| CPC G06F 16/29 (2019.01) [G06F 16/24578 (2019.01); G06F 16/285 (2019.01)] | 20 Claims |
|
1. A computer-implemented method, comprising:
in response to receiving data from a plurality of predefined functional areas in a particular geographical area in which a plurality of physical objects are located, wrangling the data to correlate the data from the functional areas with respective ones of the physical objects, wherein the data are collected from the plurality of predefined functional areas in the particular geographical area in which the plurality of physical objects are located;
transforming the wrangled data corresponding to each of the physical objects into features, each feature corresponding to a respective one of the functional areas;
for each of the physical objects, processing the features according to predefined rules for generating a rank for each of the functional areas;
computing dynamic weights for at least some of the features to account for data drift by comparing historical data with latest data;
transforming the ranks and the dynamic weights into a vandalism score for each of the physical objects, wherein a clustering analysis is performed on the rank and the dynamic weights to determine a number of clusters of the physical objects having a similar impact from vandalism; and
outputting at least some of the vandalism scores and/or derivatives thereof.
|