Online content delivery based on information from social networks

• US 20050278443A1
• Filed: 06/14/2004
• Published: 12/15/2005
• Est. Priority Date: 06/14/2004
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Winner, Jeffrey B., Galbreath, Nicholas
• Granted Patent: US 10,373,173 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Relevant content is prepared and selected for delivery to a member of a network based, in part, on prior online activities of the other members of the network, and the closeness of the member'"'"'s relationship with the other members of the network. The relevant content may be an online ad, and is selected from a number of candidate online ads based on click-through rates of groups that are predefined with respect to the member and with respect to certain attributes. An online ad'"'"'s revenue-generating potential may be considered in the selection process.

Claims

1. A method of preparing content to be delivered to a member of a network, comprising the steps of:

tracking online activities of members of the network who are friends of said member with respect to a certain act;

estimating a probability that said member will perform said certain act based the online activities tracked with respect to said certain act; and

preparing the content to be delivered to said member based on the estimated probability.

2. The method according to claim 1, wherein content associated with said certain act is included in the content to be delivered to said member if the estimated probability is larger than a predetermined threshold.

3. The method according to claim 1, wherein said certain act includes clicking on an online ad and the content associated with said certain act includes the online ad.

4. The method according to claim 3, wherein the step of estimating includes the step of computing a click-through rate of said members of the network who are friends of said member for said online ad, wherein the computed click-through rates are used in the step of estimating the probability.

5. The method according to claim 4, further comprising the step of computing a click-through rate of all members of the network who share a specific interest with said member for said online ad, wherein the computed click-through rate of all members of the network who share said specific interest with said member for said online ad is also used in the step of estimating the probability.

6. The method according to claim 1, further comprising the steps of:

tracking online activities of said members of the network who are friends of said member with respect to another act;

estimating a probability that said member will perform said another act based the online activities tracked with respect to said another act; and

estimating expected revenues from delivering content associated with said certain act to said member and from delivering content associated with said another act to said member, based on the estimated probabilities,

wherein content associated with the act with the higher estimated expected revenue is included in the content to be delivered to said member.

7. A method of managing delivery of online ads to a member of a network, comprising the steps of:

computing a click-through rate of members of the network who are friends of said member for each of several online ads; and

selecting one of said several online ads for delivery to said member based on the computed click-through rates.

8. The method according to claim 7, further comprising the step of estimating expected revenues from delivering said several online ads to said member based on the computed click-through rates, wherein the online ad with the highest estimated expected revenue is selected for delivery to said member.

9. The method according to claim 7, further comprising the steps of:

computing a click-through rate of members of the network who are friends of friends of said member for each of said several online ads;

computing a click-through rate of members of the network who are friends of friends of friends of said member for each of said several online ads;

computing additional click-through rates for each of said several online ads; and

for each of said several online ads, selecting a maximum click-through rate among the computed click-through rates for said online ad,

wherein the online ad that is selected for delivery to said member is based on the selected maximum click-through rates.

10. The method according to claim 9, further comprising the step of estimating expected revenues from delivering said several online ads to said member based on the selected maximum click-through rates, wherein the online ad with the highest estimated expected revenue is selected for delivery to said member.

11. The method according to claim 10, wherein the step of computing additional click-through rates includes the step of computing a click-through rate of all members of the network who are of the same gender as said member for each of said several online ads.

12. The method according to claim 10, wherein the step of computing additional click-through rates includes the step of computing a click-through rate of all members of the network who belong to the same age group as said member for each of said several online ads.

13. The method according to claim 10, wherein the step of computing additional click-through rates includes the step of computing a click-through rate of all members of the network who share a specific interest with said member for each of said several online ads.

14. A method of serving ads to a member of a network, comprising the steps of:

maintaining an ad database containing information about ads to be delivered to members of the network and a relationship database containing information about relationships between said member and other members of the network;

for each of said certain ads, estimating a probability that said member will click on said ad based on online activities of said other members of the network and the relationship information;

for each of said certain ads, estimating an expected revenue from said ad, based on the estimated probability that said member will click on said ad and a per-click revenue associated with said ad;

selecting one or more ads to be delivered to said member, from said certain ads based on the estimated expected revenues; and

delivering the selected ads to said member.

15. The method according to claim 14, wherein the step of estimating a probability for each of said certain ads includes the steps of:

computing a click-through rate of members of the network who are friends of said member for said ad;

computing a click-through rate of members of the network who are friends of friends of said member for said ad;

computing a click-through rate of members of the network who are friends of friends of friends of said member for said ad; and

computing additional click-through rates for said ad,

wherein the highest of the computed click-through rates for said ad is selected as the estimated probability for said ad.

16. The method according to claim 15, wherein the step of computing additional click-through rates includes the step of computing a click-through rate of all members of the network who are of the same gender as said member for each of said several online ads.

17. The method according to claim 15, wherein the step of computing additional click-through rates includes the step of computing a click-through rate of all members of the network who belong to the same age group as said member for each of said several online ads.

18. The method according to claim 15, wherein the step of computing additional click-through rates includes the step of computing a click-through rate of all members of the network who share a specific interest with said member for each of said several online ads.

19. The method according to claim 14, wherein the step of estimating a probability for each of said certain ads includes the steps of:

defining two or more groups with respect to said member; and

for each of the defined groups, computing a click-through rate for said ad,

wherein the highest of the computed click-through rates for said ad is selected as the estimated probability for said ad.

20. The method according to claim 19, wherein the groups defined include a first group including members of the network who are friends of said member, a second group including members of the network who are friends of friends of said member, and a third group including members of the network who are friends of friends of friends of said member.