US 12,353,472 B2
Generic card feature extraction based on card rendering as an image
Nadav Golbandi, New York, NY (US); and Uri Schonfeld, San Jose, CA (US)
Assigned to Yahoo Assets LLC, New York, NY (US)
Filed by Yahoo Assets LLC, New York, NY (US)
Filed on Mar. 3, 2023, as Appl. No. 18/116,882.
Application 18/116,882 is a continuation of application No. 17/135,933, filed on Dec. 28, 2020, granted, now 11,599,571.
Application 17/135,933 is a continuation of application No. 16/393,836, filed on Apr. 24, 2019, granted, now 10,878,023, issued on Dec. 29, 2020.
Application 16/393,836 is a continuation of application No. 15/190,030, filed on Jun. 22, 2016, granted, now 10,318,573, issued on Jun. 11, 2019.
Prior Publication US 2023/0205811 A1, Jun. 29, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/532 (2019.01); G06F 16/58 (2019.01); G06F 16/9535 (2019.01); G06T 11/60 (2006.01); G06V 10/22 (2022.01); G06V 10/778 (2022.01)
CPC G06F 16/532 (2019.01) [G06F 16/58 (2019.01); G06F 16/9535 (2019.01); G06T 11/60 (2013.01); G06V 10/235 (2022.01); G06V 10/778 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
providing a content item for presentation via a client device associated with a user;
providing a second content item for presentation via at least one of the client device or a second client device associated with the user;
responsive to processing an indication of user interaction with the content item and a second indication of user interaction with the second content item, applying, as training data to a computer-generated model, (i) context features of the client device by which the indication of user interaction was generated and (ii) a feature of both the content item and the second content item;
providing, for presentation via at least one of the client device or the second client device, a third content item using the computer-generated model; and
responsive to processing an indication associated with the third content item, updating the computer-generated model based, at least in part, on one or more features of the third content item.