CROSS-DEVICE CONSUMER IDENTIFICATION AND DEVICE TYPE DETERMINATION

• US 20170161761A1
• Filed: 12/04/2015
• Published: 06/08/2017
• Est. Priority Date: 12/04/2015
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Lipka, Nedim, Koh, Eunyee
• Granted Patent: US 11,144,939 B2
• Time in Patent Office: Days
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

An analytics server receives data characterizing consumer interactions that are observed by a cross-section of data providers, which may include, for example, website administrators, campaign managers, application developers, and the like. Such observational data includes device and login identifiers for a particular interaction, and optionally, timestamp information indicating when the interaction occurred. A statistical device graph model is generated based on this observational data. The statistical device graph model allows inferences to be drawn with respect to whether a given device is a private device, a shared device, or a public device. This, in turn, allows private devices which are “owned” by a single consumer to be identified. Depending on the type of observational data collected by the data providers, a wide range of additional insights can be drawn from the statistical device graph model, including for example, device usage patterns and confidence levels.

Claims

1. A non-transitory computer readable medium having instructions encoded thereon that, when executed by one or more processors, cause a device type determination process to be carried out, the process comprising:

receiving observational data from a plurality of data providers, wherein;

the observational data characterizes a plurality of consumer interactions with the data providers,

each of the consumer interactions is characterized by a device identifier and a login identifier, the device identifier being associated with a device that is used to provide the login identifier to one of the data providers, and

the observational data includes a plurality of device identifiers that are associated with a corresponding plurality of devices;

determining a first quantity of unique login identifiers observed by a first data provider as having been provided by a particular one of the plurality of devices, wherein the first data provider is one of the plurality of data providers from which observational data is received;

setting a Device-Type parameter for the particular device based on the first quantity;

determining a second quantity of unique login identifiers observed by a second data provider as having been provided by the particular device, wherein the second data provider is one of the plurality of data providers from which observational data is received; and

reevaluating the Device-Type parameter based on the second quantity.

2. The non-transitory computer readable medium of claim 1, wherein the Device-Type parameter is selected from a group consisting of Private, Shared, and Public.

3. The non-transitory computer readable medium of claim 1, wherein:

the observational data further includes timestamp data associated with certain of the consumer interactions; and

determining the first quantity of unique login identifiers comprises evaluating consumer interactions that occurred within a defined timeframe.

4. The non-transitory computer readable medium of claim 1, wherein setting the Device-Type parameter comprises setting the Device-Type parameter to Private when the first quantity is one.

5. The non-transitory computer readable medium of claim 1, wherein reevaluating the Device-Type parameter comprises changing the Device-Type parameter from Private to Shared or Public when the first quantity is one and the second quantity is greater than one.

6. The non-transitory computer readable medium of claim 1, wherein the device type determination process further comprises:

defining a node that corresponds to the particular device;

adding the node to a statistical device graph model that comprises a plurality of additional nodes, each of which corresponds to one of the plurality of devices; and

displaying the statistical device graph model.

7. The non-transitory computer readable medium of claim 1, wherein the device type determination process further comprises:

defining a node that corresponds to the particular device;

adding the node to a statistical device graph model that comprises a plurality of additional nodes, each of which corresponds to one of the plurality of devices; and

establishing a link between the node and one of the additional nodes, wherein the linked nodes correspond to at least two devices that were observed to have provided a common login identifier to a particular data provider.

8. The non-transitory computer readable medium of claim 1, wherein each of the consumer interactions comprises a consumer using one of the plurality of devices to provide a login identifier associated with the consumer to one of the plurality of data providers.

9. The non-transitory computer readable medium of claim 1, wherein the device type determination process further comprises:

defining a node that corresponds to the particular device; and

associating the reevaluated Device-Type parameter with the node.

10. The non-transitory computer readable medium of claim 1, wherein the device type determination process further comprises recording, in a data structure stored in a memory device, metadata characterizing (a) a node that corresponds to the particular device, and (b) the reevaluated Device-Type parameter.

11. A computer-implemented cross-device consumer identification method comprising:

receiving observational data from a plurality of data providers, wherein;

the observational data characterizes a plurality of consumer interactions with the data providers, and

each of the consumer interactions is characterized by a device identifier and a login identifier, the device identifier being associated with a device that is used to provide the login identifier to one of the data providers;

defining a plurality of nodes, each of which corresponds to a device that is associated with one or more of the plurality of consumer interactions characterized by the observational data;

setting a Device-Type parameter for a particular one of the plurality of nodes, wherein the Device-Type parameter characterizes the device corresponding to the particular node as Private, Shared, or Public, and wherein the Device-Type parameter is set based on consumer interactions with more than one of the plurality of data providers from which the observational data is received;

establishing a link between at least two of the plurality of nodes, wherein the at least two linked nodes correspond to at least two devices that were observed to have provided a login identifier that is common to a single data provider; and

recording, in a data structure stored in a memory device, metadata characterizing the plurality of nodes and the established link.

12. The computer-implemented cross-device consumer identification method of claim 11, further comprising:

determining a first quantity of unique login identifiers observed by a first data provider as having been provided by the device; and

determining a second quantity of unique login identifiers observed by a second data provider as having been provided by the device, wherein the Device-Type parameter is initially set based on the first quantity, and is reevaluated based on the second quantity.

13. The computer-implemented cross-device consumer identification method of claim 11, wherein the link is associated with an edge weight that corresponds to a quantity of data providers that observed the at least two devices providing the login identifier that is common to the single data provider.

14. The computer-implemented cross-device consumer identification method of claim 11, further comprising displaying a statistical device graph model comprising the plurality of nodes and an edge connecting the at least two nodes corresponding to the at least two devices that were observed to have provided the common login identifier to the single data provider.

15. The computer-implemented cross-device consumer identification method of claim 11, further comprising determining a distribution of login identifiers observed as having been provided by a particular device.

16. The computer-implemented cross-device consumer identification method of claim 11, wherein the device identifier comprises cookie data transmitted from the device to one of the data providers.

17. A device modeling system that comprises a memory device and a processor that is operatively coupled to the memory device, wherein the processor is configured to execute instructions stored in the memory device that, when executed cause the processor to carry out a device modeling process that comprises:

receiving observational data from a plurality of data providers, wherein;

the observational data characterizes a plurality of consumer interactions with the data providers, and

each of the consumer interactions is characterized by a device identifier and a login identifier, the device identifier being associated with a device that is used to provide the login identifier to one of the data providers;

defining a plurality of nodes, each of which corresponds to a device that is associated with one or more of the plurality of consumer interactions characterized by the observational data; and

setting a Device-Type parameter for a particular one of the plurality of nodes, wherein the Device-Type parameter characterizes the device corresponding to the particular node as Private, Shared, or Public, and wherein the Device-Type parameter is set based on consumer interactions with more than one of the plurality of data providers from which the observational data is received.

18. The device modeling system of claim 17, wherein the device modeling process further comprises:

establishing a link between at least two of the plurality of nodes, wherein the at least two linked nodes correspond to at least two devices that were observed to have provided a login identifier that is common to a single data provider; and

recording, in a data structure stored in a memory device, metadata characterizing the plurality of nodes and the established link.

19. The device modeling system of claim 17, wherein at least one of the consumer interactions comprises providing the login identifier to access an online resource provided by one of the data providers.

20. The device modeling system of claim 17, wherein the Device-Type parameter is set to Private in response to receiving observational data indicating that multiple data providers have observed the device providing only one login identifier.