Structural Representation Learning and Disentanglement for Evidential Chinese Patent Approval Prediction

TL;DR

This paper introduces DiSPat, a novel framework for Chinese patent approval prediction that leverages structural representation learning and disentanglement to improve accuracy and provide decision-making evidence.

Contribution

It pioneers a retrieval-based classification approach with structural and disentangled representations for evidential patent approval prediction.

Findings

DiSPat outperforms state-of-the-art baselines on three Chinese patent datasets.

The framework enhances evidentiality in patent approval decisions.

Structural and disentangled representations improve prediction accuracy.

Abstract

Automatic Chinese patent approval prediction is an emerging and valuable task in patent analysis. However, it involves a rigorous and transparent decision-making process that includes patent comparison and examination to assess its innovation and correctness. This resultant necessity of decision evidentiality, coupled with intricate patent comprehension presents significant challenges and obstacles for the patent analysis community. Consequently, few existing studies are addressing this task. This paper presents the pioneering effort on this task using a retrieval-based classification approach. We propose a novel framework called DiSPat, which focuses on structural representation learning and disentanglement to predict the approval of Chinese patents and offer decision-making evidence. DiSPat comprises three main components: base reference retrieval to retrieve the Top-k most similar patents as a reference base; structural patent representation to exploit the inherent claim hierarchy in patents for learning a structural patent representation; disentangled representation learning to learn disentangled patent representations that enable the establishment of an evidential decision-making process. To ensure a thorough evaluation, we have meticulously constructed three datasets of Chinese patents. Extensive experiments on these datasets unequivocally demonstrate our DiSPat surpasses state-of-the-art baselines on patent approval prediction, while also exhibiting enhanced evidentiality.