US 12,468,776 B2
Method and system for providing customized content using generative artificial intelligence
Doo Geon Hwang, Busan (KR)
Assigned to PIAMOND CORP., Busan (KR)
Filed by Piamond Corp., Busan (KR)
Filed on Dec. 11, 2023, as Appl. No. 18/535,434.
Claims priority of application No. 10-2022-0172872 (KR), filed on Dec. 12, 2022; and application No. 10-2023-0174802 (KR), filed on Dec. 5, 2023.
Prior Publication US 2024/0241920 A1, Jul. 18, 2024
Int. Cl. G06F 16/958 (2019.01); G06N 3/0475 (2023.01); G06Q 30/0202 (2023.01)
CPC G06F 16/958 (2019.01) [G06N 3/0475 (2023.01); G06Q 30/0202 (2013.01)] 8 Claims
OG exemplary drawing
 
1. A method for providing content of a computer device including at least one processor, comprising:
providing, to a user terminal of a user by the at least one processor, a notification regarding provision of target content generated using a generative artificial intelligence model in response that the user terminal accesses a first page including original content;
providing, to the user terminal by the at least one processor, a selection function for selecting, in association with the generative artificial intelligence model, a preference intensity indicating a preference strength associated with the original content;
collecting content information of the original content included in the first page and behavior information of the user for the original content, in relation to the original content, by the at least one processor;
inferring preference information of the user based on the content information and the behavior information, by the at least one processor;
generating the target content through the generative artificial intelligence model based on the preference intensity selected through the selection function and the inferred preference information of the user, by the at least one processor;
providing the generated target content, by the at least one processor; and
providing, to an external service by the at least one processor, identification information of the generated target content including a hash value, parameter information used to call the generative artificial intelligence model, and the preference information used by the generative artificial intelligence model to generate the target content,
wherein the first page includes a function for collecting behavior information of the user for the first page in real-time and asynchronously,
wherein the generating the target content comprises:
determining whether to provide the target content based on consent of the user including cookies consent with regard to provision of the target content using the generative artificial intelligence model; and
generating the target content through the generative artificial intelligence model based on the inferred preference information of the user in case that it is determined to provide the target content in response to the consent of the user,
wherein the generating the target content comprises:
generating the target content by using a first preference information of the user previously inferred for a second page which the user has previously visited before the first page, in response that content consumption time for the first page by the user inferred based on the behavior information is shorter than preset average time, and
generating the target content by using a second preference information of the user inferred for the first page in response that the content consumption time is longer than the preset average time, and
wherein the providing the generated target content comprises updating, in real-time, content to be displayed at bottom of the first page as the target content according to the user's scrolling operation for the first page.