SOTAVerified

Patent classification

Patent reviewers usually are responsible to classify the patent applications, i.e., they assign the design codes. This is time-consuming due to the numerous classification codes. For instance, the U.S. design patent system has 33 classes which are further divided into subclasses. Given that design patents include both titles and visual content, the goal of the experiment is patent classification by integrating titles, captions, and images. Although a single design patent can be associated with multiple design codes, we focus on the primary classification—solving the task as a multi-class classification problem.

Papers

Showing 11–20 of 36 papers

TitleStatusHype
Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent ClassificationCode0
Event-based Dynamic Graph Representation Learning for Patent Application Trend PredictionCode0
A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological DistanceCode0
Multi label classification of Artificial Intelligence related patents using Modified D2SBERT and Sentence Attention mechanism—0
CinPatent: Datasets for Patent Classification—0
Technological taxonomies for hypernym and hyponym retrieval in patent textsCode0
Guiding Data-Driven Design Ideation by Knowledge Distance—0
Patents Phrase to Phrase Semantic Matching Dataset—0
A Survey on Sentence Embedding Models Performance for Patent AnalysisCode0
Automated Single-Label Patent Classification using Ensemble Classifiers—0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.