| CPC G06F 21/6254 (2013.01) [G06F 16/2228 (2019.01); G06F 16/2379 (2019.01); G06F 16/2471 (2019.01); G06F 16/285 (2019.01)] | 20 Claims |

|
1. A method of anonymising an input data item using a processing device, the method comprising:
obtaining a set of data points, wherein each data point is defined by a numeric value, and wherein the set of data points defines a representation of the input data item;
assigning an index value to each of the plurality of data points, the index value representing a position of the data point in the representation of the input data item;
clustering the data points into one or more clusters;
determining a deviation of each data point from a reference data point of its respective cluster;
generating a unique identification for each data point;
generating one or more entries for a translation table mapping the unique identification for each data point to the corresponding index value;
generating one or more entries for a deviation table mapping the unique identification for each data point to the corresponding deviation;
generating one or more entries for a cluster table mapping the unique identification for each data point to its corresponding cluster;
generating one or more entries for a reference table comprising the reference data points of each of the one or more clusters, the reference table mapping the reference data points to the corresponding unique identification; and
storing the one or more entries for the translation, deviation, cluster and reference tables.
|