Technology opportunity discovery based on patent analysis: a hybrid approach of subject-action-object and generative topographic mapping
- 27 October 2022
- journal article
- research article
- Published by Taylor & Francis in Technology Analysis & Strategic Management
- Vol. 36 (9) , 2070-2083
Abstract
An incomplete understanding of the technical details in a firm’s technology selection can lead to a failure in the process of the technology opportunity discovery (TOD) and cause a series of R&D problems. This study proposes an approach for the automated TOD by combining the subject-section-object (SAO) and the generative topographic mapping (GTM), which concentrates on the role of the semantic information in TOD process. First, the semantic information of the technology components in a target field is extracted and the topics of different semantic structures are defined. Second, the GTM-based patent map is established to discover technology opportunities based on a vector matrix composed of patents and topics. Finally, the degree of semantic similarity is applied to measure the technology novelty and to identify promising technology opportunities. The case of the coal-bed methane extraction technology demonstrates that the automated approach based on the semantic information can help understand the concrete details of technology opportunities and improve the accuracy of TOD.Keywords
Funding Information
- Shanghai Science and Technology Program (20040501300, 22692113300)
This publication has 28 references indexed in Scilit:
- Identifying the sources of technological novelty in the process of inventionResearch Policy, 2015
- Document clustering method using dimension reduction and support vector clustering to overcome sparsenessExpert Systems with Applications, 2014
- A semantic analysis approach for identifying patent infringement based on a product–patent mapTechnology Analysis & Strategic Management, 2014
- How to combine term clumping and technology roadmapping for newly emerging science & technology competitive intelligence: “problem & solution” pattern based semantic TRIZ tool and case studyScientometrics, 2014
- An SAO-based text mining approach to building a technology tree for technology planningExpert Systems with Applications, 2012
- Development of a GTM-based patent map for identifying patent vacuumsExpert Systems with Applications, 2012
- An approach to discovering new technology opportunities: Keyword-based patent map approachTechnovation, 2009
- On the development and application of a self–organizing feature map–based patent mapR&D Management, 2002
- The contribution of technology selection to core competenciesInternational Journal of Production Economics, 2002
- Knowledge Spillovers and Patent Citations: Evidence from a Survey of InventorsAmerican Economic Review, 2000