Advertisement campaign system using socially collaborative filtering

• US 20090271256A1
• Filed: 04/25/2008
• Published: 10/29/2009
• Est. Priority Date: 04/25/2008
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Lawler, Brian Patrick, Toebes, John, Chou, Gary T.
• Granted Patent: US 8,380,562 B2
• Time in Patent Office: Days
• US Class Current: 705/14.260
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: H04L 67/306 User profiles

Abstract

In one embodiment, a method comprises identifying, in a network, user selection preferences of an identified user having accessed the network, the identifying based on an accumulation of user selection inputs executed by the identified user, the user selection inputs accumulated relative to input options presented to the user and identifying respective available network items; classifying, by an apparatus in the network, the identified user into one of multiple user affinity categories relative to an advertisement campaign for a targeted product, the classifying based on determining whether one of the user selection inputs represents a view gesture of the user having viewed the targeted product; and selecting an advertisement asset for delivery to the identified user based on the classifying of the identified user into the one user affinity category.

Claims

1. A method comprising:

identifying, in a network, user selection preferences of an identified user having accessed the network, the identifying based on an accumulation of user selection inputs executed by the identified user, the user selection inputs accumulated relative to input options presented to the user and identifying respective available network items;

classifying, by an apparatus in the network, the identified user into one of multiple user affinity categories relative to an advertisement campaign for a targeted product, the classifying based on determining whether one of the user selection inputs represents a view gesture of the user having viewed the targeted product; and

the apparatus selecting an advertisement asset for delivery to the identified user based on the classifying of the identified user into the one user affinity category, the advertisement asset selected from among multiple advertisement assets associated with the respective user affinity categories for the advertisement campaign.

2. The method of claim 1, further comprising:

updating the user selection preferences of the identified user in response to detecting a user selection input expressing an identifiable gesture relative to the advertisement asset delivered to the identified user, and

updating user affinity values associated with the advertisement asset, for determining subsequent selection of the advertisement asset for the one user affinity category.

3. The method of claim 1, wherein the classifying includes:

if none of the user selection inputs for the identified user demonstrates the view gesture, classifying the identified user based on determining preferred network items for users having the view gesture relative to the targeted product, and determining a correlation level between the user selection inputs by the identified user relative to the preferred network items, or

if at least one of the user selection inputs for the identified user demonstrates a view gesture, classifying the identified user based on whether one of the user selection inputs of the identified user represents a creation gesture relative to the targeted product;

4. The method of claim 3, wherein the user affinity categories for the targeted product include:

a lurker category of users containing at least the view gesture relative to the targeted product, the lurker category including an active participants category of users containing the view gesture and at least the creation gesture, the active participants category including a key influencers category identifying active participants having created content related to the targeted product, using the corresponding creation gesture, that generate substantially favorable gestures by other users having viewed the created content relative to other created content created by other active participants;

a missed opportunity category of users that do not have the view gesture relative to the targeted product, the missed opportunity category of users having a highest correlation of shared interests with the lurker category of users;

a potential customer category of users that do not have the view gesture relative to the targeted product, the potential customer category of users having a lower correlation of shared interests with the lurker category of users than the missed opportunity category of users; and

a not interested category of users that do not have the view gesture relative to the targeted product, the not interested category of users having a lowest correlation of shared interests with the lurker category of users relative to the missed opportunity category of users and the potential customer category of users.

5. The method of claim 4, wherein if none of the user selection inputs for the identified user demonstrates the view gesture, the classifying includes generating a first ordered list of the preferred network items having respective item affinity values generated for the lurker category of users, and generating a second ordered list of identified network users distinct from the lurker category of users and providing respective user affinity values for each of the preferred network items based on the respective user selection preferences, the identified user classified into one of the missed opportunity category, the potential customer category, or the not interested category, based on a relative position of the identified user within the second ordered list.

6. The method of claim 4, wherein if at least one of the user selection inputs for the identified user demonstrates a view gesture, the classifying includes:

generating a first ordered list of the lurker category of users having respective user affinity values for the targeted product;

generating a second ordered list of the created content having respective affinity correlation values relative to the targeted product based on evaluating the respective creation gestures that generated the created content;

evaluating gestures for viewing the created content by the other users having viewed the created content;

reordering the second ordered list based on evaluating the gestures for viewing the created content, according to an accumulated influence value determined for each created content based on the corresponding gestures for viewing the corresponding created content;

reordering the first ordered list of the lurker category of users according to the respective accumulated influence values, the reordered first ordered list ordering in sequence the key influencers category, the active participants category and the lurker category; and

classifying the identified user based on a relative position of the identified user within the reordered first ordered list.

7. The method of claim 6, wherein the identified user is classified within the key influencers category of users as contrarian user having expressed a substantial dislike of the targeted product and having an accumulated influence value indicating a substantial influence among the other users having viewed the created content, wherein the advertisement asset delivered to the identified user is directed for the contrarian user within the key influencers category of users.

