US 2022/0092441 A1 · TRAINING METHOD AND APPARATUS, DIALOGUE PROCESSING METHOD AND SYSTEM, AND MEDIUM

Abstract

Disclosed are a reinforcement learning model training method and apparatus, a dialogue processing method and a dialogue system, and a computer-readable storage medium. The reinforcement learning model training method includes: acquiring unlabelled data and labelled data which are used for training a reinforcement learning model; on the basis of the unlabelled data, generating, with reference to the labelled data, an experience pool for training the reinforcement learning model; and using the experience pool to train the reinforcement learning model.

Claims24

Dependent claims

A method for training a reinforcement learning model, comprising:

acquiring unlabeled data and labeled data for training the reinforcement learning model;
generating an experience pool for training the reinforcement learning model with reference to the labeled data, based on the unlabeled data;
and
training the reinforcement learning model by using the experience pool.

1 more element

Dependencies are inferred from the claim text.

Facts

Application

17/413,373Filed 9 May 2020

Priority

CN 201910390546.510 May 2019

Published

24 Mar 2022

Term ends

Not estimatedThe source records don’t support an estimate.

Classification16 codes

G06V 10/82
Using pattern recognition or machine learning: using neural networks
G06F 16/332
Querying: query formulation
G06F 16/35
Of unstructured textual data: clustering; Classification
G06F 18/2155
Generating training patterns; Bootstrap methods, e.g. bagging or boosting: characterised by the incorporation of unlabelled data, e.g. multiple…

Training method and apparatus, dialogue processing method and system, and medium

Life of this patent

Training method and apparatus, dialogue processing method and system, and medium

Life of this patent

Abstract

Claims24