Predicting Institution Outcomes for Inter Partes Review (IPR) Proceedings at the United States Patent Trial & Appeal Board by Deep Learning of Patent Owner Preliminary Response Briefs

Abstract

A key challenge for artificial intelligence in the legal field is to determine from the text of a party’s litigation brief whether, and why, it will succeed or fail. This paper shows a proof-of-concept test case from the United States: predicting outcomes of post-grant inter partes review (IPR) proceedings for invalidating patents. The objectives are to compare decision-tree and deep learning methods, validate interpretability methods, and demonstrate outcome prediction based on party briefs. Specifically, this study compares and validates two distinct approaches: (1) representing documents with term frequency inverse document frequency (TF-IDF), training XGBoost gradient-boosted decision-tree models, and using SHAP for interpretation. (2) Deep learning of document text in context, using convolutional neural networks (CNN) with attention, and comparing LIME and attention visualization for interpretability. The methods are validated on the task of automatically determining case outcomes from unstructured written decision opinions, and then used to predict trial institution or denial based on the patent owner’s preliminary response brief. The results show how interpretable deep learning architecture classifies successful/unsuccessful response briefs on temporally separated training and test sets. More accurate prediction remains challenging, likely due to the fact-specific, technical nature of patent cases and changes in applicable law and jurisprudence over time.

An Invalidity Strategy against Patent Barriers: Evidence from Chinese Enterprises

“…The integrated resources (i.e. IP Attache, lawyers, technicians, translators, funds, databases) based on the cooperation can assistant the foreign alleged infringer in dealing with speci cs of the proceedings like detailed retrieval, petition writing as well as expert depositions, oral hearing, while the former two are the key element in initiating a trial (Mishra et al, 2017;Sokhansanj & Rosen, 2022), the latter two determine the probability that the patent being invalid (Bar & Kalinowski, 2019). Hence, we propose the hypothesis 1a.…”

“…which the APJs decides whether the petition along with evidences submitted therewith, can demonstrate a reasonable likelihood that the petitioner would prevail with respect to at least one of the claims challenged (Mishra et al, 2017). Once the petition instituted, the APJs may decide to institute review for partial or all the petitioned claims, then a nal verdict on patent validity will issue after the second stage's additional brie ng, expert depositions and oral hearing (Sokhansanj & Rosen, 2022). Six possible outcomes are: denial (respondent wins), grant (the petitioner wins), denial on rehearing (the respondent ask for the decision to be reconsidered and the APJs reverse it), grant on rehearing, mixed (trial granted on some grounds or claims but not on others) and inde nite.…”