US 12,259,945 B2
Systems, methods, and storage media for training a model for image evaluation
Elham Saraee, Medford, MA (US); Jehan Hamedi, Wellesley, MA (US); and Zachary Halloran, Franklin, MA (US)
Assigned to VIZIT LABS, INC., Boston, MA (US)
Filed by VIZIT LABS, INC., Boston, MA (US)
Filed on Oct. 21, 2024, as Appl. No. 18/922,058.
Application 16/672,227 is a division of application No. 16/271,780, filed on Feb. 8, 2019, granted, now 10,467,504, issued on Nov. 5, 2019.
Application 18/922,058 is a continuation of application No. 18/737,861, filed on Jun. 7, 2024, granted, now 12,124,535.
Application 18/737,861 is a continuation of application No. 18/416,371, filed on Jan. 18, 2024, granted, now 12,019,707, issued on Jun. 25, 2024.
Application 18/416,371 is a continuation of application No. 18/471,771, filed on Sep. 21, 2023, granted, now 11,880,429, issued on Jan. 23, 2024.
Application 18/471,771 is a continuation of application No. 17/979,978, filed on Nov. 3, 2022, granted, now 11,768,913, issued on Sep. 26, 2023.
Application 17/979,978 is a continuation of application No. 17/857,980, filed on Jul. 5, 2022, granted, now 11,531,840, issued on Dec. 20, 2022.
Application 17/857,980 is a continuation in part of application No. 17/466,820, filed on Sep. 3, 2021, granted, now 11,663,811, issued on May 30, 2023.
Application 17/466,820 is a continuation of application No. 16/672,227, filed on Nov. 1, 2019, granted, now 11,113,572, issued on Sep. 7, 2021.
Claims priority of provisional application 63/218,814, filed on Jul. 6, 2021.
Prior Publication US 2025/0045358 A1, Feb. 6, 2025
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06V 10/40 (2022.01); G06V 10/82 (2022.01)
CPC G06F 18/214 (2023.01) [G06F 18/22 (2023.01); G06V 10/40 (2022.01); G06V 10/82 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
determining, by a computing device, a target audience of a plurality of training content items;
assigning, by the computing device, an identifier of the target audience to a model;
receiving, by the computing device, a request including a candidate content item and an identification of the target audience, the candidate content item corresponding to a plurality of features;
determining, by the computing device, the candidate content item is of the target audience;
determining, by the computing device using the model, a candidate content item performance score for the candidate content item based on an impact of each of the plurality of features on performance scores generated by the model for the target audience,
wherein determining the candidate content item performance score using the model comprises executing the model using the candidate content item responsive to determining the target audience of the candidate content item matches the assigned identifier of the generated model; and
generating, by the computing device, a record identifying the candidate content item performance score for the candidate content item.