Deep Patent Landscaping Model Using Transformer and Graph Embedding
This work addresses the need for automated patent landscaping to reduce resource-intensive manual processes in R&D, though it is incremental as it builds on existing deep learning and graph embedding techniques.
The authors tackled automated patent landscaping by proposing a deep learning model that combines a modified transformer for text analysis and a graph embedding method (Diff2Vec) for metadata, along with introducing four benchmark datasets; the model achieved state-of-the-art performance compared to existing models.
Patent landscaping is a method used for searching related patents during a research and development (R&D) project. To avoid the risk of patent infringement and to follow current trends in technology, patent landscaping is a crucial task required during the early stages of an R&D project. As the process of patent landscaping requires advanced resources and can be tedious, the demand for automated patent landscaping has been gradually increasing. However, a shortage of well-defined benchmark datasets and comparable models makes it difficult to find related research studies. In this paper, we propose an automated patent landscaping model based on deep learning. To analyze the text of patents, the proposed model uses a modified transformer structure. To analyze the metadata of patents, we propose a graph embedding method that uses a diffusion graph called Diff2Vec. Furthermore, we introduce four benchmark datasets for comparing related research studies in patent landscaping. The datasets are produced by querying Google BigQuery, based on a search formula from a Korean patent attorney. The obtained results indicate that the proposed model and datasets can attain state-of-the-art performance, as compared with current patent landscaping models.