Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD AND APPARATUS FOR GENERATING TARGET DEEP LEARNING MODEL
Document Type and Number:
WIPO Patent Application WO/2023/245522
Kind Code:
A1
Abstract:
Provided in the present disclosure are a method and apparatus for generating a target deep learning model. The method comprises: acquiring an indication, which is input by a user, and raw data for generating a target deep learning model, wherein the indication comprises a task, which is expected to be executed by means of the target deep learning model; then, generating training data from the raw data; determining a first deep learning model corresponding to the task; and next, training the first deep learning model by using the training data, so as to obtain the target deep learning model.

Inventors:
XIAO HAN (DE)
WANG NAN (CN)
WANG BO (DE)
MAXIMILIAN WERK (DE)
GEORGIOS MASTRAPAS (DE)
Application Number:
PCT/CN2022/100582
Publication Date:
December 28, 2023
Filing Date:
June 22, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
JINA AI GMBH (DE)
JINA AI BEIJING CO LTD (CN)
International Classes:
G06N20/00
Foreign References:
CN110991649A2020-04-10
CN111310934A2020-06-19
CN109325541A2019-02-12
CN109325490A2019-02-12
US20210150340A12021-05-20
Other References:
See also references of EP 4328805A4
Attorney, Agent or Firm:
BEIJING HUIJIALUN INTELLECTUAL PROPERTY AGENCY CO., LTD (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: METHOD AND APPARATUS FOR DETERMINING LOCATION INFORMATION OF CONTROL RESOURCE

Next Patent: METHOD AND APPARATUS FOR GENERATING TRAINING DATA