8. The method of claim 3, further comprising the apparatus selecting the advertisement campaign for the targeted product, from among a plurality of advertisement campaigns for respective targeted products, based on:

determining a group of network users having a highest correlation of shared interests with the identified user, based on (1) identifying, from the available network items, second preferred network items having highest relative item affinity values generated for the identified user based on the user selection preferences, and (2) identifying first network users providing highest relative user affinity values for each of the preferred network items based on the respective user selection preferences;

generating a first ordered list of network items most likely to be preferred by the identified user based on determining, from among network items not presented to the identified user, the preferred network items for each of the first network users in the group based on the respective user selection preferences, the first ordered list of network items including the advertisement campaign for the targeted product and at least one of the plurality of advertisement campaigns;

filtering the first ordered list of network items with a second list of network items related to a context presented to the identified user, the second list of network items including the advertisement campaign for the targeted product and at least one of the plurality of advertisement campaigns; and

identifying the advertisement campaign for the targeted product as having a highest relative position within first ordered list filtered with the second list, relative to any of the plurality of advertisement campaigns.

9. The method of claim 1, further comprising creating the advertisement campaign for the targeted product based on adding the advertisement campaign for the targeted product as an available network item in the network, including artificially creating a substantially strong affinity value between the advertisement campaign and at least one of an ideal targeted user having an artificially created item affinity value toward at least one other network item, a prescribed demographic identifying users having respective item affinity values toward network items, or an existing network item.

10. The method of claim 9, wherein the creating the advertisement campaign includes storing a set of user-item relationships for the ideal targeted user that specifies a substantially strong affinity value between the advertisement campaign and the ideal targeted user, and the artificially created item affinity value toward the at least one other network item.

11. The method of claim 9, wherein the creating the advertisement campaign includes identifying the users within the prescribed demographic, and assigning to each of the users the substantially strong affinity value toward the advertisement campaign as a corresponding input to the corresponding user selection preferences.

12. The method of claim 9, wherein the creating the advertisement campaign includes creating the substantially strong affinity value between the advertisement campaign and the existing network item based on creating a similarity relationship between the existing network item and the advertisement campaign, causing user affinity values associated with user selection preferences of respective users to be replicated toward the advertisement campaign.

13. An apparatus comprising:

a network interface circuit configured for determining an identified user is accessing a network, and in response outputting, via the network for presentation to the identified user, an advertisement asset for delivery to the identified user; and

a processor circuit configured for;

identifying user selection preferences of the identified user based on an accumulation of user selection inputs executed by the identified user, the user selection inputs accumulated relative to input options presented to the user and identifying respective available network items, classifying the identified user into one of multiple user affinity categories relative to an advertisement campaign for a targeted product, the classifying based on the processor circuit determining whether one of the user selection inputs represents a view gesture of the user having viewed the targeted product, and

selecting the advertisement asset for delivery to the identified user based on the classifying of the identified user into the one user affinity category, the advertisement asset selected from among multiple advertisement assets associated with the respective user affinity categories for the advertisement campaign.

14. The apparatus of claim 13, wherein the processor circuit further is configured for:

updating the user selection preferences of the identified user in response to detecting a user selection input expressing an identifiable gesture relative to the advertisement asset delivered to the identified user, and

updating user affinity values associated with the advertisement asset, for determining subsequent selection of the advertisement asset for the one user affinity category.

15. The apparatus of claim 13, wherein the processor circuit is configured for classifying the identified user based on:

if none of the user selection inputs for the identified user demonstrates the view gesture, classifying the identified user based on determining preferred network items for users having the view gesture relative to the targeted product, and determining a correlation level between the user selection inputs by the identified user relative to the preferred network items, or

if at least one of the user selection inputs for the identified user demonstrates a view gesture, classifying the identified user based on whether one of the user selection inputs of the identified user represents a creation gesture relative to the targeted product.

16. The apparatus of claim 15, wherein the user affinity categories for the targeted product include:

a lurker category of users containing at least the view gesture relative to the targeted product, the lurker category including an active participants category of users containing the view gesture and at least the creation gesture, the active participants category including a key influencers category identifying active participants having created content related to the targeted product, using the corresponding creation gesture, that generate substantially favorable gestures by other users having viewed the created content relative to other created content created by other active participants;

a missed opportunity category of users that do not have the view gesture relative to the targeted product, the missed opportunity category of users having a highest correlation of shared interests with the lurker category of users;

a potential customer category of users that do not have the view gesture relative to the targeted product, the potential customer category of users having a lower correlation of shared interests with the lurker category of users than the missed opportunity category of users; and

a not interested category of users that do not have the view gesture relative to the targeted product, the not interested category of users having a lowest correlation of shared interests with the lurker category of users relative to the missed opportunity category of users and the potential customer category of users.

17. The apparatus of claim 16, wherein the processor circuit is configured such that if none of the user selection inputs for the identified user demonstrates the view gesture, the processor circuit executes the classifying based on generating a first ordered list of the preferred network items having respective item affinity values generated for the lurker category of users, and generating a second ordered list of identified network users distinct from the lurker category of users and providing respective user affinity values for each of the preferred network items based on the respective user selection preferences, the identified user classified by the processor circuit into one of the missed opportunity category, the potential customer category, or the not interested category, based on a relative position of the identified user within the second ordered list.

