Measuring similarity between patents is an essential step to ensure novelty
of innovation. However, a large number of methods of measuring the similarity
between patents still rely on manual classification of patents by experts.
Another body of research has proposed automated methods; nevertheless, most of
it solely focuses on the semantic similarity of patents. In order to tackle
these limitations, we propose a hybrid method for automatically measuring the
similarity between patents, considering both semantic and technological
similarities. We measure the semantic similarity based on patent texts using
BERT, calculate the technological similarity with IPC codes using Jaccard
similarity, and perform hybridization by assigning weights to the two
similarity methods. Our evaluation result demonstrates that the proposed method
outperforms the baseline that considers the semantic similarity only.

提出了一种混合方法来自动测量专利之间的相似度，该方法考虑了语义和技术上的相似性，并使用 BERT 评估文本之间的语义相似度，使用 Jaccard 相似度计算 IPC 代码之间的技术相似度，并通过为两个相似度方法分配权重进行混合化。评估结果表明，该方法优于仅考虑语义相似性的基线。

一种新的专利相似度测量方法：语义距离和技术距离

A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological Distance

Patent data is an important source of knowledge for innovation research,
while the technological similarity between pairs of patents is a key enabling
indicator for patent analysis. Recently researchers have been using patent
vector space models based on different NLP embeddings models to calculate the
technological similarity between pairs of patents to help better understand
innovations, patent landscaping, technology mapping, and patent quality
evaluation. More often than not, Text Embedding is a vital precursor to patent
analysis tasks. A pertinent question then arises: How should we measure and
evaluate the accuracy of these embeddings? To the best of our knowledge, there
is no comprehensive survey that builds a clear delineation of embedding models'
performance for calculating patent similarity indicators. Therefore, in this
study, we provide an overview of the accuracy of these algorithms based on
patent classification performance and propose a standard library and dataset
for assessing the accuracy of embeddings models based on PatentSBERTa approach.
In a detailed discussion, we report the performance of the top 3 algorithms at
section, class, and subclass levels. The results based on the first claim of
patents show that PatentSBERTa, Bert-for-patents, and TF-IDF Weighted Word
Embeddings have the best accuracy for computing sentence embeddings at the
subclass level. According to the first results, the performance of the models
in different classes varies, which shows researchers in patent analysis can
utilize the results of this study to choose the best proper model based on the
specific section of patent data they used.

本研究旨在评估基于不同 NLP 嵌入模型的专利数据嵌入模型计算专利技术相似度的准确度，提出了一个评估嵌入模型准确度的标准库和数据集，研究结果表明 PatentSBERTa、Bert-for-patent 和 TF-IDF 加权词嵌入在子类别级别计算句子嵌入具有最好的精确度。