Patent Analytics Based on Feature Vector Space Model: A Case of IoT

TL;DR

This paper introduces a feature vector space model (FVSM) for patent analysis, leveraging CNN-extracted features to overcome limitations of traditional VSM, demonstrated through an IoT patent case study.

Contribution

It proposes a novel FVSM that improves patent analysis by capturing sentence semantics and reducing dimensionality, replacing traditional VSM.

Findings

FVSM outperforms traditional VSM in patent similarity tasks

Enhanced clustering and mapping accuracy with FVSM

Effective application demonstrated in IoT patent case study

Abstract

The number of approved patents worldwide increases rapidly each year, which requires new patent analytics to efficiently mine the valuable information attached to these patents. Vector space model (VSM) represents documents as high-dimensional vectors, where each dimension corresponds to a unique term. While originally proposed for information retrieval systems, VSM has also seen wide applications in patent analytics, and used as a fundamental tool to map patent documents to structured data. However, VSM method suffers from several limitations when applied to patent analysis tasks, such as loss of sentence-level semantics and curse-of-dimensionality problems. In order to address the above limitations, we propose a patent analytics based on feature vector space model (FVSM), where the FVSM is constructed by mapping patent documents to feature vectors extracted by convolutional neural networks (CNN). The applications of FVSM for three typical patent analysis tasks, i.e., patents similarity comparison, patent clustering, and patent map generation are discussed. A case study using patents related to Internet of Things (IoT) technology is illustrated to demonstrate the performance and effectiveness of FVSM. The proposed FVSM can be adopted by other patent analysis studies to replace VSM, based on which various big data learning tasks can be performed.