Natural language processing in the patent domain: a survey

2024-03-06

Artificial Intelligence Review

AI Summary

Patent texts present unique challenges—including complex hierarchical structure, rigorous legal semantics, and dense technical terminology—posing significant barriers for NLP applications. Method: This work systematically constructs the first comprehensive patent NLP application taxonomy, covering nine analytical and four generative tasks, integrating patent law principles, technical document characteristics, and modern NLP—especially large language models (LLMs). We propose a structured task classification framework that clarifies LLM adaptation pathways, identifies critical bottlenecks (e.g., logical modeling of claims, multimodal text-diagram understanding), and establishes domain-specific evaluation paradigms. Our approach innovatively unifies legal text analysis, fine-grained technical term modeling, patent structural parsing, and multimodal (text + figures) processing to enable targeted LLM adaptation. Contribution/Results: The resulting framework serves as an accessible entry point for NLP researchers into the patent domain, substantially lowering interdisciplinary barriers and advancing high-precision applications—including prior-art retrieval, claim generation, and infringement analysis.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Patents, which encapsulate crucial technical and legal information in text form and referenced drawings, present a rich domain for natural language processing (NLP). As NLP technologies evolve, large language models (LLMs) have demonstrated outstanding capabilities in general text processing and generation tasks. However, the application of LLMs in the patent domain remains under-explored and under-developed due to the complexity of patents, particularly their language and legal framework. Understanding the unique characteristics of patent documents and related research in the patent domain becomes essential for researchers to apply these tools effectively. Therefore, this paper aims to equip NLP researchers with the essential knowledge to navigate this complex domain efficiently. We introduce the relevant fundamental aspects of patents to provide solid background information. In addition, we systematically break down the structural and linguistic characteristics unique to patents and map out how NLP can be leveraged for patent analysis and generation. Moreover, we demonstrate the spectrum of text-based and multimodal patent-related tasks, including nine patent analysis and four patent generation tasks.

Problem

• Exploring NLP applications in complex patent documents
• Addressing under-developed LLM use in patent analysis
• Systematizing patent-specific NLP tasks and characteristics

Innovation

• Survey NLP applications in patent domain
• Analyze patent structure and language
• Explore multimodal patent tasks