
Innovation topics within a technology can be defined as generalized technical subjects that the technology desires to develop or improve. Since innovation topics act as a driving force for technical innovation, monitoring such concepts is necessary for understanding the current technology and directing further R&D. However, little attention has been paid to identifying latent innovation topics within a technology, and analyzing their relationships and potential for opportunity. Therefore, this paper proposes a multi-step approach to technological innovation topic analysis, on the basis of patents. The steps consist of: 1) structuring patent-keyword vectors; 2) identifying innovation topics based on semantic patent analysis; 3) constructing an innovation topic network; and 4) generating an opportunity-focused innovation topic map. The process of our approach is illustrated using patents that are related to augmented reality. This method can contribute to the systematic monitoring of a technology system’s innovation topics and their potential.
Patent mining, topic modeling, opportunity analysis, augmented reality technology, Electrical engineering. Electronics. Nuclear engineering, network analysis, TK1-9971
Patent mining, topic modeling, opportunity analysis, augmented reality technology, Electrical engineering. Electronics. Nuclear engineering, network analysis, TK1-9971
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 23 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Top 10% | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Top 10% | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
