Details
Poster
Presenter(s)
![Baoxian Zhou Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/21152.jpg?h=1b08aa16&itok=bpXsZzsD)
Display Name
Baoxian Zhou
- Affiliation
-
AffiliationTianjin University of Science and Technology
- Country
Abstract
With the development of smart grid, the continuous updating of power grid data texts has increased the redundancy of the database, which has led to difficulties of filtering and obtaining information. Therefore, an intelligent recommendation method for power grid data is proposed, which combines deep learning to mark entities based on existing knowledge bases and knowledge graphs, and then uses intent prediction matching algorithms to deeply mine user search intentions to realize accurate prediction of user search intent. The experimental results show that the model has a good prediction effect, a wide range of applications, and effectively improves work efficiency.