TECHNOLOGICAL CONVERGENCE IDENTIFICATION MODEL (TCIM) FOR R&D&I ACTIVITIES

Abstract

Technological advancements have accelerated the emergence of new technologies, and with these rapid changes, organizations must identify new innovation opportunities. In this context, Technology Convergence (TC) emerges as a critical factor, integrating distinct technologies to meet the complex demands of society and the competitive market. The development of research focused on identifying emerging technologies is vital to effectively respond to disruptive forces and innovate in existing businesses. To this end, the objective of this study is to propose a model aimed at identifying TC to support managers' decision-making in Research, Development, and Innovation (R&D&I) activities. The method employed was the implementation of the model to identify technological convergences from patent analysis, integrating Knowledge Graphs (KG), semantic technologies in Natural Language Processing (NLP), and Artificial Neural Networks (ANN) based on Transformer architectures. Preliminary results indicate that the integration of KGs, NLP, and ANNs represents a possible solution, demonstrating viability for identifying convergence patterns from patent data and assisting managers in decision-making during R&D&I activities.