Two Findings from the Analysis of Pharmaceutical Patents -Sales Estimation and Patent Grant Prediction within Patent Family
浩一 上條, 和夫 大関 · Institutional Repositories DataBase (IRDB) · 2022
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Institutional Repositories DataBase (IRDB) · National Institute of Informatics · article · 2022
Abstract
Abstract:We report two cases of findings obtained by analyzing the specification of pharmaceutical patents using machine learning.The first is about pharmaceutical sales estimation.Many pharmaceutical companies take a huge amount of time and money to develop a pharmaceutical, and it is strongly desired to estimate future sales volume at an early development stage.The second is about the patent family.Many pharmaceutical companies apply for the same patent in multiple countries as a patent family, but it is often the case that the same patent is granted in one country but not in another.In both cases, it turns out that deep learning provides good predictive performance by using the words used in the patent and the "hot" words that were also published in the journal at the time of filing.Keywords:sales estimation, pharmaceuticals, patent specification, deep learning, natural language processing.
Open the resolved locator · 10.57403/00000017
Metadata licence: OpenAlex metadata (CC0)