US 12,001,516 B2
Method and assistance system for parameterizing an anomaly detection method
Johannes Kehrer, Munich (DE); Christoph Paulitsch, Karlsruhe (DE); and Stefan Hagen Weber, Munich (DE)
Assigned to SIEMENS AKTIENGESELLSCHAFT, Munich (DE)
Appl. No. 17/277,067
Filed by Siemens Aktiengesellschaft, Munich (DE)
PCT Filed Aug. 30, 2019, PCT No. PCT/EP2019/073176
§ 371(c)(1), (2) Date Mar. 17, 2021,
PCT Pub. No. WO2020/057937, PCT Pub. Date Mar. 26, 2020.
Claims priority of application No. 18195130 (EP), filed on Sep. 18, 2018.
Prior Publication US 2022/0051051 A1, Feb. 17, 2022
Int. Cl. G06K 9/62 (2022.01); G06F 18/213 (2023.01); G06F 18/23 (2023.01); G06F 30/20 (2020.01); G06T 7/00 (2017.01)
CPC G06F 18/23 (2023.01) [G06F 18/213 (2023.01); G06F 30/20 (2020.01); G06T 7/0004 (2013.01); G06T 2200/24 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/30108 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for parameterizing an anomaly detection method which carries out a density-based cluster method on a basis of a multiplicity of sensor data points, the method comprising:
a) mapping, by at least one processor, each sensor data point in a data space into a pixel data point in a pixel space spanned by a multiplicity of pixel data points;
b) simulating, by the at least one processor, at least one operation of the density-based cluster method in the data space by means of at least one pixel operation in the pixel space;
c) receiving, by the at least one processor, at least one parameter value for each parameter of the density-based cluster method;
d) applying, by the at least one processor, the at least one pixel operation to the pixel data points according to the received parameter values;
e) outputting, by the at least one processor, a cluster result in visual form in the pixel space; and
f) providing, by the at least one processor, the received parameter values for the anomaly detection method.