Patent №
US 11,604,792
Granted
2023-03-14
Filed 2020
Owner
GUANGDONG UNIVERSITY OF TECHNOLOGY
Lab
—
AI components
6
ml · nlp · vision · speech · planning · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
16824705
The invention discloses a method and a device for constructing a SQL statement based on reinforcement learning, wherein the method includes: initializing an actor-critic network parameter; acquiring a sequence pair of natural language and real SQL statement from a data set; inputting a natural language sequence into an actor network encoder, and inputting a real SQL sequence into a critic network encoder; using an encoded hidden state as an initialized hidden state of a corresponding decoder; gradually predicting, by an actor network decoder, a SQL statement action, and inputting the SQL statement action to a critic network decoder and an environment to obtain a corresponding reward; and using a gradient descent algorithm to update the network parameters, and obtaining a constructing model of the natural language to the SQL statement after repeated iteration training.
AI classification
Ownership
GUANGDONG UNIVERSITY OF TECHNOLOGY
assignment · 522290686
Assignors
CAI, RUICHU, XU, BOYAN, LIANG, ZHIHAO, LI, ZIJIAN, HAO, ZHIFENG, WEN, WEN, CHEN, BINGFENG
On an employer assignment, the assignors are typically the inventors.