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 1–10 of 36 papers

TitleStatusHype
DAPFAM: A Domain-Aware Patent Retrieval Dataset Aggregated at the Family Level—0
Research on feature fusion and multimodal patent text based on graph attention network—0
The evolving boundary of green technology—0
Innovative activities of Activision Blizzard: A patent network analysis—0
Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices—0
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design PatentsCode1
Towards Automated Patent Workflows: AI-Orchestrated Multi-Agent Framework for Intellectual Property Management and Analysis—0
Retrouver l'inventeur-auteur : la levée d'homonymies d'autorat entre les brevets et les publications scientifiques—0
Semantic Similarity Matching for Patent Documents Using Ensemble BERT-related Model and Novel Text Processing Method—0
Unveiling Black-boxes: Explainable Deep Learning Models for Patent Classification—0
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.