US 12,093,251 B2
Natural language processing system
Abhishek Parasnath Yadav, Bangalore (IN); Rahul Singhal, Bangalore (IN); Alok Yadav, Singapore (SG); and Rajesh Hanumakonda, Vijayawada (IN)
Assigned to Visa International Service Association, San Francisco, CA (US)
Filed by Visa International Service Association, San Francisco, CA (US)
Filed on Sep. 15, 2023, as Appl. No. 18/368,666.
Application 18/368,666 is a continuation of application No. 17/466,027, filed on Sep. 3, 2021, granted, now 11,803,542.
Application 17/466,027 is a continuation of application No. 16/177,869, filed on Nov. 1, 2018, granted, now 11,144,542, issued on Oct. 12, 2021.
Prior Publication US 2024/0004873 A1, Jan. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); G06F 16/242 (2019.01); G06F 16/2457 (2019.01); G06F 16/9035 (2019.01); G06F 40/30 (2020.01); G06Q 10/1093 (2023.01)
CPC G06F 16/243 (2019.01) [G06F 16/24578 (2019.01); G06F 16/9035 (2019.01); G06F 40/30 (2020.01); G06Q 10/1095 (2013.01)] 20 Claims
OG exemplary drawing
 
15. A method for determining a merchant based on a natural language query, comprising:
converting, with at least one processor, at least one word of a natural language query to a vector using at least one neural network to form a set of vectors;
determining, with the at least one processor, a vector distance from the set of vectors to each profile in a set of profiles associated with a plurality of entities, wherein each is profile associated with an entity;
communicating, with the at least one processor, entity data associated with at least one entity of the plurality of entities based on the vector distance of each of the profiles to the set of vectors; and
receiving, with the at least one processor, a selection of a first entity associated with the entity data; and
wherein the at least one word of the natural language query is at least one first word, wherein the set of vectors is a first set of vectors, wherein each profile in the set of profiles comprises data associated with a respective entity, the data associated with the respective entity comprising at least one second word, wherein each profile is associated with a second set of vectors comprising at least one second vector associated with the at least one second word, and wherein determining the vector distance from the first set of vectors to each profile in the set of profiles comprises:
determining the vector distance from the first set of vectors to each profile in the set of profiles based on a Euclidean distance from at least one first vector of the first set of vectors to the at least one second vector of the second set of vectors.