Network-based targeted content delivery based on queue adjustment factors calculated using the weighted combination of overall rank, context, and covariance scores for an invitational content item

• US 8,504,419 B2
• Filed: 05/28/2010
• Issued: 08/06/2013
• Est. Priority Date: 05/28/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Priyadarshan, Eswar, Sun, Kenley, Grigorovici, Dan Marius, Chittari, Ravikiran, Vadrevu, Jayasurya, Abdala, Omar
• Primary Examiner(s): Jarrett, Scott L
• Application Number:
  US12/790,741
• Publication Number:
  US 20110295628A1
• Time in Patent Office: 1,166 Days
• Field of Search: 705/14.4
• US Class Current: 705/14.4
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods are provided for audience targeting based on a performance history of invitational content from secondary content providers, such as advertisements. In operation, responsive to request from a user for content package, a queue of available invitational content is retrieved. Thereafter, based at least on a performance history of the available invitational content in the queue, a context of the primary content, and a performance history of invitational content previously presented to other users, the queue can be at least partially reordered to provide an adjusted queue. The invitational content for the content package can then be selected based on the adjusted queue.

Claims

1. A method, comprising:

receiving a request for an internet content package designed to include instructions for presenting content from the content package in a user interface, the request associated with one of a plurality of users and one or more user contextual characteristics, wherein user contextual characteristics include at least one of channel characteristics, demographic characteristics, behavioral characteristics, or spatial-temporal characteristics;

calculating queue adjustment factors for a queue of available invitational content items, each invitational content item in the queue of available invitational content items being at least one of propaganda or inducements and each invitational content item having a queue adjustment factor specifying a value for adjusting a position of the invitational content item within the queue, wherein the calculating is based on a weighted combination of an overall rank score, a context score, and a covariance score for the invitational content item, wherein an overall rank score specifies an overall performance of the invitational content item with respect to other invitational content items previously presented to the plurality of users, a context score specifies a performance of the invitational content item in a context of the request with respect to other invitational content previously presented to the plurality of users in a context, and a covariance score specifies an interest in the invitational content item based on a correlation between a behavior of the plurality of users and the one user with respect to previously presented invitational content, and further wherein the weighted combination is based on a goal for the invitational content item;

adjusting positions of the available invitational content items within the queue of available invitational content items based on the calculated queue adjustment factors;

assembling, via a processor, the content package for the one of the plurality of users, the content package comprising at least one of the available invitational content items selected according to the adjusted queue; and

transmitting via a network the assembled content package for presentation to the requesting one of the plurality of users.

2. The method of claim 1, wherein calculating the queue adjustment factors further comprises:

calculating a plurality of covariance values based on the performance history of the invitational content previously presented to the plurality of users;

computing the covariance scores for the available invitational content based on a portion of the plurality of covariance values associated with invitational content previously presented to the one of the plurality of users.

3. The method of claim 1, wherein calculating the adjustment factors further comprises:

obtaining a performance ranking of the invitational content previously presented to the plurality of users based on the performance history; and

calculating the overall rank scores for at least a portion of the available invitational content based on the performance ranking.

4. The method of claim 1, wherein calculating the queue adjustment factors further comprises:

obtaining a performance ranking of the invitational content previously presented to the plurality of users based on the performance history for a context having the contextual characteristics associated with the request;

calculating the context rank scores for at least a portion of the available invitational content based on the performance ranking.

5. The method of claim 1, wherein the weighted combination comprises a weighted sum.

6. A non-transitory computer-readable medium having code for causing a computer to perform a method stored thereon, the method comprising:

receiving a request for an internet content package, the request associated with one of a plurality of users;

identifying user contextual characteristics for the internet content package to be delivered to the one of the plurality of users, the content package including instructions for presenting content from the content package in a user interface, and wherein user contextual characteristics include at least one of channel characteristics, demographic characteristics, behavioral characteristics, or spatial-temporal characteristics;

calculating queue adjustment factors for a queue of available invitational content items, each invitational content item in the queue of available invitational content items being at least one of propaganda or inducements and each invitational content item having a queue adjustment factor specifying a value for adjusting a position of the invitational content item within the queue, wherein the calculating is based on a weighted combination of an overall rank score, a context score, and a covariance score for the invitational content item, wherein an overall rank score specifies an overall performance of the invitational content item with respect to other invitational content items previously presented to the plurality of users, a context score specifies a performance of the invitational content item in a context of the request with respect to other invitational content previously presented to the plurality of users in a context, and a covariance score specifies an interest in the invitational content item based on a correlation between a behavior of the plurality of users and the one user with respect to previously presented invitational content, and further wherein the weighted combination is based on a goal for the invitational content item;

adjusting positions of the available invitational content items within the queue of available invitational content items associated with the contextual characteristics based on the calculated queue adjustment factors; and

assembling the content package for the one of the plurality of users, the content package comprising at least one of the available invitational content items selected according to the adjusted queue; and

transmitting via a network the assembled content package for presenting to the requesting one of the plurality of users.

