Open AccessResearch and Application of Construction Method of Power Grid Dispatching Professional Corpus
Author(s) -
Yue Zhang,
Hai Wei,
Han Feng,
Lianfei Shan
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/804/3/032006
Subject(s) - computer science , scheduling (production processes) , natural language processing , grid , artificial intelligence , segmentation , text corpus , corpus linguistics , speech recognition , engineering , operations management , geometry , mathematics
The existing word segmentation tools are difficult to effectively segment the scheduling professional corpus, which leads to the problem of limited application of scheduling professional corpus. A method is proposed for constructing a professional corpus for power grid dispatch based on natural language processing and artificial intelligence technology. Faced with data of various structures and forms, the different methods are applied to establish the recognition model for scheduling professional corpus. The scheduling professional corpus is recognized in database and document table based on rule mask. The entity recognition and relation extraction technology are used to extract professional corpus in text. The scheduling instruction corpus is formed by determining the operation intention and slot of the dispatcher. Finally, the similarity between the scheduling professional corpus are calculated based on the text similarity algorithm, and the semantically identical corpus is formed into a mapping relationship. The application results show that the automatic speech recognition model based on the scheduling professional corpus has higher recognition accuracy and is suitable for practical applications.