Entity Identification and/or Association Using Multiple Data Elements

• US 20110119291A1
• Filed: 09/07/2010
• Published: 05/19/2011
• Est. Priority Date: 06/14/2006
• Status: Abandoned Application

• Current Assignee: Qsent, Inc., TransUnion Teledata, LLC (TransUnion Corporation)
• Original Assignee: Qsent, Inc., TransUnion Teledata, LLC (TransUnion Corporation)
• Inventors: Rice, Scott Gregory Robert
• Application Number:
  US12/877,096
• Publication Number:
  US 20110119291A1
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/2264 Multidimensional index structures
• CPC Class Codes: G06F 16/283 Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP

Abstract

Data values from a plurality of data elements can be combined to form one or more entity identifiers to facilitate identifications of and/or associations among a plurality of data records representing one or more entities. Associated data records can represent the same entity and/or multiple entities that can be properly associated. Associations can be made among two or more unique entities and/or their respective representative data records if they correspond to substantially the same entity identifier. In one embodiment, the number, type, and/or characteristics of values for data elements used to form an entity identifier can be selected so that the entity identifier is substantially statistically unique.

Claims

1. A method for associating data records representing one or more entities, comprising:

obtaining access to a plurality of data records, each data record including a plurality of data elements;

selecting two or more data elements from the plurality of data elements, the selected data elements being selected so as to enable one or more entity identifiers to be formed from values for the selected data elements from the plurality of data records; and

associating a first data record with a second data record if a first entity identifier formed from values for the selected data elements from the first data record substantially matches a second entity identifier formed from values for the selected data elements from the second data record.

2. The method of claim 1 wherein the data elements are selected so that the formed one or more entity identifiers are substantially statistically unique.

3. The method of claim 2 wherein the data elements are selected so that the formed one or more entity identifiers have a number of possible values in excess of a number of entities represented by the plurality of data records.

4. The method of claim 3 wherein the selected data elements are selected so that the number of possible values for the formed one or more entity identifiers exceeds the number of entities by at least a predetermined factor.

5. The method of claim 4 wherein the predetermined factor is determined based at least in part on a source for the plurality of data records.

6. The method of claim 4 wherein the predetermined factor is determined at least in part according to an intended purpose for associating the first data record with the second data record.

7. The method of claim 4 wherein the predetermined factor is determined so that the associating of the first data records with the second data record achieves at least a predetermined confidence level.

8. The method of claim 1 wherein the selected data elements encompass values that are substantially randomly assigned to entities represented by the plurality of data records.

9. The method of claim 1 wherein the selected data elements encompass values that are substantially evenly distributed among entities represented by the plurality of data records.

10. The method of claim 1, further comprising defining a criterion for the one or more entity identifiers, wherein the data elements are selected so that the one or more entity identifiers are formed to satisfy the criterion.