Development of a GTM-based patent map for identifying patent vacuums

Abstract

The patent map has long been considered as a useful tool for mining latent technological information. Among others, the detection of patent vacuums, defined as unexplored areas of new technologies, deserves intensive research. However, previous studies for identifying patent vacuums on the patent map have been subjected to some limitations, stemming from the subjective and manual identification of patent vacuums. To address these limitations, this paper proposes a generative topographic mapping (GTM)-based patent map, which aims to automatically identify a patent vacuum. Since GTM is a probabilistic approach of mapping multidimensional data space onto a low-dimensional latent space and vice versa, it contributes to the automatic detection and interpretation of patent vacuums. The proposed approach consists of three stages. Firstly, text mining is executed in order to transform patent documents into keyword vectors as structured data. Secondly, the GTM is employed to develop the patent map, subsequently leading to the discovery of patent vacuums, which are expressed as blank areas in the map. Lastly, the meaning of each patent vacuum is interpreted by the inverse mapping of patent vacuums onto the original keyword vector. The case study is conducted with lithography technology-related patents. We believe the proposed approach not only saves time and effort for identifying patent vacuums, but also increases objectivity and reliability.