18. The apparatus of claim 16, wherein the processor circuit is configured such that if at least one of the user selection inputs for the identified user demonstrates a view gesture, the processor circuit executes the classifying based on:

generating a first ordered list of the lurker category of users having respective user affinity values for the targeted product;

generating a second ordered list of the created content having respective affinity correlation values relative to the targeted product based on evaluating the respective creation gestures that generated the created content;

evaluating gestures for viewing the created content by the other users having viewed the created content;

reordering the second ordered list based on evaluating the gestures for viewing the created content, according to an accumulated influence value determined for each created content based on the corresponding gestures for viewing the corresponding created content;

reordering the first ordered list of the lurker category of users according to the respective accumulated influence values, the reordered first ordered list ordering in sequence the key influencers category, the active participants category and the lurker category; and

classifying the identified user based on a relative position of the identified user within the reordered first ordered list.

19. The apparatus of claim 18, wherein the identified user is classified by the processor circuit within the key influencers category of users as contrarian user having expressed a substantial dislike of the targeted product and having an accumulated influence value indicating a substantial influence among the other users having viewed the created content, wherein the advertisement asset delivered to the identified user is directed for the contrarian user within the key influencers category of users.

20. The apparatus of claim 15, wherein the processor circuit is configured for selecting the advertisement campaign for the targeted product, from among a plurality of advertisement campaigns for respective targeted products, based on:

determining a group of network users having a highest correlation of shared interests with the identified user, based on (1) identifying, from the available network items, second preferred network items having highest relative item affinity values generated for the identified user based on the user selection preferences, and (2) identifying first network users providing highest relative user affinity values for each of the preferred network items based on the respective user selection preferences;

generating a first ordered list of network items most likely to be preferred by the identified user based on determining, from among network items not presented to the identified user, the preferred network items for each of the first network users in the group based on the respective user selection preferences, the first ordered list of network items including the advertisement campaign for the targeted product and at least one of the plurality of advertisement campaigns;

filtering the first ordered list of network items with a second list of network items related to a context presented to the identified user, the second list of network items including the advertisement campaign for the targeted product and at least one of the plurality of advertisement campaigns; and

identifying the advertisement campaign for the targeted product as having a highest relative position within first ordered list filtered with the second list, relative to any of the plurality of advertisement campaigns.

21. The apparatus of claim 13, wherein the processor circuit is configured for creating the advertisement campaign for the targeted product based on adding the advertisement campaign for the targeted product as an available network item in the network, including the processor circuit artificially creating a substantially strong affinity value between the advertisement campaign and at least one of an ideal targeted user having an artificially created item affinity value toward at least one other network item, a prescribed demographic identifying users having respective item affinity values toward network items, or an existing network item.

22. The apparatus of claim 21, wherein the processor circuit is configured for creating the advertisement campaign based on storing a set of user-item relationships for the ideal targeted user that specifies a substantially strong affinity value between the advertisement campaign and the ideal targeted user, and the artificially created item affinity value toward the at least one other network item.

23. The apparatus of claim 21, wherein the processor circuit is configured for creating the advertisement campaign based on identifying the users within the prescribed demographic, and assigning to each of the users the substantially strong affinity value toward the advertisement campaign as a corresponding input to the corresponding user selection preferences.

24. The apparatus of claim 23, wherein the processor circuit is configured for creating the advertisement campaign based on creating the substantially strong affinity value between the advertisement campaign and the existing network item based on creating a similarity relationship between the existing network item and the advertisement campaign, causing user affinity values associated with user selection preferences of respective users to be replicated toward the advertisement campaign.

25. An apparatus comprising:

a network interface circuit configured for determining an identified user is accessing a network, and in response outputting, via the network for presentation to the identified user, an advertisement asset for delivery to the identified user; and

means for selecting the advertisement asset based on;

identifying user selection preferences of the identified user based on an accumulation of user selection inputs executed by the identified user, the user selection inputs accumulated relative to input options presented to the user and identifying respective available network items,

classifying the identified user into one of multiple user affinity categories relative to an advertisement campaign for a targeted product, the classifying based on determining whether one of the user selection inputs represents a view gesture of the user having viewed the targeted product, and

selecting the advertisement asset for delivery to the identified user based on the classifying of the identified user into the one user affinity category, the advertisement asset selected from among multiple advertisement assets associated with the respective user affinity categories for the advertisement campaign.

26. Logic encoded in one or more tangible media for execution and when executed operable for:

identifying user selection preferences of an identified user having accessed the network, the identifying based on an accumulation of user selection inputs executed by the identified user, the user selection inputs accumulated relative to input options presented to the user and identifying respective available network items;

classifying the identified user into one of multiple user affinity categories relative to an advertisement campaign for a targeted product, the classifying based on determining whether one of the user selection inputs represents a view gesture of the user having viewed the targeted product; and

selecting an advertisement asset for delivery to the identified user based on the classifying of the identified user into the one user affinity category, the advertisement asset selected from among multiple advertisement assets associated with the respective user affinity categories for the advertisement campaign.