US 11,941,376 B2
AI differentiation based HW-optimized intelligent software development tools for developing intelligent devices
Won-Tae Kim, Cheonan-si (KR); Young-Jin Kim, Cheongju-si (KR); and Deun-Sol Cho, Cheonan-si (KR)
Assigned to Korea University of Technology, Cheonan-si (KR); and Education Industry-University Cooperation Foundation, Chungcheongnam-do (KR)
Filed by KOREA UNIVERSITY OF TECHNOLOGY AND EDUCATION INDUSTRY-UNIVERSITY COOPERATION FOUNDATION, Cheonan-si (KR)
Filed on Dec. 6, 2021, as Appl. No. 17/542,545.
Claims priority of application No. 10-2021-0162280 (KR), filed on Nov. 23, 2021.
Prior Publication US 2023/0161568 A1, May 25, 2023
Int. Cl. G06F 8/35 (2018.01); G06F 8/10 (2018.01); G06F 8/41 (2018.01); G06F 8/60 (2018.01); G06N 20/00 (2019.01)
CPC G06F 8/35 (2013.01) [G06F 8/10 (2013.01); G06F 8/44 (2013.01); G06F 8/60 (2013.01); G06N 20/00 (2019.01)] 9 Claims
OG exemplary drawing
 
1. A method of providing intelligent software, the method comprising:
receiving a pre-trained AI model and meta information of the AI model;
creating a plurality of AI differentiation models from the AI model in accordance with a plurality of differentiation levels;
performing profiling on the AI differentiation models on the basis of pre-differentiation AI information;
storing AI model data, which includes the meta information of the AI model, the AI differentiation models, hardware specifications of the device, and the profile information, into a storage; and
receiving demands of a target device, and selecting a first model, which satisfies the demands, from the AI model data stored in the storage, and transmitting the first model to the target device.