101. Power System Text Information Matehing Researeh Based on Deep Learning
- Author
-
Xuan Xiaohua, Bao Wei, Ruan Lixiang, Shi Liqin, Lu Chengyu, and Luo Huafeng
- Subjects
Matching (statistics) ,Computer science ,business.industry ,Deep learning ,Text segmentation ,Control (management) ,Keyword extraction ,Word formation ,computer.software_genre ,Recurrent neural network ,Artificial intelligence ,business ,computer ,Natural language processing ,Word (computer architecture) - Abstract
An information matching technique based on deep learning is proposed: The word sequence of the text is obtained by Chinese text segmentation model using word formation. Then, keyword extraction model is employed to classify large-scale textual information (the texts with the same keyword are treated as in the same group). Finally, the matching degree is given by the two-tier deep learning model, in which the first tier is used to judge whether the texts belong to the same group, and the second tier to calculate the matching degree. The examples indicate that the technique can provide effective results in dispatching/control information matching and operating instruction matching.
- Published
- 2019