US 11,886,597 B2
Detection of common patterns in user generated content with applications in fraud detection
Alexandros Vlissidis, Sunnyvale, CA (US); Nicola Corradi, San Francisco, CA (US); Fang Yu, Sunnyvale, CA (US); and Olivia Wang, Fremont, CA (US)
Assigned to Data Visor, Inc., Mountain View, CA (US)
Filed by DataVisor, Inc., Mountain View, CA (US)
Filed on Oct. 19, 2020, as Appl. No. 17/074,463.
Claims priority of provisional application 62/916,743, filed on Oct. 17, 2019.
Prior Publication US 2021/0117552 A1, Apr. 22, 2021
Int. Cl. G06F 21/00 (2013.01); G06F 21/57 (2013.01); G06F 18/23 (2023.01); G06F 18/211 (2023.01); G06F 18/213 (2023.01); G06F 18/20 (2023.01); G06F 18/2415 (2023.01)
CPC G06F 21/577 (2013.01) [G06F 18/211 (2023.01); G06F 18/213 (2023.01); G06F 18/23 (2023.01); G06F 18/2415 (2023.01); G06F 18/285 (2023.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
identifying one or more potential clusters of malicious accounts;
for each cluster, processing a collection of content associated with each account of the cluster, the processing comprising applying a plurality of models in series to determine whether the collection of content indicates a common pattern, the applying the plurality of models in series comprising:
applying a plurality of instances of a single user model to respective portions of the collection of content,
applying a multi-users model to the output of the plurality of instances of the single user model, and
applying a group model to the output of the multi-users model; and
based on the respective determinations, classifying the accounts of each cluster as either ordinary or suspicious.