7. The computer-readable medium of claim 6, wherein the step of calculating further comprises computing the overall rank score, the computing comprising:

obtaining a ranking for invitational content previously presented to the plurality of users based on a performance history for the invitational content previously presented to the plurality of users; and

calculating the overall rank score for at least a portion of the available invitational content based on the performance ranking.

8. The computer-readable medium of claim 6, wherein the step of calculating further comprises computing the context rank score, the computing comprising:

obtaining a performance ranking for the invitational content previously presented to the plurality of users in a content associated with the contextual characteristics, the ranking based on a performance history for the invitational content previously presented to the plurality of users;

calculating the context rank score for at least a portion of the available invitational content based on the ranking.

9. The computer-readable medium of claim 6, wherein the step of calculating further comprises computing the covariance score, the computing comprising:

calculating a plurality of covariance values based on a performance history of the invitational content previously presented to the plurality of users;

computing the plurality of covariance scores for the available invitational content based on a portion of the plurality of covariance values associated with invitational content previously presented to the one of the plurality of users.

10. A content delivery system, comprising:

a communications interface for receiving requests for internet content packages from one or more user terminals, a content package including instructions for presenting content from the content package in a user interface;

a storage element for storing at least one queue of available invitational content items; and

a processing element communicatively coupled to the communications interface and the storage element, wherein responsive to the communication interface receiving a new request, the processing element is configured for;

identifying a one of a plurality of users associated with the new request and one or more user contextual characteristics, wherein user contextual characteristics include at least one of channel characteristics, demographic characteristics, behavioral characteristics, or spatial-temporal characteristics,

computing queue adjustment factors for the available invitational content items, each invitational content item in the queue of available invitational content items being at least one of propaganda or inducements and each invitational content item having a queue adjustment factor specifying a value for adjusting a position of the invitational content item within the queue, wherein the computing is based on a weighted combination of overall rank scores, context scores, and covariance scores for invitational content previously presented at the user terminals, wherein an overall rank score specifies an overall performance of the invitational content item with respect to other invitational content items previously presented to the plurality of users, a context score specifies a performance of the invitational content item in a context of the request with respect to other invitational content previously presented to the plurality of users in a context, and a covariance score specifies an interest in the invitational content item based on a correlation between a behavior of the plurality of users and the one user with respect to previously presented invitational content, and further wherein the weighted combination is based on a goal for the invitational content item,

generating an adjusted queue for the identified user from the stored queue based on the queue adjustment factors by adjusting positions of the available invitational content items within the queue,

assembling a content package for the identified user, the content package comprising at least a portion of the available invitational content items selected based on the adjusted queue, and

transmitting via a network the assembled content package for presentation to the one of the plurality of users.

11. The system of claim 10, wherein the weighted combinations are weighted sums of the overall rank scores, the context rank scores, and the covariance scores.

12. The system of claim 10, wherein the processing element is further configured for:

obtaining a performance ranking of the invitational content previously presented to the plurality of users based on the performance history; and

calculating the overall rank scores for at least a portion of the available invitational content in the stored queue based on the performance ranking.

13. The system of claim 10, wherein the processing element is further configured for:

obtaining a performance ranking of the invitational content previously presented to the plurality of users based on the performance history for a context having the contextual characteristics for the content package; and

calculating the context rank scores for at least a portion of the available invitational content in the stored queue based on the performance ranking.

14. The system of claim 10, wherein the processing element is further configured for:

calculating a plurality of covariance values based on the performance history of the invitational content previously presented to the plurality of users; and

computing the plurality of covariance scores for available invitational content in the stored queue based on a portion of the plurality of covariance values associated with a plurality of invitational content previously presented to the one of the plurality of users.

15. The system of claim 10, wherein the processing element is further configured for:

prior to assembling the content package, generating an alternate pricing for the selected portion of the available invitational content.

16. The system of claim 10, wherein the processing element is further configured for:

prior to assembling the content package, identifying a first portion of the available invitational content according to the adjusted queue, identifying at least a second portion of the available invitational content at least partially related to the first portion, obtaining bids associated with the first and second portions of the available content, and identifying as a selected portion of the available invitational content for the content package at one of the first and second portions of the available content associated with a higher bid.