US 11,907,057 B2
Fault processing method and system
Xiao Yin Che, Beijing (CN); Hao Tian Hui, Suzhou (CN); Jiao Jian Wang, Nanjing (CN); Ruo Gu Sheng, Beijing (CN); and Daniel Schneegaß, Beijing (CN)
Assigned to SIEMENS AKTIENGESELLSCHAFT, Munich (DE)
Appl. No. 17/769,778
Filed by Siemens Ltd., China, Beijing (CN)
PCT Filed Oct. 16, 2019, PCT No. PCT/CN2019/111520
§ 371(c)(1), (2) Date Apr. 18, 2022,
PCT Pub. No. WO2021/072687, PCT Pub. Date Apr. 22, 2021.
Prior Publication US 2022/0374300 A1, Nov. 24, 2022
Int. Cl. G06F 11/07 (2006.01)
CPC G06F 11/079 (2013.01) [G06F 11/076 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A fault processing method comprising:
receiving two historical faults similar to a target fault;
searching predefined keywords in a description of the target fault and a respective text description of each historical fault, wherein the predefined keywords are classified into N different grades, and for each system component in a grade, the grade comprises at least one keyword for describing the system component, wherein N is an integer no less than 2;
for each of the N different grades, counting a quantity of identical system components represented by the keywords in the grade in the text description of each historical fault and the keywords in the grade in the text description of the target fault, respectively; and
comparing a degree of similarity of each historical fault to the target fault according to the quantity of identical system components counted in each grade of the N different grades, wherein a historical fault relating to a larger number of high-grade identical system components has a higher degree of similarity to the target fault.