US 11,914,626 B2
Machine learning approach to cross-language translation and search
Rushik Upadhyay, San Jose, CA (US); Dhamodharan Lakshmipathy, San Jose, CA (US); Nandhini Ramesh, San Jose, CA (US); and Aditya Kaulagi, Singapore (SG)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PAYPAL, INC., San Jose, CA (US)
Filed on Mar. 22, 2021, as Appl. No. 17/208,876.
Application 17/208,876 is a continuation of application No. 16/232,796, filed on Dec. 26, 2018, granted, now 10,956,466.
Prior Publication US 2021/0240751 A1, Aug. 5, 2021
Int. Cl. G06F 40/53 (2020.01); G06F 16/33 (2019.01); G06F 16/31 (2019.01); G06N 20/00 (2019.01); G06F 40/284 (2020.01)
CPC G06F 16/3337 (2019.01) [G06F 16/313 (2019.01); G06F 40/284 (2020.01); G06F 40/53 (2020.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more machine-readable storage media having instructions stored thereon that, in response to being executed by the one or more processors, cause the system to perform operations comprising:
in response to receiving an input symbol, retrieving an index file from a server, wherein the index file includes a plurality of word tokens;
determining, by a preprocessing module, a frequency of each word token included in the index file;
calculating, by the preprocessing module, respective frequency scores based on the determining the frequency;
identifying, by the preprocessing module, important word tokens based in part of the frequency scores, wherein the identifying the important word tokens includes determining a difference between the frequency scores of each word token and a frequency token threshold; and
determining a match between the received input symbol and the plurality of word tokens, wherein the determining the match includes using an elimination criteria and the important word tokens.