US 11,899,701 B2
Identifying false positives between matched words
Rushik Upadhyay, San Jose, CA (US); Dhamodharan Lakshmipathy, San Jose, CA (US); Nandhini Ramesh, San Jose, CA (US); and Aditya Kaulagi, San Francisco, CA (US)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PAYPAL, INC., San Jose, CA (US)
Filed on Jun. 22, 2021, as Appl. No. 17/353,939.
Application 17/353,939 is a continuation of application No. 16/236,550, filed on Dec. 30, 2018, granted, now 11,042,580, issued on Jun. 22, 2021.
Prior Publication US 2021/0311977 A1, Oct. 7, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/33 (2019.01); G06F 16/335 (2019.01); G06F 40/295 (2020.01)
CPC G06F 16/334 (2019.01) [G06F 16/335 (2019.01); G06F 40/295 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more hardware processors; and
a non-transitory memory storing computer-executable instructions, that in response to execution by the one or more hardware processors, causes the system to perform operations comprising:
in response to receiving text data that corresponds to an Internet search, determining at least a portion of the text data is included in a first set of keywords previously identified by the system;
calculating a first false positive score associated with the text data, wherein the first false positive score is calculated at least in part by comparing the text data to a plurality of text strings that contain one or more keywords from the first set of keywords, and wherein the plurality of text strings were previously determined to be false positive;
determining a set of trusted keywords using at least a frequency score, wherein the frequency score is determined based at least in part on a frequency of each word of the plurality of text strings appearing in the plurality of text strings that were previously determined to be false positive;
calculating a second false positive score associated with the text data, wherein the second false positive score is calculated based in part on a number of times a word from the set of trusted keywords is included in the text data;
identifying, based on the first false positive score and the second false positive score, the text data as a match to a result type; and
determining, based on the identifying, whether one or more webpages containing the text data should be returned as a result of the Internet search.