US 12,093,702 B2
Method and electronic device for managing a boost time required for an application launch
Naresh Kumar Narasimma Moorthy, Bengaluru (IN); Dwait Bhatt, Bengaluru (IN); Anuradha Kanukotla, Bengaluru (IN); Sripurna Mutalik, Bengaluru (IN); Prateek Bansal, Bengaluru (IN); Jaeho Kim, Suwon-si (KR); Syama Sudheesh, Bengaluru (IN); and Renju Chirakarotu Nair, Bengaluru (IN)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Aug. 3, 2022, as Appl. No. 17/880,234.
Claims priority of application No. 202141034945 (IN), filed on Aug. 3, 2021; application No. 202241031576 (IN), filed on Jun. 2, 2022; and application No. 2021 41034945 (IN), filed on Jul. 26, 2022.
Prior Publication US 2023/0045617 A1, Feb. 9, 2023
Int. Cl. G06F 9/445 (2018.01); G06N 5/022 (2023.01)
CPC G06F 9/44521 (2013.01) [G06N 5/022 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A method for managing a boost time required for an application launch in an electronic device, the method comprising:
detecting, by the electronic device, a user input to launch the application running in the electronic device;
measuring, by the electronic device, real-time system health parameters of the electronic device;
predicting, by the electronic device, an application launch time by inputting the real-time system health parameters to an artificial intelligence (AI)-based application prediction model; and
boosting, by the electronic device, at least one hardware of the electronic device based on the predicted application launch time,
wherein the method further comprises training the AI-based application prediction model by:
obtaining, by the electronic device, screen frames of the electronic device for a plurality of application launches while at least one application of a plurality of applications is launched at the electronic device;
determining, by the electronic device, a plurality of system health parameters of the electronic device while at least one application of the plurality of applications is launched at the electronic device;
determining, by the electronic device, an application launch time of the at least one application based on the screen frames of the electronic device and the plurality of system health parameters; and
training, by the electronic device, the AI-based application prediction model with the determined application launch time and the plurality of system health parameters of the electronic device, and
wherein the determining, by the electronic device, of the application launch time of the at least one application for each of the application launch comprises:
determining, by the electronic device, a launch start time (LST) by comparing the screen frames of the electronic device with an initial frame of the electronic device for each application launch of the plurality of application launches;
determining, by the electronic device, a launch end time (LET) by comparing the screen frames of the electronic device with a final frame of the electronic device for each application launch of the plurality of application launches;
determining, by the electronic device, a difference between the LST and the LET; and
determining, by the electronic device, the application launch time of the at least one application for each of the application launch based on the difference between the LST and the LET.