PeTIT: Perceiving the Technological Innovation Trends via the Heuristic Model of Community Detection

Patent analysis is widely used in many kinds of research, such as competitive intelligence analysis, technology trends perceiving, industrial distribution planning, macro-economy regulations, and so on. Based on the patent data, this paper proposed a novel algorithm, which named PeTIT, to perceive the technological innovation trends by applying the heuristic community detection model. The PeTIT algorithm included four steps: patent ontology extraction, technological innovation tree construction, technological innovation community detection, and technological innovation trends perceiving. We implemented the PeTIT algorithm on the real dataset of invention patents in the field of artificial intelligence in China, which ranged from Jun 1st, 2000 to May 1st, 2019. The results showed that the innovation situation of artificial intelligent was mainly concentrated in 10 fields. Moreover, the application field of intelligent driving has become one of the fastest-growing industries. Finally, the experimental results demonstrated that the cubic exponential smoothing model had a higher performance by perceiving the technological innovation trends.