Selection and delivery of invitational content based on prediction of user interest

• US 9,183,247 B2
• Filed: 07/10/2013
• Issued: 11/10/2015
• Est. Priority Date: 08/31/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Priyadarshan, Eswar, Sun, Kenley, Grigorovici, Dan Marius, Vadrevu, Jayasurya, Abdala, Omar
• Primary Examiner(s): ALAM, SHAHID AL
• Application Number:
  US13/938,880
• Publication Number:
  US 20130304748A1
• Time in Patent Office: 853 Days
• Field of Search: 707/721, 707/722, 707/770, 707/801, 707/727, 707/740, 707/748
• US Class Current: 1/1
• CPC Class Codes: G06F 16/1805 Append-only file systems, e.g. using logs or journals to store data
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods are provided for selecting invitational content for users based on their short-term and their long-term features. In operation, responsive to a request from a user terminal for a content package a journal of events associated with a user. Thereafter, short-term and long-term features in the journal are identified and tagged with pre-defined tags indicating a type of content associated with the patterns. The tags are then used to select invitational content by selecting content based on tags for the identified short-term features associated with a threshold level of activity or tags for the identified long-term features.

Claims

1. A computer-implemented method, comprising:

identifying, via a processor, events completed via a device associated with a user;

based on the events, identifying, via the processor, a sequence of events completed by the device;

comparing, via the processor, the sequence of events completed at the device with predefined sequences of events which result in respective conversion actions to identify partial sequences of events from the predefined sequences of events corresponding to at least a portion of the sequence of events completed at the device;

computing, via the processor, scores for the partial sequences of events, each of the scores indicating a proximity of a respective one of the partial sequences of events to a completion of a conversion action from the respective conversion actions; and

selecting, via the processor, invitational content to deliver to the device based on a highest score from the scores for the partial sequences of events.

2. The method of claim 1, wherein the invitational content is selected from a pre-defined queue of invitational content according to a set of default rules when the highest score from the scores for the partial sequences of events fails to meet a threshold criteria, and wherein the predefined sequence of events leading to the conversion is determined by evaluating at least one of previous event or previous conversions.

3. The method of claim 1, wherein computing the scores for the partial sequences of events is based on a frequency or a duration of each of the partial sequences of events.

4. The method of claim 1, wherein computing the scores for the partial sequences of events for each of the partial sequences of events comprises:

determining a temporal relationship between the events in the predefined sequence of events;

assigning event weights to the events based at least on the temporal relationship for the sequence of events; and

calculating the score based on the event weights.

5. The method of claim 4, wherein weights for each of the sequence of events are associated with short-term conduct.

6. The method of claim 1, wherein the identifying sequences of events is based on a pre-defined time window.

7. The method of claim 1, further comprising selecting invitational content to deliver to the device based on a lowest score from the scores for the partial sequences of events.

8. A non-transitory computer-readable medium having stored thereon instructions which, when executed by a processor, cause the processor to perform operations comprising:

obtaining a corpus of data identifying one or more events, the events in the corpus comprising at least one of events at a plurality of user terminals associated with a user, events during a plurality of sessions associated with the user, or events associated with a plurality of content packages delivered to the user at one or more of the plurality of user terminals;

based on the corpus of data, identifying events completed by a user terminal;

comparing the sequence of events completed at the device with at least one predefined sequence of events that lead to a conversion action to identify a partial sequences of events comprising a portion of the at least one predefined sequence of events that is also included in the sequence of events completed at the user terminal;

computing scores for the partial sequences of events, each of the scores indicating a proximity of a respective one of the partial sequences of events to a completion of conversion action from the respective conversion actions; and

selecting invitational content to deliver to the user terminal based on a highest score from the scores for the partial sequences of events.

9. The computer-readable medium of claim 8, wherein the invitational content is selected from a pre-defined queue of invitational content when the highest score from the scores for the partial sequences of events fails to meet a threshold criteria.

10. The computer-readable medium of claim 8, wherein the scores for the partial sequences of events are computed based on a frequency and a duration of the partial sequences of events.

11. The computer-readable medium of claim 8, wherein computing the scores for the partial sequences of events further comprises:

determining a temporal relationship between events in the sequence of events;

assigning event weights to the events based at least on the temporal relationship for the sequence of events; and

calculating the score based on the event weights.

12. The computer-readable medium of claim 8, wherein identifying the sequence of events is based on a pre-defined time window.

13. The computer-readable medium of claim 8, storing additional instructions which, when executed by the processor, result in an operation comprising selecting invitational content to deliver to the user terminal based on a lowest score from the scores for the partial sequences of events.

14. A content delivery system, comprising:

a processor; and

a computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform operations comprising;

identifying events completed via a device associated with a user;

based on the events, identifying a sequence of events completed by the device,

comparing the sequence of events completed at the device with predefined sequences of events which result in respective conversion actions to identify partial sequences of events from the predefined sequences of events corresponding to at least a portion of the sequence of events completed at the device,

computing scores for the partial sequences of events, each of the scores indicating a proximity of a respective one of the partial sequences of events to a completion of a conversion action from the respective conversion actions, and

selecting invitational content to deliver to the user terminal based on the a highest score from the scores for the partial sequences of events.

15. The content delivery system of claim 14, wherein selecting the invitational content is from a pre-defined queue of invitational content when the highest score from the scores for the partial sequences of events fails to meet a threshold criteria.

16. The content delivery system of claim 14, wherein computing the scores for the partial sequences of events is based on a frequency and a duration of each of the partial sequences of events.

17. The content delivery system of claim 14, wherein computing the scores for the partial sequences of events comprises:

determining a temporal relationship between

assigning weights to the events of based at least on the temporal relationship; and

calculating the intent score based on the weights.

18. The content delivery system of claim 14, wherein the identifying of the sequence of events is based on a pre-defined time window.

19. The content delivery system of claim 14, the computer-readable storage medium storing additional instructions which, when executed by the processor, result in an operation comprising selecting invitational content to deliver to the user terminal based on a lowest score from the scores for the partial sequences of events.

20. The content delivery system of claim 14, wherein the events comprise at least one of events at a plurality of user terminals associated with the user, events during a plurality of sessions associated with the user, or events associated with a plurality of content packages delivered to the user at one or more of the plurality of user terminals.