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

• US 8,640,032 B2
• Filed: 08/31/2010
• Issued: 01/28/2014
• 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): LEGGETT, ANDREA C.
• Application Number:
  US12/873,235
• Publication Number:
  US 20120054627A1
• Time in Patent Office: 1,246 Days
• Field of Search: 715/736, 715/738
• US Class Current: 715/736
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

Systems and methods are provided for delivering invitational content based on a prediction of the intent of a user. In particular, partial action sequences are identified in a journal of events associated with the user. Thereafter, the partial sequences are analyzed and scored based on their degree of proximity to completion. Based on this scoring, a queue of invitational content can then be generated, where the scoring can be used to select and order the invitational content for the user. In some configurations, the information in the journal can be used to determine future time intervals at which sequences will be completed by the user. Consequently, a queue can be adjusted to provide delivery of appropriate invitational content at these future time intervals.

Claims

1. A computer-implemented method, comprising:

obtaining a journal of user events associated with a request from a user terminal for a content package, wherein the user terminal is associated with a user;

detecting sequences of user events in the journal, wherein each of the sequences makes up a respective portion of a predefined sequence of user events corresponding to a respective response mode;

computing an intent score for each respective response mode based on the respective portion of the predefined sequence of user events made up by each of the sequences detected, the intent score indicating a proximity of the respective portion of the predefined sequence of user events to a completion of the predefined sequence of user events that corresponds to the respective response mode; and

selecting invitational content for the content package based on the intent score of each respective response mode, wherein the invitational content selected is associated with the respective response mode having a highest intent score.

2. The method of claim 1, wherein the step of selecting further comprises assembling a queue of invitational content based on the intent score of each respective response mode, wherein the invitational content associated with the respective response mode having the highest intent score is positioned at a top of the queue.

3. The method of claim 1, wherein the step of selecting further comprises choosing invitational content associated with the respective response mode having a respective intent score meeting a threshold criteria.

4. The method of claim 1, wherein the step of selecting further comprises selecting invitational content associated with a pre-defined number of response modes having highest intent scores.

5. The method of claim 1, wherein the step of computing further comprises calculating the intent score for each respective response mode based on a temporal relationship among the user events associated with a respective sequence from the sequences of user events.

6. The method of claim 1, wherein the step of detecting further comprises:

for each of the sequences of user events, identifying user events in the journal and determining a presence, in the journal, of the respective portion of the predefined sequence of user events if the user events identified in the journal have an equivalent temporal relationship as the respective portion of the predefined sequence of user events.

7. A system comprising:

a processor; and

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

receiving a request for a content package from a user terminal associated with a user;

storing a journal of user events associated with the user terminal and a plurality of pre-defined response sequences associated with one or more response modes;

detecting groups of user events in the journal, wherein each group makes up a respective portion of a predefined sequence of user events associated with a respective response mode;

computing an intent score for each respective response mode based on the respective portion of the predefined sequence of user events made up by each group from the groups detected, the intent score indicating a proximity of the respective portion of the predefined sequence of user events to a completion of the predefined sequence of user events associated with the respective response mode; and

selecting invitational content for the content package based on the intent score for each respective response mode, wherein the invitational content selected is associated with a response mode having a highest intent score.

8. The system of claim 7, wherein the invitational content is selected from a queue of invitational content assembled based on the intent score for each respective response mode, wherein the invitational content associated with the response mode having the highest intent score is positioned at a top of the queue.

9. The system of claim 7, wherein the selecting step further comprises choosing the invitational content associated with the respective response mode having an intent score meeting a threshold criteria.

10. The system of claim 7, wherein the selecting step further comprises choosing the invitational content associated with a pre-defined number of response modes having highest intent scores.

11. The system of claim 7, wherein the computing step further comprises by calculating the intent score for each respective response mode based on a temporal relationship among the user events associated with a group from the group of user events.

12. The system of claim 7, wherein the detecting step further comprises detecting the groups of user events based on identifying the user events from the respective portion of the predefined sequence of user events associated with the respective response mode and determining a presence, in the journal, of the respective portion of the predefined sequence of user events if the user events identified in the journal have an equivalent temporal relationship as the user events in the respective portion of the predefined sequence of user events associated with the respective response mode.

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

obtaining a journal of user events associated with a request of a content package from a user terminal associated with a user;

detecting sequences of user events in the journal, wherein each sequence makes up a respective portion of a predefined sequence of user events associated with a respective response mode;

computing an intent score for each respective response mode based on the respective portion of the predefined sequence of user events made up by each sequence from the sequences of user events detected, the intent score indicating a proximity of the respective portion of the predefined sequence of user events to a completion of the predefined sequence of user events associated with the respective response mode; and

organizing a queue of invitational content for the user based on the intent score for each respective response mode, wherein the invitational content in the queue comprises invitational content associated with the sequences of user events in the journal, wherein a position of the invitational content associated with the sequences of user events in the journal in the queue is based on the intent score for each respective response mode.

14. The computer-readable medium of claim 13, wherein the step of organizing further comprises:

projecting at least one future time interval at which completion of selected ones of the sequences of user events detected will occur based on the journal; and

configuring the queue to deliver invitational content associated with the respective response mode corresponding to the selected ones of the sequences of user events at the future time interval.

15. The computer-readable medium of claim 13, wherein the step of organizing further comprises positioning the invitational content associated with the sequences of user events at a top of the queue.

16. The computer-readable medium of claim 13, wherein the step of organizing further comprises choosing invitational content associated with the respective response mode having an intent score meeting a threshold criteria.

17. The computer-readable medium of claim 13, wherein the step of organizing further comprises selecting invitational content associated with a pre-defined number of response modes having highest intent scores.

18. The computer-readable medium of claim 13, wherein the step of computing further comprises calculating the intent score for each respective response mode based on a temporal relationship among user events associated with a respective sequence of user events.

19. The computer-readable medium of claim 13, wherein the step of detecting further comprises:

for each respective response mode, identifying the user events from the sequences of user events detected in the journal and determining a presence, in the journal, of a sequence of user events that makes up the respective portion of predefined sequence of user events associated with the respective response mode if the user events in the journal have an equivalent temporal relationship as the user events in the sequence of user events.

20. 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;

retrieving a journal of user events associated with a user terminal in response to receiving a request for a content package from the user terminal, wherein the user terminal is associated with a user;

detecting sequences of user events in the journal, wherein each of the sequences makes up a respective portion of a predefined sequence of user events associated with a respective response mode;

computing an intent score for each respective response mode, the intent score indicating a proximity of the respective portion of the predefined sequence of user events to a completion of the predefined sequence of user events associated with the respective response mode; and

assembling a queue of invitational content for the user based on the intent score of each respective response mode, wherein a position of the invitational content in the queue is based on the intent for each respective response mode.

21. The system of claim 20, wherein invitational content associated with the respective portion of the predefined sequence of user events associated with the respective response mode is positioned at a top of the queue.

22. The system of claim 20, wherein assembling the queue further comprises choosing invitational content associated with response modes having intent scores meeting a threshold criteria.

23. The system of claim 20, wherein assembling the queue further comprises selecting invitational content associated with a pre-defined number of response modes having highest intent scores.

24. The system of claim 20, wherein the computing steps further comprises computing the intent score for each respective response mode based on a temporal relationship among the user events associated with a respective sequence of user events.

25. The system of claim 20, wherein the detecting step further comprises identifying user events in the journal and determining a presence of a sequence of user events in the journal if the user events identified in the journal have an equivalent temporal relationship as the user events in the sequence of user events.