US 11,869,063 B2
Optimize shopping route using purchase embeddings
Kate Key, Powhatan, VA (US); Anh Truong, Champaign, IL (US); Jeremy Goodsitt, Champaign, IL (US); Galen Rafferty, Mahomet, IL (US); Austin Walters, Savoy, IL (US); and Vincent Pham, Champaign, IL (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Jul. 1, 2021, as Appl. No. 17/365,311.
Prior Publication US 2023/0005042 A1, Jan. 5, 2023
Int. Cl. G06Q 10/00 (2023.01); G06Q 30/0601 (2023.01); G06Q 30/0201 (2023.01); G06F 16/29 (2019.01); G01C 21/34 (2006.01); G06F 16/245 (2019.01); G06Q 40/10 (2023.01)
CPC G06Q 30/0631 (2013.01) [G01C 21/3407 (2013.01); G01C 21/3461 (2013.01); G06F 16/245 (2019.01); G06F 16/29 (2019.01); G06Q 30/0201 (2013.01); G06Q 30/0206 (2013.01); G06Q 30/0639 (2013.01); G06Q 40/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method for suggesting alternative sources of goods or services, the method comprising:
receiving information identifying purchases, by a user, of a first plurality of items, wherein the information comprises data records in a multi-dimensional space relating to the first plurality of items;
identifying, based on the information, a correlation between the purchases of the first plurality of items, wherein the correlation shows a purchasing pattern of the user within a first geographic region;
detecting a second geographic region that includes a location of the user;
querying one or more databases for descriptions of a second plurality of items;
calculating, based on the descriptions and the received information identifying purchases, measures of similarity between the first and the second pluralities of items;
identifying, using a machine learning model and based on the descriptions and the calculating, a subset of the second plurality of items that are available for purchase within the second geographic region and that have measures of similarity to the first plurality of items that exceed predetermined thresholds;
generating, based on the identifying of the correlation and the identifying of the subset, a proposed pattern for purchasing the subset within the second geographic region, wherein the proposed pattern provides one or more vendor locations within the second geographic region at which the subset is sold;
sending, based on the proposed pattern exceeding a rating based on one or more metrics relating to the proposed pattern and to a device associated with the user, instructions with the proposed pattern for purchasing the subset;
receiving purchase information relating to the proposed pattern for purchasing the subset; and
updating the machine learning model based on the received purchase information and the generated proposed pattern.