US 11,838,591 B2
Methods and systems for recommendations based on user-supplied criteria
Michael Joseph Karlin, Bethesda, MD (US); Daniel Z. Zanger, San Francisco, CA (US); and Ariel Mikhael Katz, Potomac, MD (US)
Assigned to MARKETX LLC, Bethesda, MD (US)
Appl. No. 17/759,029
Filed by MarketX LLC, Bethesda, MD (US)
PCT Filed Feb. 10, 2021, PCT No. PCT/US2021/017475
§ 371(c)(1), (2) Date Jul. 18, 2022,
PCT Pub. No. WO2021/163206, PCT Pub. Date Aug. 19, 2021.
Claims priority of provisional application 62/972,430, filed on Feb. 10, 2020.
Prior Publication US 2023/0040678 A1, Feb. 9, 2023
Int. Cl. H04N 21/466 (2011.01); H04N 21/25 (2011.01); H04N 21/258 (2011.01); H04N 21/475 (2011.01)
CPC H04N 21/4668 (2013.01) [H04N 21/251 (2013.01); H04N 21/25891 (2013.01); H04N 21/4666 (2013.01); H04N 21/4755 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A system of providing recommendations based on user-supplied criteria using machine learning models, the system comprising:
memory; and
non-transitory computer-readable memory comprising instructions that cause a processor to perform operations comprising:
receiving a user preference for content recommendations from a user;
retrieving a user profile for the user;
comparing the user preference to the user profile to determine a criterion for content recommendations for the user by generating a first feature input for a first machine learning model based on the user preference and the user profile and inputting the first feature input into the first machine learning model to receive the criterion, wherein the first machine learning model comprises a first content-based filtering component and a first collaborative filtering component;
receiving a content attribute for content provided by a content provider;
retrieving a content provider profile for the content provider;
comparing the content attribute to the content provider profile to determine a normalized content attribute for content recommendations for the content provider by generating a second feature input for a second machine learning model based on the content attribute and the content provider profile and inputting the second feature input into the second machine learning model to receive the normalized content attribute, wherein the second machine learning model comprises a second content-based filtering component and a second collaborative filtering component;
matching the criterion to the normalized content attribute; and
in response to matching the criterion to the normalized content attribute, generating for display a recommendation to the user for the content.