US 11,775,357 B1
Relevant notifications of third party content
Ravneet Ghuman, Phoenix, AZ (US); Madhu Sudhan Reddy Gudur, Phoenix, AZ (US); Sandeep Bose, Phoenix, AZ (US); Shashank Kapoor, Phoenix, AZ (US); Rahul Panwar, New York, NY (US); Nikhil Jain, Phoenix, AZ (US); and Vinod Yadav, Scottsdale, AZ (US)
Assigned to American Express Travel Related Services Company, Inc., New York, NY (US)
Filed by American Express Travel Related Services Company, Inc., New York, NY (US)
Filed on Jan. 20, 2021, as Appl. No. 17/153,170.
Int. Cl. G06F 16/00 (2019.01); G06F 9/54 (2006.01); G06F 16/958 (2019.01); G06N 20/00 (2019.01); G06F 16/955 (2019.01); G06F 16/906 (2019.01)
CPC G06F 9/542 (2013.01) [G06F 16/906 (2019.01); G06F 16/958 (2019.01); G06F 16/9566 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a computing device comprising a processor and a memory; and
machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
receive a plurality of publications from a third party data source based at least in part on a keyword topic, wherein the plurality of publications are individually displayed on a respective web page and include an event associated with the keyword topic;
generate an embedding for at least one of the plurality of publications based at least in part on executing a text embedding service, wherein the embedding comprises a plurality of numeric representations that individually correspond to a unique word;
determine a reference embedding associated with the keyword topic based at least in part on a context profile that provides a particular context of use for the keyword topic, the context profile including a criteria for filtering the plurality of publications related to a context of use for the keyword topic;
classify a subset of the plurality of publications as associated with the keyword topic by generating a similarity score from the embedding of the plurality of publications and the reference embedding associated with the keyword topic;
identify a plurality of organizations included in the subset of the plurality of publications based at least in part on a context of a respective organization included in the subset of the plurality of publications;
generate a list based at least in part on identifying a portion of the plurality of organizations corresponding to an entity name in a database; and
transmit a notification to a client device, wherein the notification includes the entity name from the list and a uniform resource locator for the respective web page associated with the event.