US 11,681,900 B2
Providing field extraction recommendations for display
Adam Jamison Oliner, San Francisco, CA (US); Nghi Huu Nguyen, Union City, CA (US); Jacob Leverich, San Francisco, CA (US); and Zidong Yang, Millbrae, CA (US)
Assigned to Splunk Inc., San Francisco, CA (US)
Filed by SPLUNK Inc., San Francisco, CA (US)
Filed on Jun. 15, 2020, as Appl. No. 16/901,985.
Application 16/901,985 is a continuation of application No. 15/420,754, filed on Jan. 31, 2017, granted, now 10,685,279.
Application 15/420,754 is a continuation in part of application No. 15/276,693, filed on Sep. 26, 2016, granted, now 10,909,140.
Prior Publication US 2020/0311518 A1, Oct. 1, 2020
Int. Cl. G06F 16/00 (2019.01); G06N 3/045 (2023.01); G06F 16/26 (2019.01); G06F 16/25 (2019.01)
CPC G06N 3/045 (2023.01) [G06F 16/254 (2019.01); G06F 16/26 (2019.01); G06F 2221/2151 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
causing display of a set of events, each event in the set of events comprising a time-stamped portion of raw machine data, the raw machine data produced by one or more components within an information technology environment and reflecting activity within the information technology or security environment;
receiving an indication to view field extraction recommendations; and
causing display of a set of field extraction recommendations, each field extraction recommendation comprising a set of variable text identified, via a neural network, within a corresponding event, wherein the set of variable text is identified based on using a probability of a next character, given a previous set of characters in the corresponding event, to identify when the set of variable text begins or ends within the corresponding event.