Systems and methods for trending and relevance of phrases for a user

• US 9,135,211 B2
• Filed: 12/20/2011
• Issued: 09/15/2015
• Est. Priority Date: 12/20/2011
• Status: Active Grant

• Current Assignee: Bitly, Inc.
• Original Assignee: Bitly, Inc.
• Inventors: Stern, Peter, Mason, Hilary, Dewar, Michael
• Primary Examiner(s): BUI, JONATHAN A
• Application Number:
  US13/332,090
• Publication Number:
  US 20130159506A1
• Time in Patent Office: 1,365 Days
• Field of Search: 707/723, 707/724, 707/725, 707/726, 707/727, 707/728, 707/729, 707/730, 707/731, 709/224
• US Class Current: 1/1
• CPC Class Codes: G06F 15/173 using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

The present disclosure is directed to a method for identifying which phrases are trending across an aggregate of users that are relevant to a specific user. The method may include receiving, by a server, identification of a user. The server may identify a plurality of phrases that are trending upwards based on velocity of clicks to content containing, related to or associated with the plurality of phrases. The server may identify trending or temporally popular phrases based on aggregating multiple users'"'"' interactions with an aggregate of content. The server may determine a relevance score for each phrase of the plurality of phrases that are trending upwards based on identification of the user and actions of the user on content associated with each phrase, such as user clicking on content identifying or related to each phrase. The server may identify one or more phrases of the plurality of phrases based on relevance score.

Claims

1. A method for identifying phrases trending and relevant to a user, the method comprising:

(a) receiving, by a server of a linking system, an identification of a user;

(b) receiving, by the server, identification of a plurality of clicks of encoded uniform resource locator (URL) links, the encoded URL links generated by the server and linked to content items on destination servers, the plurality of clicks corresponding to clicks performed by a plurality of users via devices on which the encoded URL links are provided for display;

(c) determining, by the server, for each of the content items on destination servers, a velocity of the clicks of the plurality of clicks to one or more of the encoded URL links linked to the content item, the velocity of the clicks of the plurality of clicks corresponding to a number of clicks per unit time;

(d) identifying, by the server, from the content items, a plurality of phrases that are trending upwards based on the determined velocity of clicks to encoded URL links linked to the content items that comprise the plurality of phrases;

(e) determining, by the server, a relevance score for each phrase of the plurality of phrases that are trending upwards based on the identification of the user and actions of the user on content comprising each phrase;

(f) identifying, by the server, one or more phrases of the plurality of phrases based on the relevance score; and

(g) selecting, by the server, content to serve the user based on the identified one or more phrases.

2. The method of claim 1, wherein step (a) further comprises receiving, by the server, the identification of the user via a cookie.

3. The method of claim 1, wherein step (d) further comprises identifying, by the server, the plurality of phrases that are trending upwards above a predetermined threshold.

4. The method of claim 1, wherein step (d) further comprises identifying, by the server, an enumerated list of the plurality of phrases trending from highest to lowest.

5. The method of claim 1, wherein the actions of the user comprise a plurality of actions of the user to click on a link to content comprising each phrase.

6. The method of claim 1, wherein the actions of the user comprise a plurality of actions of the user to share content comprising each phrase.

7. The method of claim 1, wherein step (f) further comprises selecting, by the server, the one or more phrases with the highest relevance score.

8. The method of claim 1, wherein step (f) further comprises selecting, by the server, the one or more phrases with a relevance score greater than a predetermined threshold.

9. The method of claim 1, wherein step (f) further comprises selecting, by the server, the one or more phrases with a relevance score greater than a first predetermined threshold and that are trending within a second predetermined threshold.

10. A system for identifying phrases trending and relevant to a user, the system comprising:

a server of a linking system including one or more hardware processors receiving an identification of a user and identification of a plurality of clicks of encoded uniform resource locator (URL) links, the encoded URL links enumerated by the server and linked to content items on destination servers, the plurality of clicks corresponding to clicks performed by a plurality of users via devices on which the encoded URL links are provided for display;

a trending engine determining, for each of the content items on destination servers, a velocity of the clicks of the plurality of clicks to one or more of the encoded URL links linked to the content item, the velocity of the clicks of the plurality of clicks corresponding to a number of clicks per unit time and identifying, from the content items, a plurality of phrases that are trending upwards based on the determined velocity of clicks to encoded URL links linked to the content items that comprise the plurality of phrases;

a relevance scorer determining for each phrase of the plurality of phrases that are trending upwards based on the identification of the user and actions of the user on content comprising each phrase;

wherein the server identifies one or more phrases of the plurality of phrases based on the relevance score; and

wherein the server selects content to serve the user based on the identified one or more phrases.

11. The system of claim 10, wherein the server receives the identification of the user via a cookie.

12. The system of claim 10, wherein the trending engine identifies the plurality of phrases that are trending upwards above a predetermined threshold.

13. The system of claim 10, wherein the trending engine identifies an enumerated list of the plurality of phrases trending from highest to lowest.

14. The system of claim 10, wherein the actions of the user comprise a plurality of actions of the user to click on a link to content comprising each phrase.

15. The system of claim 10, wherein the actions of the user comprise a plurality of actions of the user to share content comprising each phrase.

16. The system of claim 10, wherein the server selects the identified one or more phrases with the highest relevance score.

17. The system of claim 10, wherein the server selects the identified one or more phrases with a relevance score greater than a predetermined threshold.

18. The system of claim 10, wherein the server selects the identified one or more phrases with a relevance score greater than a first predetermined threshold and that are trending within a second predetermined threshold.