US 12,321,992 B2
Systems and methods for rapid natural language based message categorization
Sameer Khanna, Sunnyvale, CA (US)
Assigned to Fortinet, Inc., Sunnyvale, CA (US)
Filed by Fortinet, Inc., Sunnyvale, CA (US)
Filed on Mar. 18, 2024, as Appl. No. 18/608,552.
Application 18/608,552 is a continuation of application No. 17/570,210, filed on Jan. 6, 2022, granted, now 11,971,983.
Claims priority of provisional application 63/235,887, filed on Aug. 23, 2021.
Prior Publication US 2024/0256654 A1, Aug. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/08 (2012.01); G01V 1/01 (2024.01); G01W 1/10 (2006.01); G06F 18/24 (2023.01); G06F 21/31 (2013.01); G06F 21/55 (2013.01); G06F 21/62 (2013.01); G06F 40/242 (2020.01); G06F 40/279 (2020.01); G06F 40/284 (2020.01); G06N 7/01 (2023.01); G06Q 20/38 (2012.01); G06Q 40/02 (2023.01); G06V 10/56 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 40/20 (2022.01); H04L 9/40 (2022.01); H04L 43/045 (2022.01); G06F 40/205 (2020.01); G06Q 50/26 (2012.01)
CPC G06Q 40/08 (2013.01) [G01V 1/01 (2024.01); G01W 1/10 (2013.01); G06F 18/24 (2023.01); G06F 21/316 (2013.01); G06F 21/552 (2013.01); G06F 21/6218 (2013.01); G06F 40/242 (2020.01); G06F 40/279 (2020.01); G06F 40/284 (2020.01); G06N 7/01 (2023.01); G06Q 20/389 (2013.01); G06Q 40/02 (2013.01); G06V 10/56 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 40/20 (2022.01); H04L 43/045 (2013.01); H04L 63/1416 (2013.01); H04L 63/1425 (2013.01); G06F 40/205 (2020.01); G06Q 50/26 (2013.01)] 19 Claims
OG exemplary drawing
 
10. A system comprising:
a processing resource;
a non-transitory computer-readable medium, coupled to the processing resource, having stored therein instructions that when executed by the processing resource cause the processing resource to:
receive, by a processing resource, a message including text;
determine, by the processing resource, a set of exclusion values for the message, the set of exclusion values including an exclusion value for each unique word in the message based at least in part on a frequency of the unique word in the message and a frequency of the unique word in a dictionary;
form, by the processing resource, a vector including a subset of the set of exclusion values corresponding to a vector definition for a topic;
compare, by the processing resource, at least one of a first dimension value of the vector with a first extreme for the topic and a second dimension value of the vector with a second extreme for the topic; and
determine, by the processing resource, that the message matches the topic in response to comparing the first and second extremes.