Transformers for Prior Art Search," World Patent Information, vol. 73, p. 102192, 2023.   [5]   K. Higuchi and K. Yanai, "Patent Image Retrieval Using Transformer-Based Deep Metric Learning," World Patent Information, vol. 74, p. 102217, 2023.   [6]  H. Wang and Y. Zhang, "Learning Efficient Representations for Image-Based Patent Retrieval," arXiv preprint arXiv:2308.13749, 2023.   [7] S. Björkqvist and J. Kallio, "Building a Graph-Based Patent Search Engine," *Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '23)*, pp. 3300–3304, 2023. [8]  V. Stamatis and M. Salampasis, "Results Merging in the Patent Domain," arXiv preprint arXiv:2203.00350, 2022.   [9]   K. Daniell, I. Buzhinsky, and S. Björkqvist, "Efficient Patent Searching Using Graph Transformers," arXiv preprint arXiv:2508.10496, 2025.   [10]  A. Ali, A. Tufail, L. C. De Silva, and P. E. Abas, "Innovating Patent Retrieval: A Comprehensive Review of Techniques, Trends, and Challenges in Prior Art Searches," *Applied System Innovation*, vol. 7, no. 5, p. 91, 2024.