Determining whether to provide an advertisement to a user of a social network

• US 9,805,391 B2
• Filed: 05/29/2013
• Issued: 10/31/2017
• Est. Priority Date: 09/15/2010
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Excalibur IP, LLC (Acacia Research Corporation)
• Inventors: Agarwal, Deepak K.
• Primary Examiner(s): Sittner, Matthew T
• Application Number:
  US13/904,848
• Publication Number:
  US 20130275212A1
• Time in Patent Office: 1,616 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Techniques are described herein for determining whether to provide an advertisement to a user of a social network. The determination is based on a click probability and a social network value for the user. The click probability indicates a likelihood of the user to select the advertisement if provided to the user via the social network. The social network value is based on a subscription probability of the user and further based on subscription probabilities of other users in the social network that are included in an affinity set of the user. Each subscription probability indicates a likelihood of a respective user to subscribe to a paid service with respect to the social network.

Claims

1. An advertisement serving system, comprising:

communication interface circuitry, configured to communicate data with user devices and a social network server over the Internet, the social network server configured to serve at least a part of a social network website over the Internet; and

targeted advertisement circuitry communicatively coupled to the communication interface circuitry, the targeted advertisement circuitry including;

a processing device configured to determine whether to provide specified advertisements to the user devices served the part of the social network website;

click probability circuitry configured to;

learn a machine learned rule based on historical logs; and

determine a click probability for a user of the at least part of the website by applying the machine learned rule to an attribute of the user, the click probability indicating a likelihood of the user selecting an advertisement if the advertisement is provided to the user via the part of the social network website;

subscription probability circuitry configured to determine a plurality of subscription probabilities for a plurality of users of the social network website, the plurality of users including the user and second users that are included in an affinity set of the user, each subscription probability indicating a likelihood of a user of the plurality of users to subscribe to a paid service of the social network website offered by the social network website for the social network website;

network value circuitry configured to determine a social network value for the user based on the plurality of subscription probabilities;

the a processing device further configured to determine that the click probability meets or exceeds a click probability threshold and that the social network value for the user is at or below a social network value threshold; and

provision determination circuitry configured to communicate over the Internet the advertisement through the communication interface circuitry to the social network server that communicates the part of the social network with the advertisement to the user in response to the processing device determining that the click probability meets or exceeds the click probability threshold and the social network value for the user is at or below the social network value threshold.

2. The advertisement serving system of claim 1, wherein the network value circuitry is further configured to:

receive, from the social network server over the Internet, social network link data about links between users of the social network website; and

determine the social network value of the user using the received social network link data.

3. The advertisement serving system of claim 2, wherein the social network link data includes an associated link weight indicative of number, frequency, quality, or any combination thereof, of communications between the user and other users of the social network website.

4. The advertisement serving system of claim 3, wherein the network value circuitry is further configured to receive social network link data, from the social network server over the Internet, for communications between the user and the second users in the affinity set.

5. The advertisement serving system of claim 3, wherein the network value circuitry comprises an iterative calculation circuitry configured to calculate a score for users including the user using the received social network link data, wherein the network value circuitry is further configured to use a ranking algorithm and the calculated scores for the users to determine the social network value.

6. The advertisement serving system of claim 1, wherein the provision determination circuitry is configured to:

determine a risk value for the advertisement based on the click probability and the social network value of the user; and

use the risk value to determine whether to provide the advertisement to the user via the part of the social network website.

7. The advertisement serving system of claim 6, wherein the risk value is indicative of a likelihood of the advertisement negatively impacting an experience of the user using the social network website.

8. The advertisement serving system of claim 1, wherein the provision determination circuitry is configured to determine whether to provide the advertisement by comparing the social network value for the user to a threshold.

9. The advertisement serving system of claim 1, wherein the provision determination circuitry is configured to determine whether to provide the advertisement by comparing the click probability for the user for the advertisement to a click probability threshold and comparing the social network value for the user to a social network value threshold.

10. A method, comprising:

determining, by subscription probability circuitry, a plurality of subscription probabilities for a plurality of users of a social network website by applying machine learned rules to attributes of the plurality of user, the plurality of users including a user and second users that are included in an affinity set of the user, each subscription probability indicating a likelihood of a user of the plurality of users to subscribe to a paid service of the social network website offered by the social network website for the social network website;

determining, by network value circuitry, a social network value for the user based on the plurality of subscription probabilities;

determining, by click probability circuitry, a click probability for the user, the click probability indicating a likelihood of the user selecting an advertisement if the advertisement is provided to the user via a webpage of the social network website;

selecting, by targeted advertisement circuitry, the advertisement to show to the user, when the click probability meets or exceeds a click probability threshold and when the social network value for the user is at or below a social network value threshold; and

communicating, by communication interface circuitry over the Internet, the advertisement to a social network server that serves the webpage with the advertisement to the user.

11. The method of claim 10, wherein the determining a social network value further includes:

identifying other users of the social network with which the user has a relationship through the social network;

determining a value for the relationships between the user and the identified other users; and

using the value for the relationships to determine the social network value.

12. The method of claim 11, wherein the determining a value for the relationships comprises determining a value using a number of connections the user has with the identified other users through the social network website.

13. The method of claim 11, wherein the determining a value for the relationships comprises determining a value using information about an extent with which the user communicates with the other users through the social network website.

14. The method of claim 11, further comprising:

determining, by the provision determination circuitry, a risk value for the advertisement based on the click probability, the social network value of the user, and a level of aggressiveness of the advertisement;

comparing the risk value to a risk threshold; and

selecting the advertisement to show to the user if the risk value does not exceed the risk threshold.

15. A method, comprising:

determining, by click probability circuitry, a click probability for an advertisement for a user of a social network website;

determining, by subscription probability circuitry, a plurality of subscription probabilities for a plurality of users of the social network website, the plurality of users including the user and second users that are included in an affinity set of the user, each subscription probability indicating a likelihood of a user of the plurality of users to subscribe to a paid service of the social network website offered by the social network website for the social network website;

determining, by network value circuitry, a social network value for the user based on the plurality of subscription probabilities;

selecting, by provision determination circuitry, the advertisement to provide to the user when the click probability meets or exceeds a click probability threshold and when the social network value for the user is at or below a social network value threshold; and

communicating, by communication interface circuitry over the Internet, the selected advertisement to a social network server that serves the website and the advertisement to the user.

16. The method of claim 15, further comprising:

determining, by the provision determination circuitry, a risk value for the advertisement based on the click probability and the social network value of the user, the risk value indicating a likelihood of the advertisement to negatively impact an experience of the user with respect to the social network web site;

comparing the determined risk value with a risk threshold; and

selecting the advertisement to provide to the user when the determined risk value exceeds the risk threshold.

17. The method of claim 15, further comprising:

determining, by targeted advertisement circuitry, a user score value as an initial score for the user based on the plurality of subscription probabilities;

iteratively updating the user score value based on social network data for the user; and

iteratively determining the risk value based on the updated user score.

18. The method of claim 15, further comprising:

receiving, by the network value circuitry from the social network server over the Internet, social network link data about links between users of the social network website; and

determining, by the network value circuitry, the social network value of the user using the received social network link data.