METHODS AND APPARATUS FOR IDENTIFYING UNIQUE USERS FOR ON-LINE ADVERTISING

• US 20160117736A1
• Filed: 10/27/2014
• Published: 04/28/2016
• Est. Priority Date: 10/27/2014
• Status: Active Grant

• Current Assignee: Amobee, Inc. (Nexxen International Ltd.)
• Original Assignee: Turn (Nexxen International Ltd.)
• Inventors: Dasdan, Ali, Rangwala, Sumit, Kolay, Santanu Kumar
• Granted Patent: US 10,134,058 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/306 User profiles

Abstract

Methods and apparatus for finding detecting unique on-line users for advertisement or content targeting are disclosed. A bid request with initial fingerprint context data for a user and for content that is requested by such user is received at a bid management system, and the bid request is received with or without a user identifier. At the bid management system, an optimum bid for the bid request is determined based on the initial fingerprint context data for the user and the content. The optimum bid with a reference to an advertisement and a script for obtaining additional fingerprint context data from a device of the user is sent from the bid management system. The additional fingerprint context data is received and a unique user identifier is assigned in association with a combination of the initial and additional fingerprint context data.

Claims

1. A method for detecting unique users for advertisement or content targeting, the method comprising:

at a bid management system, receiving a bid request with initial fingerprint context data for a user and for content that is requested by such user, wherein the bid request is received with or without a user identifier;

at the bid management system, determining an optimum bid for the bid request based on the initial fingerprint context data for the user and the content;

from the bid management system, sending the optimum bid with a reference to an advertisement and a script for obtaining additional fingerprint context data from a device of the user; and

at the bid management system or a unique user detection system associated with such bid management system, receiving the additional fingerprint context data and assigning a unique user identifier in association with a combination of the initial and additional fingerprint context data.

2. The method of claim 1, wherein the script for obtaining additional fingerprint context data is written in any supported programming language and is downloaded into the user'"'"'s device in response to receipt of a content request from the user'"'"'s device.

3. The method of claim 1, wherein the initial fingerprint context data includes an Internet Protocol address and application identifier.

4. The method of claim 3, wherein the additional fingerprint context data includes one or more of the following:

browser user agent, device parameters, a list of all applications installed on a device, a list of browser plugins that are installed in an application browser of the user, a list of system fonts that are installed, a system time zone (TZ), a system clock drift, and one or more network parameters.

5. The method of claim 4, wherein the initial fingerprint context data further comprises geographical location data.

6. The method of claim 1, further comprising:

for each of a plurality of first users, repeating the operations for receiving a bid request, determining and sending an optimum bid, receiving additional fingerprint context data and assigning a unique user identifier;

at one or more processors, obtaining a plurality of user data sets associated with a plurality of unique user identifiers, including the unique user identifiers assigned for the first users, wherein each user data set of each unique user identifier specifies one or more user attributes, including a combination of initial and additional fingerprint context data, and on-line user events that have occurred for such user identifier;

at the one or more processors and for each attribute, determining a correlation to a success metric value for a particular type of event or attribute that has occurred for a plurality of user identifiers that are each associated with such attribute; and

at the one or more processors, clustering the plurality of user identifiers and associated data sets into a plurality of user groups that each has similar data sets by weighting based on the attributes'"'"' relative correlation to such success metric.

7. The method of claim 6, wherein the success metric value for each attribute is a count of click events for user identifiers that are associated with such attribute.

8. The method of claim 6, wherein the success metric value for each attribute is a count of conversion events for user identifiers that are associated with such attribute.

9. The method of claim 6, further comprising stopping the clustering based on an evaluation metric of the clustering with respect to a golden set of the user identifiers that are known to belong to similar users.

10. The method of claim 1, wherein the bid request is received without a user identifier.

11. A system for detecting unique on-line users for advertisement or content targeting, the system comprising at least a processor and a memory, wherein the at one processor and memory are configured to perform the following operations:

receiving a bid request with initial fingerprint context data for a user and for content that is requested by such user, wherein the bid request is received without a user identifier;

determining an optimum bid for the bid request based on the initial fingerprint context data for the user and the content;

sending the optimum bid with a reference to an advertisement and a script for obtaining additional fingerprint context data from a device of the user; and

receiving the additional fingerprint context data and assigning a unique user identifier in association with a combination of the initial and additional fingerprint context data.

12. The system of claim 11, wherein the script for obtaining additional fingerprint context data is written in any supported programming language and is downloaded into the user'"'"'s device in response to receipt of a content request from the user'"'"'s device.

13. The system of claim 11, wherein the initial fingerprint context data includes an Internet Protocol address and application identifier.

14. The system of claim 13, wherein the additional fingerprint context data includes one or more of the following:

browser user agent, device parameters, a list of all applications installed on a device, a list of browser plugins that are installed in an application browser of the user, a list of system fonts that are installed, a system time zone (TZ), a system clock drift, and one or more network parameters.

15. The system of claim 14, wherein the initial fingerprint context data further comprises geographical location data.

16. The system of claim 11, wherein the at least one processor and memory are further configured for causing the following operations:

for each of a plurality of first users, repeating the operations for receiving a bid request, determining and sending an optimum bid, receiving additional fingerprint context data and assigning a unique user identifier;

obtaining a plurality of user data sets associated with a plurality of unique user identifiers, including the unique user identifiers assigned for the first users, wherein each user data set of each unique user identifier specifies one or more user attributes, including a combination of initial and additional fingerprint context data, and on-line user events that have occurred for such user identifier;

for each attribute, determining a correlation to a success metric value for a particular type of event or attribute that has occurred for a plurality of user identifiers that are each associated with such attribute; and

clustering the plurality of user identifiers and associated data sets into a plurality of user groups that each has similar data sets by weighting based on the attributes'"'"' relative correlation to such success metric.

17. The system of claim 16, wherein the success metric value for each attribute is a count of click events for user identifiers that are associated with such attribute.

18. The system of claim 16, wherein the success metric value for each attribute is a count of conversion events for user identifiers that are associated with such attribute.

19. The system of claim 16, further comprising stopping the clustering based on an evaluation metric of the clustering with respect to a golden set of the user identifiers that are known to belong to similar users.

20. At least one non-transitory computer readable storage medium having computer program instructions stored thereon that are arranged to perform the following operations:

at a bid management system, receiving a bid request with initial fingerprint context data for a user and for content that is requested by such user, wherein the bid request is received without a user identifier;

at the bid management system, determining an optimum bid for the bid request based on the initial fingerprint context data for the user and the content;

from the bid management system, sending the optimum bid with a reference to an advertisement and a script for obtaining additional fingerprint context data from a device of the user; and

at the bid management system or a unique user detection system associated with such bid management system, receiving the additional fingerprint context data and assigning a unique user identifier in association with a combination of the initial and additional fingerprint context data.

21. The at least one non-transitory computer readable storage medium of claim 20, wherein the script for obtaining additional fingerprint context data is written in any supported programming language and is downloaded into the user'"'"'s device in response to receipt of a content request from the user'"'"'s device.

22. The at least one non-transitory computer readable storage medium of claim 21, wherein the initial fingerprint context data includes an Internet Protocol address and application identifier.

23. The at least one non-transitory computer readable storage medium of claim 22, wherein the additional fingerprint context data includes one or more of the following:

browser user agent, device parameters, a list of all applications installed on a device, a list of browser plugins that are installed in an application browser of the user, a list of system fonts that are installed, a system time zone (TZ), a system clock drift, and one or more network parameters.

24. The at least one non-transitory computer readable storage medium of claim 23, wherein the initial fingerprint context data further comprises geographical location data.