US 11,880,692 B2
Apparatus and method for managing application program
Hyunjoo Jung, Suwon-si (KR); Jaedeok Kim, Suwon-si (KR); and Chiyoun Park, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Nov. 18, 2020, as Appl. No. 16/951,725.
Application 16/951,725 is a continuation of application No. 16/678,548, filed on Nov. 8, 2019, granted, now 10,884,760.
Claims priority of application No. 10-2019-0000861 (KR), filed on Jan. 3, 2019.
Prior Publication US 2021/0073002 A1, Mar. 11, 2021
Int. Cl. G06F 9/445 (2018.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01); G06N 3/08 (2023.01); G06N 3/045 (2023.01)
CPC G06F 9/445 (2013.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01)] 28 Claims
OG exemplary drawing
 
1. An apparatus for managing a program, the apparatus comprising:
at least one memory storing a common neural network, a first program comprising a first neural network and a first mapping information indicating that the first program utilizes a common neural network that is associated with the first program, and a second program comprising a second neural network, and a second mapping information indicating that the second program utilizes the common neural network; and
at least one processor configured to:
based on execution of the first program:
load the common neural network using the first mapping information, and perform, using the common neural network and the first neural network, a first processing for first data of the first program, and
obtain a first execution result of the first processing for the first data based on the common neural network and the first neural network; and
based on execution of the second program:
load the common neural network using the second mapping information, and perform, using the common neural network and the second neural network, a second processing for second data of the second program, and
obtain a second execution result of the second processing for the second data based on the common neural network and the second neural network,
wherein the first processing for obtaining the first execution result comprises using output data of the common neural network as input data of the first neural network or using output data of the first neural network as input data of the common neural network, and
wherein the second processing for obtaining the second execution result comprises using the output data of the common neural network as input data of the second neural network or using output data of the second neural network as the input data of the common neural network.