.png){kind=icon}
.png){kind=icon}
Return
An evolutionary prediction model for enterprise basic research based on knowledge graph
.png){kind=icon}
OA
AI
DOI：10.1038/s41598-025-89494-z.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Currently, China's enterprise basic research faces problems due to a need for more systematic guidance and dispersed themes. The construction of an enterprise basic research knowledge graph is of great practical significance for tracking the frontier technology of enterprises and playing the leading role of enterprise innovation. By constructing enterprise basic research dataset and mining the intrinsic correlation between data, the paper proposes a multilayer CNN-BiLSTM-based enterprise basic research evolutionary prediction model, and inference complements the enterprise basic research knowledge graph. At the same time, the paper constructs a probabilistic computational model of enterprise basic research with multi-attention mechanism, and computationally obtains the future hotspots of enterprise basic research. The experimental results show that compared with the existing classical models, the KG-CNN-BiLSTM evolutionary prediction model constructed in this paper has significant improvement in indicators such as AUC and F1 value, and excellent prediction accuracy. This study can more accurately capture several types of cutting-edge research topics within the field of basic research, and provides algorithmic guidance for related scholars to predict the development trend in the field of basic research.
Keywords:
Enterprise basic research
Knowledge graph
Attention mechanism
Evolutionary prediction models
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.9
Papers:
27.4W
Citations:
83.5W