Already since the 1950s TRIZ shows that patents and the technical
contradictions they solve are an important source of inspiration for the
development of innovative products. However, TRIZ is a heuristic based on a
historic patent analysis and does not make use of the ever-increasing number of
latest technological solutions in current patents. Because of the huge number
of patents, their length, and, last but not least, their complexity there is a
need for modern patent retrieval and patent analysis to go beyond
keyword-oriented methods. Recent advances in patent retrieval and analysis
mainly focus on dense vectors based on neural AI Transformer language models
like Google BERT. They are, for example, used for dense retrieval, question
answering or summarization and key concept extraction. A research focus within
the methods for patent summarization and key concept extraction are generic
inventive concepts respectively TRIZ concepts like problems, solutions,
advantage of invention, parameters, and contradictions. Succeeding rule-based
approaches, finetuned BERT-like language models for sentence-wise
classification represent the state-of-the-art of inventive concept extraction.
While they work comparatively well for basic concepts like problems or
solutions, contradictions - as a more complex abstraction - remain a challenge
for these models. This paper goes one step further, as it presents a method to
extract TRIZ contradictions from patent texts based on Prompt Engineering using
a generative Large Language Model (LLM), namely OpenAI's GPT-4. Contradiction
detection, sentence extraction, contradiction summarization, parameter
extraction and assignment to the 39 abstract TRIZ engineering parameters are
all performed in a single prompt using the LangChain framework. Our results
show that "off-the-shelf" GPT-4 is a serious alternative to existing
approaches.

本文提出了一种基于 Prompt Engineering 的方法，利用生成式大型语言模型（LLM），即 OpenAI 的 GPT-4，从专利文本中提取 TRIZ 矛盾。

基于 LLM 的专利矛盾提取

LLM-based Extraction of Contradictions from Patents

Patent retrieval has been attracting tremendous interest from researchers in
intellectual property and information retrieval communities in the past
decades. However, most existing approaches rely on textual and metadata
information of the patent, and content-based image-based patent retrieval is
rarely investigated. Based on traits of patent drawing images, we present a
simple and lightweight model for this task. Without bells and whistles, this
approach significantly outperforms other counterparts on a large-scale
benchmark and noticeably improves the state-of-the-art by 33.5% with the mean
average precision (mAP) score. Further experiments reveal that this model can
be elaborately scaled up to achieve a surprisingly high mAP of 93.5%. Our
method ranks first in the ECCV 2022 Patent Diagram Image Retrieval Challenge.

基于专利绘图图像的特征，本文提出了一个简单轻量级的模型，用于专利检索，在大规模基准测试上表现显著优于其他方法，均值平均精度（mAP）得分提高了 33.5%，进一步实验证明此模型能够精确扩展以达到惊人的 93.5% 的 mAP，此方法在 ECCV 2022 专利图像检索挑战赛中排名第一。