Geo-clustering for data de-identification
AssigneePrivacy Analytics Inc.
InventorsAndrew Richard Baker, Khaled El Emam
Life of this patent
Estimating the term…
Abstract
The present disclosure is related to a method of geo-clustering of data for de-identification of a dataset. The method includes generating a plurality of geoclusters based on a plurality of geocodes. The geocodes may include ZIP codes or postal codes. The method further includes identifying the geoclusters having the smallest population. The geocluster having the smallest population is iteratively merged with the nearest geocluster until a minimum population threshold is met. Once the smallest geocluster meets the minimum population threshold, the plurality of geoclusters can be used to cluster the geocodes within a dataset to be de-identified.
Claims15
A method of de-identification of data in a dataset by geo-clustering, wherein the data identifies individuals residing in a plurality of geocodes, and wherein each geocode is uniquely associated with one of many population areas, the method comprising:
- determining, by a server, a plurality of hierarchical geoclusters of the data in the dataset, wherein each determined hierarchical geocluster is based on a unique one of the plurality of geocodes;
- identifying, by the server, a first geocluster of the plurality of hierarchical geoclusters having a first smallest number of individuals, and a second geocluster of the plurality of hierarchical geoclusters having the geocode that is nearest to the geocode of the first geocluster and a second smallest number of individuals, wherein the first and second smallest number of individuals is less than a minimum population threshold;
- merging, by the server, data of the first geocluster and data of the second geocluster to obtain a merged geocluster;
- repeating the identifying and the merging to create a hierarchy of geoclusters until each geocluster in the created hierarchy of geoclusters is associated with a number of individuals greater than the minimum population threshold;
- de-identifying the data in the created hierarchy of geoclusters based on k-anonymity;
- and
- presenting the de-identified data on a computer display.
A system for de-identification of data in a dataset by geo-clustering, wherein the data identifies individuals residing in a plurality of geocodes, and wherein each geocode is uniquely associated with one of many population areas, the system comprising:
- a server configured to:
- determine a plurality of hierarchical geoclusters of the data in the dataset, wherein each determined hierarchical geocluster is based on a unique one of the plurality of geocodes;
- identify a first geocluster of the plurality of hierarchical geoclusters having a first smallest number of individuals, and a second geocluster of the plurality of hierarchical geoclusters having the geocode that is nearest b the geocode of the first geocluster and a second smallest number of individuals, wherein the first and second smallest number of individuals is less than a minimum population threshold;
- merge data of the first geocluster and data of the second geocluster to obtain a merged geocluster;
- repeat the identify and the merge to create a hierarchy of geoclusters until each geocluster in the created hierarchy of geoclusters is associated with a number of individuals greater than the minimum population threshold;
- de-identify the data in the created hierarchy of geoclusters based on k-anonymity;
- and
- present the de-identified data on a computer display.
A method of de-identification of data in a dataset by geo-clustering, wherein the data identifies individuals residing in a plurality of geocodes, and wherein each geocode is uniquely associated with one of many population areas, the method comprising:
- determining, by a server, a minimum population threshold based on risk assessment metrics;
- determining, by the server, a plurality of hierarchical geoclusters of the data in the dataset, wherein each determined hierarchical geocluster is based on a unique one of the plurality of geocodes;
- identifying, by the server, a first geocluster of the plurality of hierarchical geoclusters having a first smallest number of individuals, and a second geocluster of the plurality of hierarchical geoclusters having the geocode that is nearest to the geocode of the first geocluster and a second smallest number of individuals, wherein the first and the second smallest number of individuals is less than a minimum population threshold;
- merging, by the server, data of the first geocluster and data of the second geocluster to obtain a merged geocluster;
- repeating the identifying and the merging to create a hierarchy of geoclusters until each geocluster in the created hierarchy of geoclusters is associated with a number of individuals greater than the minimum population threshold;
- de-identifying the data in the created hierarchy of geoclusters based on k-anonymity;
- and
- presenting the de-identified data on a computer display.
Dependencies are inferred from the claim text.