Systems and methods for performing data analytics on sensitive data in remote network environments without exposing content of the sensitive data
AssigneeCitibank, N.A.
InventorsLeena Mary Francis, Vaibhav Kumar, Ashutosh Pandey
Life of this patent
Estimating the term…
Abstract
Systems and methods for performing data analytics on sensitive data, such as deduplication are disclosed herein. A first request to perform a first data analytics operation for a set of sensitive data instances may be received. A first set of image representations for the set of sensitive data instances may be retrieved. A first sensitive data instance and a second sensitive data instance may be clustered into a first cluster. The first data analytics operation may be performed on the first cluster.
Claims20
A system for performing data analytics on sensitive data in remote network environments without exposing content of the sensitive data, the system comprising:
- one or more processors;
- and
- a non-transitory, computer-readable medium storing instructions that, when executed by the one or more processors, cause operations comprising:
- receiving a first request to perform a first data analytics operation for a set of sensitive data instances, wherein the first data analytics operation enables deduplication of data instances;
- retrieving a first set of image representations for the set of sensitive data instances, wherein the first set of image representations comprises:
- a first image representation for a first sensitive data instance for the set of sensitive data instances, wherein the first image representation is based on a first mapping template, wherein the first mapping template maps a first set of alphanumeric characters in the first sensitive data instance to a first set of color coding, and wherein the first set of color coding enables representation of the first sensitive data instance using color gradient, color intensity and hue;
- and
- a second image representation for a second sensitive data instance for the set of sensitive data instances, wherein the second image representation is based on the first mapping template;
- clustering the first sensitive data instance and the second sensitive data instance into a first cluster based on similarities between the first image representation and the second image representation;
- retrieving a first instance identifier for the first sensitive data instance and a second instance identifier for the second sensitive data instance;
- and
- labeling the first instance identifier and the second instance identifier as corresponding to a duplicate.
A method for performing data analytics on sensitive data in remote network environments without exposing content of the sensitive data, the method comprising:
- receiving a first request to perform a first data analytics operation for a set of sensitive data instances;
- retrieving a first set of image representations for the set of sensitive data instances, wherein the first set of image representations comprises:
- a first image representation for a first sensitive data instance for the set of sensitive data instances, wherein the first image representation is based on a first mapping template, and wherein the first mapping template maps a first set of alphanumeric characters in the first sensitive data instance to a first set of color coding;
- and
- a second image representation for a second sensitive data instance for the set of sensitive data instances, wherein the second image representation is based on the first mapping template, wherein the first mapping template maps a second set of alphanumeric characters in the second sensitive data instance to a second set of color coding;
- clustering the first sensitive data instance and the second sensitive data instance into a first cluster based on similarities between the first image representation and the second image representation;
- and
- performing the first data analytics operation on the first cluster.
A non-transitory, computer-readable medium storing instructions that, when executed by one or more processors, cause operations comprising:
- receiving a first request to perform a first data analytics operation for a set of sensitive data instances;
- retrieving a first set of image representations for the set of sensitive data instances, wherein the first set of image representations comprises:
- a first image representation for a first sensitive data instance for the set of sensitive data instances, wherein the first image representation is based on a first mapping template, wherein the first mapping template maps a first feature in the first sensitive data instance to a first set of color coding;
- and
- a second image representation for a second sensitive data instance for the set of sensitive data instances, wherein the second image representation is based on the first mapping template, wherein the first mapping template maps a second feature in the second sensitive data instance to a second set of color coding;
- clustering the first sensitive data instance and the second sensitive data instance into a first cluster based on similarities between the first image representation and the second image representation;
- and
- performing the first data analytics operation on the first cluster.
Dependencies are inferred from the claim text.