MOBILE DEVICE-RELATED MEASURES OF AFFINITY

• US 20170091645A1
• Filed: 12/14/2016
• Published: 03/30/2017
• Est. Priority Date: 10/01/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Matus, Jonathan Arie
• Granted Patent: US 10,257,309 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 21/00 Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 65/403 Arrangements for multi-party communication, e.g. for conferences data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04W 4/50 Service provisioning or reconfiguring

Abstract

In one embodiment, a method includes sending a request for a measure of affinity associated with a first user for a particular content associated with a second user, where the measure of affinity predicts a level of interest the first user has for the particular content; sending weighting information for computing the measure of affinity, where the weighting information includes information specifying a first weight to be attributed to a first predictor function that is based on the second user and a second weight to be attributed to a second predictor function that is based on concepts associated with the particular content; receiving the measure of affinity; and sending, to the first user, the particular content, based on the received measure of affinity.

Claims

1. A method comprising, by one or more computing devices associated with an application:

sending, to a computer server machine, a request for a first measure of affinity associated with a first user for a particular content, wherein the first measure of affinity predicts a level of interest the first user has for the particular content, and wherein the particular content is associated with a second user;

sending, to the computer server machine, a first weighting information that is to be used in computing the first measure of affinity, wherein the first weighting information comprises information specifying;

a first weight to be attributed to a first predictor function that is based on the second user, and

a second weight to be attributed to a second predictor function that is based on one or more concepts associated with the particular content;

receiving, by one or more of the computing devices associated with the application, the first measure of affinity; and

sending, to the first user, the particular content, based at least in part on the received first measure of affinity.

2. The method of claim 1, further comprising determining the first weight and the second weight based on the relative importance of their respective predictor functions to the first measure of affinity with respect to sending the particular content to the first user.

3. The method of claim 1, wherein:

the first predictor function predicts a level of interest the first user has in viewing content posted by the second user; and

the second predictor function predicts a level of interest the first user has for the particular content.

4. The method of claim 1, wherein the first weighting information further comprises information specifying a third weight to be attributed to a third predictor function that is based on one or more attributes of the first user.

5. The method of claim 1, further comprising:

sending a request for a second measure of affinity associated with the first user for the particular content;

determining one or more weights to be included in a second weighting information;

sending the second weighting information that is to be used in computing the second measure of affinity;

receiving the second measure of affinity; and

wherein the particular content is sent to the first user based at least in part on the received first measure of affinity and the second measure of affinity.

6. The method of claim 5, wherein the second weighting information comprises information specifying:

a fourth weight to be attributed to a fourth predictor function, the fourth predictor function being based on one or more attributes of the first user;

a fifth weight to be attributed to a fifth predictor function, the fifth predictor function being based on a history of actions performed by the first user on a particular client system associated with the first user; and

a sixth weight to be attributed to a sixth predictor function, the sixth predictor function predicting a level of interest the first user has for the second user.

7. The method of claim 1, wherein a delivery of the particular content is customized based on the received measure of affinity.

8. The method of claim 1, wherein the particular content comprises a social endorsement for a particular item.

9. The method of claim 1, wherein the particular content comprises a request to join a particular application.

10. The method of claim 1, wherein determining the subsequent action comprises determining a customization of the delivery of information to the first user.

11. The method of claim 1, wherein determining the subsequent action comprises determining to filter content that is sent to first user.

12. The method of claim 1, wherein the measure of affinity is further based on one or more actions taken by the first user with respect to a client system associated with the first user.

13. The method of claim 12, wherein the one or more of the actions taken by the first user with respect to the client system comprises actions using a telephone feature of the client system, accessing content through a network connection, actions using contact information stored on the client system, or actions affecting one or more applications on the client system.

14. The method of claim 1, wherein the computer server machine is associated with a social-networking system and the first user is a user of the social-networking system.

15. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

send a request for a measure of affinity associated with a first user for a particular content, wherein the measure of affinity predicts a level of interest the first user has for the particular content, and wherein the particular content is associated with-a second user;

send weighting information that is to be used in computing the measure of affinity, wherein the weighting information comprises information specifying;

a first weight to be attributed to a first predictor function that is based on the second user, and

a second weight to be attributed to a second predictor function that is based on one or more concepts associated with the particular content;

receive the measure of affinity; and

send, to the first user, the particular content, based at least in part on the received measure of affinity.

16. The media of claim 15, wherein the software is further operable when executed to:

determine the first weight and the second weight based on the relative importance of their respective predictor functions to the first measure of affinity with respect to sending the particular content to the first user.

17. The media of claim 15, wherein:

the first predictor function predicts a level of interest the first user has in viewing content posted by the second user; and

the second predictor function predicts a level of interest the first user has for the particular content.

18. The media of claim 15, wherein the first weighting information further comprises information specifying a third weight to be attributed to a third predictor function that is based on one or more attributes of the first user.

19. The media of claim 15, wherein the software is further operable when executed to:

receive a second measure of affinity associated with the first user for the particular content;

send second weighting information that is to be used in computing the second measure of affinity;

receive the second measure of affinity; and

wherein the particular content is sent to the first user based at least in part on the received first measure of affinity and the second measure of affinity.

20. A system comprising:

one or more processors associated with one or more computer servers associated with a social-networking system; and

a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to;

send a request for a measure of affinity associated with a first user for a particular content, wherein the measure of affinity predicts a level of interest the first user has for the particular content, and wherein the particular content is associated with a second user;

send weighting information that is to be used in computing the measure of affinity, wherein the weighting information comprises information specifying;

a first weight to be attributed to a first predictor function that is based on the second user, and

a second weight to be attributed to a second predictor function that is based on one or more concepts associated with the particular content;

receive the measure of affinity; and

send, to the first user, the particular content, based at least in part on the received measure of affinity.