Identifying multiple devices belonging to a single user

• US 10,116,536 B2
• Filed: 11/18/2015
• Issued: 10/30/2018
• Est. Priority Date: 11/18/2015
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Palanciuc, Virgil-Artimon, Fecioru, Mihai Daniel, Costache, Catalin, Menguy, Charles
• Primary Examiner(s): Miah, Razu A
• Application Number:
  US14/944,300
• Publication Number:
  US 20170141980A1
• Time in Patent Office: 1,077 Days
• Field of Search: 709224
• CPC Class Codes: H04L 43/08 Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
• CPC Class Codes: H04L 63/104 Grouping of entities
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Techniques are disclosed that provide more accurate clustering of devices by forming clusters of devices and merging or changing clusters based on predetermined criteria. The technique starts with a large number of clusters (e.g., one for each account) and refines the clusters, for example, by merging clusters or determining which cluster a given device should be in when the device is associated with multiple clusters. One technique iteratively adjusts clusters of devices by merging clusters determined to be associated with a single user until a cluster contains all of the devices and accounts expected to be associated with a single user.

Claims

1. In an environment in which analytics data is compiled from users using devices connected to a computer network, a method for grouping devices to facilitate collecting analytics data for particular users from multiple devices, the method comprising:

excluding, from information relating to user identifications and devices on which the user identifications were received, one or more of;

(i) a particular user identification based on determining that data regarding the particular user identification is noisy, wherein determining that the particular user identification is noisy comprises determining that the particular user identification was received by more than a threshold number of devices, and

(ii) a particular device based on determining that data regarding the particular device is noisy, wherein determining that the particular device is noisy comprises determining that the particular device received more than a threshold number of different user identifications;

identifying, based on the information excluding the one or more of the particular user identification and the particular device, a plurality of clusters including a first cluster comprising one or more devices and a second cluster comprising one or more devices, wherein the first cluster is initially identified by identifying devices on which a first user account authentication was received and the second cluster is initially identified by identifying devices on which a second user account authentication was received;

identifying that a particular device is in both the first cluster and the second cluster; and

based on identifying that the particular device is in both the first cluster and the second cluster, determining, based on a predetermined criteria, to;

merge the first cluster and the second cluster to create a single merged cluster;

or

change the first cluster or the second cluster so that the particular device is only in one of the first cluster or the second cluster,

wherein analytics data from devices in the first cluster is associated with a first user and analytics data from devices in the second cluster is associated with a second user.

2. The method of claim 1, wherein the first cluster comprises devices for an unknown user.

3. The method of claim 1, wherein the first cluster is initially identified by identifying devices on which a first user identification was received and the second cluster is initially identified by identifying devices on which a second user identification was received.

4. The method of claim 1, further comprising iteratively identifying clusters having common devices and determining whether to merge the identified clusters based on the predetermined criteria, wherein clusters considered for merger and not merged in one iteration are not considered for possible merger in later iterations.

5. The method of claim 1 further comprising determining, based on the predetermined criteria, to merge the first cluster and the second cluster to create the single merged cluster, wherein the predetermined criteria use information about a user identification associated with the first cluster or the second cluster to determine whether to merge.

6. The method of claim 1 further comprising determining, based on the predetermined criteria, to merge the first cluster and the second cluster to create the single merged cluster, wherein the predetermined criteria use a minimum number of common devices in both the first cluster and the second cluster to determine whether to merge.

7. A computing system comprising:

a non-transitory computer-readable medium; and

a processor communicatively coupled to the non-transitory computer-readable medium, wherein the processor is configured for executing instructions stored in the non-transitory computer-readable medium on one or more devices, wherein, when executed by the processor, the instructions perform operations comprising;

excluding, from information relating to user identifications and devices on which the user identifications were received, one or more of;

(i) a particular user identification based on determining that data regarding the particular user identification is noisy, wherein determining that the particular user identification is noisy comprises determining that the particular user identification was received by more than a threshold number of devices, and

(ii) a particular device based on determining that data regarding the particular device is noisy, wherein determining that the particular device is noisy comprises determining that the particular device received more than a threshold number of different user identifications;

identifying, based on the information excluding the one or more of the particular user identification and the particular device, a plurality of clusters including a first cluster comprising one or more devices and a second cluster comprising one or more devices, wherein the first cluster is initially identified by identifying devices on which a first user account authentication was received and the second cluster is initially identified by identifying devices on which a second user account authentication was received;

identifying that a particular device is in both the first cluster and the second cluster; and

based on identifying that the particular device in both the first cluster and the second cluster, determining, based on predetermined criteria, to;

merge the first cluster and the second cluster to create a single merged cluster;

or

change the first cluster or the second cluster so that the particular device is only in one of the first cluster or the second cluster,

wherein analytics data from devices in the first cluster is associated with a first user and analytics data from devices in the second cluster is associated with a second user.

8. The system of claim 7, wherein the plurality of clusters represent groupings of devices and accounts expected to be associated with particular users.

9. The system of claim 7, wherein the first cluster comprises devices for an unknown user.

10. The system of claim 7, wherein the operations further comprise iteratively identifying clusters having common devices and determining whether to merge the identified clusters based on the predetermined criteria, wherein clusters considered for merger and not merged in one iteration are not considered for possible merger in later iterations.

11. The system of claim 7, wherein the operations further comprise determining, based on the predetermined criteria, to merge the first cluster and the second cluster to create the single merged cluster, wherein the predetermined criteria use information about a user account associated with the first cluster or the second cluster to determine whether to merge.

12. A non-transitory computer-readable medium embodying program code executable by a computer system, the non-transitory computer-readable medium comprising:

program code for excluding, from information relating to user identifications and devices on which the user identifications were received, one or more of;

(i) a particular user identification based on determining that data regarding the particular user identification is noisy, wherein determining that the particular user identification is noisy comprises determining that the particular user identification was received by more than a threshold number of devices, and

(ii) a particular device based on determining that data regarding the particular device is noisy, wherein determining that the particular device is noisy comprises determining that the particular device received more than a threshold number of different user identifications;

program code for identifying, based on the information excluding the one or more of the particular user identification and the particular device, a plurality of clusters including a first cluster comprising one or more devices and a second cluster comprising one or more devices, wherein the first cluster is initially identified by identifying devices on which a first user account authentication was received and the second cluster is initially identified by identifying devices on which a second user account authentication was received;

program code for identifying that a particular device is in both the first cluster and the second cluster;

program code for based on identifying that the particular device is in both the first cluster and the second cluster, determining, based on predetermined criteria, to;

merge the first cluster and the second cluster to create a single merged cluster;

or

change the first cluster or the second cluster so that the particular device is only in one of the first cluster or the second cluster,

wherein analytics data from devices in the first cluster is associated with a first user and analytics data from devices in the second cluster is associated with a second user.

13. The non-transitory computer-readable medium of claim 12, wherein the plurality of clusters represent groupings of devices and accounts expected to be associated with particular users.

14. The non-transitory computer-readable medium of claim 12, the first cluster comprises devices for an unknown user.

15. The non-transitory computer-readable medium of claim 12, further comprising program code for iteratively identifying clusters having common devices and determining whether to merge the identified clusters based on the predetermined criteria, wherein clusters considered for merger and not merged in one iteration are not considered for possible merger in later iterations.

16. The non-transitory computer-readable medium of claim 12 further comprising program code for determining, based on the predetermined criteria, to merge the first cluster and the second cluster to create the single merged cluster, wherein the predetermined criteria use information about a user account associated with the first cluster or the second cluster to determine whether to merge.