Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MODEL TRAINING METHOD AND APPARATUS, VIDEO USER EXPERIENCE PREDICTION METHOD AND APPARATUS, AND ELECTRONIC DEVICE
Document Type and Number:
WIPO Patent Application WO/2023/045886
Kind Code:
A1
Abstract:
The present application relates to the technical field of communications. Disclosed are a model training method and apparatus, a video user experience prediction method and apparatus, and an electronic device. The model training method comprises: collecting video user experience category data at a user equipment (UE) side, and collecting, at a base station side, radio performance data of the base station side, which radio performance data is generated when a user watches a video; generating a feature matrix according to the radio performance data of the base station side; training a convolutional neural network model on the basis of a preset algorithm, and taking the trained convolutional neural network model as a video user experience prediction model, wherein model training data comprises the feature matrix and the video user experience category data, and the video user experience prediction model is used for predicting the video user experience in real time according to the radio performance data of the base station side.

Inventors:
LIAO JINLONG (CN)
XU JING (CN)
WANG BO (CN)
RUI HUA (CN)
LV XINGZAI (CN)
Application Number:
PCT/CN2022/119734
Publication Date:
March 30, 2023
Filing Date:
September 19, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ZTE CORP (CN)
International Classes:
H04N21/466
Foreign References:
CN102685790A2012-09-19
CN102769551A2012-11-07
CN106604290A2017-04-26
CN111401637A2020-07-10
US20190287031A12019-09-19
US20200053591A12020-02-13
Attorney, Agent or Firm:
COHORIZON INTELLECTUAL PROPERTY INC. (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: SYNCHRONIZATION METHOD AND APPARATUS

Next Patent: METHOD FOR PREPARING CARBON DIOXIDE-BASED QUATERNARY COPOLYMER