US 11,868,400 B1
Systems and methods for XBRL tag outlier detection
David Palazzo, Littleton, CO (US); Vasily Korf, Berlin (DE); Lisa Teofilo, Raleigh, NC (US); Tristan Vellinga, Arvada, CO (US); and Dorette Vermeulen, Renton, WA (US)
Assigned to WORKIVA INC., Ames, IA (US)
Filed by WORKIVA INC., Ames, IA (US)
Filed on Dec. 27, 2022, as Appl. No. 18/089,223.
Int. Cl. G06F 7/00 (2006.01); G06F 16/84 (2019.01); G06N 20/00 (2019.01)
CPC G06F 16/84 (2019.01) [G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method implemented by a computer system having one or more processors and one or more memories, comprising:
receiving a first set of XBRL data records;
generating a second set of XBRL data records based upon a subset of the first set of XBRL data records;
training a machine learning model using the first set of XBRL data records and the second set of XBRL data records;
receiving an XBRL document associated with one or more assigned XBRL tags; and
analyzing the XBRL document using the trained machine learning model to identify a set of outlier XBRL tags in the one or more assigned XBRL tags, each outlier XBRL tag in the set of identified outlier XBRL tags being an uncommon tag for corresponding filing information;
wherein the generating a second set of XBRL data records based upon a subset of the first set of XBRL data records comprises:
modifying a first XBRL tag in a first record in the subset of the first set of XBRL data records to generate a second record in the second set of XBRL data records, the first record including first filing information, the second record including a second XBRL tag and the first filing information, the second XBRL tag being the modified first XBRL tag;
wherein the second XBRL tag is an outlier tag based at least upon a taxonomy and the first filing information.