Title:
TASK OPTIMIZATION METHOD AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2023/185971
Kind Code:
A1
Abstract:
Provided in the embodiments of the present specification are a task optimization method and apparatus. The task optimization method comprises: performing semantic parsing on an acquired initial file, so as to obtain model data; acquiring a model feature according to the model data, and inputting the model feature into a solver selection model, so as to obtain target solution information; and performing solving on the model data according to the target solution information, so as to obtain an optimization result. A model feature is acquired according to model data, and the model feature is input into a solver selection model, so as to obtain target solution information, such that an appropriate solver is selected to perform solving on the model, thereby improving the accuracy of an optimization result.
Inventors:
ZHAO LIANG (CN)
HUANG KUOLING (US)
YIN WOTAO (CN)
HUANG KUOLING (US)
YIN WOTAO (CN)
Application Number:
PCT/CN2023/084938
Publication Date:
October 05, 2023
Filing Date:
March 30, 2023
Export Citation:
Assignee:
ALIBABA CHINA CO LTD (CN)
International Classes:
G06F8/41; G06F8/35; G06Q10/04; G06Q10/06; G06Q50/06
Domestic Patent References:
| WO2016057001A1 | 2016-04-14 |
Foreign References:
| CN114741075A | 2022-07-12 | |||
| CN114077494A | 2022-02-22 | |||
| CN111159897A | 2020-05-15 | |||
| CN111812982A | 2020-10-23 |
Attorney, Agent or Firm:
BEIJING TONGJUN LAW FIRM (CN)
Download PDF: