Data processing method, device and equipment based on recurrent neural network

The invention discloses a data processing method, device and equipment based on a recurrent neural network, and relates to the field of cloud computing, artificial intelligence and deep learning. According to the scheme, a recurrent neural network comprises a plurality of recurrent units; each circu...

Full description

Saved in:
Bibliographic Details
Main Authors ZHENG HUIHUANG, YU DIANHAI, LI YAMEI, ZHANG LIUJIE, LAN XIANG, GUO FEI, MA YANJUN
Format Patent
LanguageChinese
English
Published 13.10.2020
Subjects
ACOUSTICS
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
MUSICAL INSTRUMENTS
PHYSICS
SPEECH ANALYSIS OR SYNTHESIS
SPEECH OR AUDIO CODING OR DECODING
SPEECH OR VOICE PROCESSING
SPEECH RECOGNITION
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a data processing method, device and equipment based on a recurrent neural network, and relates to the field of cloud computing, artificial intelligence and deep learning. According to the scheme, a recurrent neural network comprises a plurality of recurrent units; each circulating unit comprises a plurality of data processing nodes; each circulating unit further comprisesa starting node; at least one circulating unit further comprises a termination node; at least one data processing node is arranged between the starting node and the ending node. When the first targetprocessing object is processed in the first circulation unit, whether the first target processing object meets a first preset condition or not is judged, and if the first target processing object doesnot meet the first predetermined condition, the starting node in the first cycle unit is executed to add a mark to the data processing node after the starting node, adding of the mark is stopped until the data processing node
Bibliography:Application Number: CN202010600160