US 12,032,974 B2
Method and electronic device for accelerating asset execution
Anuradha Kanukotla, Karnataka (IN); Sumeen Agrawal, Karnataka (IN); Jaeho Kim, Suwon-si (KR); Kumar Abhisek, Karnataka (IN); Pavan Nittur, Karnataka (IN); Sripurna Mutalik, Karnataka (IN); and Wonseo Choi, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Jan. 8, 2021, as Appl. No. 17/144,538.
Claims priority of application No. 202041001207 (IN), filed on Jan. 10, 2020; and application No. 202041001207 (IN), filed on Dec. 9, 2020.
Prior Publication US 2021/0216335 A1, Jul. 15, 2021
Int. Cl. G06F 9/451 (2018.01); G06F 9/50 (2006.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06F 9/451 (2018.02) [G06F 9/5016 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A method for accelerating an asset execution in an electronic device, comprising:
detecting, by the electronic device, a User Interface (UI) transition associated with a first application;
predicting, by the electronic device, a sequence of at least one asset to be offloaded for a subsequent UI transition based on an asset parameter using a Machine Learning (ML) model;
offloading, by the electronic device, the at least one asset in the sequence; and
storing, by the electronic device, the at least one offloaded asset to memory of the electronic device,
wherein offloading the at least one asset in the sequence comprises:
determining, by the electronic device, a number of threads required to load the at least one asset in each thread based on a weight of a feature set and a rating for a value range of the feature set, wherein the feature set comprises a Central Processing Unit (CPU) usage, types of assets, a size of assets, a number of assets, and a device memory utilization;
loading, by the electronic device, the at least one asset to each thread for a forecasted time interval in the sequence based on the feature set; and
decoding, by the electronic device, the at least one asset in each thread.