IP Library Granted Patent US 10,193,847
Granted Patent B2
US 10,193,847 · App. 15/171,719 · Granted Jan 29, 2019

Contextual feed

Inventors: Nikita Igorevych Lytkin (Sunnyvale, CA); Ying Xuan (Sunnyvale, CA); Guy Lebanon (Menlo Park, CA)
Assignee: Microsoft Technology Licensing, LLC
H04L51/32G06F17/30516G06F17/30867H04L67/02H04L67/306
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,193,847
App. No.
15/171,719
Granted
Jan 29, 2019
Kind
B2
Abstract

A news feed system of an on-line social network system obtains and utilizes data related to events that originate with members of the on-line social network system from web pages other those members' news feed pages. The news feed system monitors signals that are not related to feed interaction and generates contextual engagement features based on those signals. The news feed system associates contextual engagement features with respective member profiles and may store the association information for a period of time. The news feed system then uses these features to train a model that ranks news feed inventory and/or as input into that model.

Claims (37)

1. A computer-implemented method comprising:

maintaining member profiles representing members in an on-line social network system, the on-line social network system comprising a news feed web page generator to generate news feed web pages for presentation to members represented by respective member profiles;

detecting events originated with the member profiles from web pages that are distinct from news feed pages generated for the respective member profiles by the news feed web page generator;

using at least one processor, generating contextual engagement features, based on the detected events, the contextual engagement features reflecting respective areas of a web site provided by the on-line social network system where respective events occurred;

including the contextual engagement features as training data for training a second pass ranker;

for a focus profile representing a focus member in the on-line social network system, detecting a request to generate news feed web page, generating focus contextual engagement features based on recent events data representing events originated with the focus member from web pages that are distinct from news feed pages previously generated for the focus member, the recent events data represents respective events detected within a predetermined period of time from the request to generate news feed web page for the focus member, and providing the focus contextual engagement features as input to the second pass ranker; and

generating, using the second pass ranker that was trained using the contextual engagement features, respective ranks for items in an inventory of updates identified as potentially of interest to a the focus member and selecting a subset of items from the inventory based on the generated respective ranks, the second pass ranker to generate the respective ranks using as input the focus contextual engagement features.

2. The method of claim 1 , comprising constructing a news feed web page that includes the subset of items from the inventory.

3. The method of claim 2 , comprising causing presentation of the news feed web page on a display device of the focus member.

4. The method of claim 1 , wherein the events originated from web pages that are distinct from news feed pages generated for the member are events detected within the on-line social network system.

5. The method of claim 4 , wherein the events detected within the on-line social network system include connect requests, email within the on-line social system, or job searches.

6. The method of claim 1 , wherein the events originated from web pages that are distinct from news feed pages generated for the member are events detected outside of the on-line social network system.

7. The method of claim 1 , wherein the events detected outside of the on-line social network system include events initiated from web pages generated by a third party entity with respect to the on-line social system, said web pages including a visual control actionable to share the web page to the on-line social system.

8. The method of claim 1 , comprising:

determining that one or more events represented by the recent events data is a job search; and

increasing respective ranks for those items from the inventory that are job postings.

9. A computer-implemented system comprising:

one or more processors; and

a non-transitory computer readable storage medium comprising instructions that when executed by the one or processors cause the one or more processors to perform operations comprising:

maintaining member profiles representing members in an on-line social network system, the on-line social network system comprising a news feed web page generator to generate news feed web pages for presentation to members represented by respective member profiles;

detecting events originated with the member profiles from web pages that are distinct from news teed pages generated for the respective member profiles by the news feed web page generator;

generating contextual engagement features based on the detected events, the contextual engagement features reflecting respective areas of a web site provided b the on-line social network system where respective events occurred;

including the contextual engagement features as training data for training a second pass ranker; and

generating, using the second pass ranker that was trained using the contextual engagement features, respective ranks for items in an inventory of updates identified as potentially of interest to a the focus member and selecting a subset of items from the inventory based on the generated respective ranks, the second pass ranker to generate the respective ranks using as input the focus contextual engagement features.

10. The system of claim 9 , wherein the news feed web page generator is to construct a news feed web page that includes the subset of items from the inventory.

11. The system of claim 10 , comprising causing presentation of the news feed web page on a display device of the focus member.

12. The system of claim 9 , wherein the events originated from web pages that are distinct from news feed pages generated for the member are events detected within the on-line social network system.

13. The system of claim 12 , wherein the events detected within the on-line social network system include connect requests, email within the on-line social system, or job searches.

14. The system of claim 9 , wherein the events originated from web pages that are distinct from news feed pages generated for the member are events detected outside of the on-line social network system.

15. The system of claim 9 , wherein the events detected outside of the on-line social network system include events initiated from web pages generated by a third party entity with respect to the on-line social system, said web pages including a visual control actionable to share the web page to the on-line social system.

16. A machine-readable non-transitory storage medium having instruction data executable by a machine to cause the machine to perform operations comprising:

maintaining member profiles representing members in an on-line social network system, the on-line social network system comprising a news feed web page generator to generate news feed web pages for presentation to members represented by respective member profiles;

detecting events originated with the member profiles from web pages that are distinct from news feed pages generated for the respective member profiles by the news feed web page generator;

generating contextual engagement features, based on the detected events, the contextual engagement features reflecting respective areas of a web site provided by the on-line social network system where respective events occurred;

including the contextual engagement features as training data for training a second pass ranker;

for a focus profile representing a focus member in the on-line social network system, detecting a request to generate news feed web page, generating focus contextual engagement features based on recent events data representing events originated with the focus member from web pages that are distinct from news feed pages previously generated for the focus member, the recent events data represents respective events detected within a predetermined period of time from the request to generate news feed web page for the focus member, and providing the focus contextual engagement features as input to the second pass ranker; and

generating, using the second pass ranker that was trained using the contextual engagement features, respective ranks for items in an inventory of updates identified as potentially of interest to a the focus member and selecting a subset of items from the inventory based on the generated respective ranks, the second pass ranker to generate the respective ranks using as input the focus contextual engagement features.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 1, 2017
From: LINKEDIN CORPORATION
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 044746/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 2, 2016
From: LYTKIN, NIKITA IGOREVYCH; XUAN, YING; LEBANON, GUY
To: LINKEDIN CORPORATION
Reel/Frame 038788/0518 →
Continuity (1)
Related Publication 20170353421A1 · Dec 7, 2017