US 12,328,476 B2
Content recommendation system and method
Peter Docherty, Glasgow (GB); Christopher McGuire, Glasgow (GB); Alan Ryman, Glasgow (GB); and Shahad Ahmed, Glasgow (GB)
Assigned to ThinkAnalytics Ltd., Glasgow (GB)
Filed by ThinkAnalytics Ltd., Glasgow (GB)
Filed on Apr. 4, 2023, as Appl. No. 18/130,880.
Prior Publication US 2024/0340498 A1, Oct. 10, 2024
Int. Cl. H04N 21/466 (2011.01); G06F 16/783 (2019.01); H04N 21/45 (2011.01); H04N 21/482 (2011.01)
CPC H04N 21/4668 (2013.01) [G06F 16/7844 (2019.01); H04N 21/4532 (2013.01); H04N 21/4826 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method of providing one or more content item recommendations for a user of a content distribution system, the method comprising:
obtaining metadata concerning items of content, the metadata representing at least some properties of the items of content;
at least one of:
determining at least one subject based on the metadata by processing a plurality of features of the metadata and grouping these features into the at least one subject such that the at least one subject is higher level than the plurality of features of the metadata; and
mapping a plurality of features of the metadata to at least one subject, wherein the at least one subject is predetermined, such that the at least one subject is higher level than the plurality of features of the metadata;
providing the at least one subject related to the metadata to be available to the user for selection;
using a selected subject selected by the user and metadata concerning content available from one or more content sources to generate at least one content item recommendation for the user, the one or more content sources having content available for the user to watch or otherwise consume, the one or more content sources having content available for the user to watch or otherwise consume, and
providing the at least one content item recommendation to the user.