Application technology opportunity discovery from technology portfolios: Use of patent classification and collaborative filtering

- An approach for TOD customized to a firm's technology capability portfolio is proposed.
- Classification codes and collaborative filtering of large-scale patents are used for TOD.
- Three indices are used to classify TOD results for technical decision-making support.
- A TOD case is demonstrated using the technology portfolio defined by an SME's patents.

Technology opportunity discovery (TOD), customized to a firm's current technology capability, can be a good starting point to formulate a technology strategy for a firm that lacks technology information, experts, and/or facilities. Although patent-based studies have suggested systematic methods for customized TOD, these methods have limitations such as insufficient consideration of a target firm's technology portfolio and difficulty of method reproducibility due to expert intervention-based text mining. Therefore, this paper proposes an approach to determine application technology opportunities customized to a target firm by applying collaborative filtering to firms' technology portfolios, which are represented as a set of patent classification codes of the firm's patents. The proposed method involves 1) structuring technology portfolios as firm-international patent classification (IPC) distribution vectors using main group-level IPC codes of the applicants' patents, 2) recommending main group-level IPCs untapped by the target firm and with high preference scores by using collaborative filtering, and 3) classifying the recommended IPCs for the firm's strategic decision-making support using indexes of heterogeneity, growth rate, and competition level. To show the workings of this approach, we applied it to a high-tech firm with wireless communication technology, building on the analysis of large-scale patents and their applicants. This approach is expected to contribute to the systematic identification of application technology opportunities customized to firms and across various industries, and to become a basis for developing future technology intelligence systems.