US 12,292,933 B2
Identifying instances of digital content
Jennifer Jiaying Qian, New York, NY (US); and Mateus De Araujo Lopes, Naperville, IL (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Jun. 7, 2023, as Appl. No. 18/206,901.
Claims priority of provisional application 63/490,874, filed on Mar. 17, 2023.
Prior Publication US 2024/0311428 A1, Sep. 19, 2024
Int. Cl. G06F 16/903 (2019.01); G06F 16/55 (2019.01); G06F 16/58 (2019.01); G06F 16/906 (2019.01); G06F 40/295 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)
CPC G06F 16/90344 (2019.01) [G06F 16/55 (2019.01); G06F 16/5866 (2019.01); G06F 16/906 (2019.01); G06F 40/295 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by a processing device, input data describing attributes of an entity segment and keywords that are associated with the attributes of the entity segment;
computing, by the processing device, numerical vector-based representations of the keywords using a machine-learning model trained on training data to classify semantically similar keywords;
identifying, by the processing device, additional keywords from a keyword corpus that are semantically similar to the keywords by comparing the numerical vector-based representations of the keywords with numerical vector-based representations of keywords of the keyword corpus using the machine-learning model and determining whether the keywords and the additional keywords have a threshold amount of similarity;
compiling, by the processing device, a set of matchable keywords that includes the keywords and the additional keywords;
identifying, by the processing device, candidate instances of digital content from a content repository based on comparing content keywords assigned to the candidate instances of the digital content and the set of matchable keywords; and
generating, by the processing device, an indication of an instance of the digital content for display in a user interface based on the candidate instances of the digital content.