Distant content discovery

Patent metadata

Field	Value
Publication number	US-11030208-B2
Application number	US-201816057229-A
Country	US
Kind code	B2
Filing date	Aug 7, 2018
Priority date	Sep 5, 2014
Publication date	Jun 8, 2021
Grant date	Jun 8, 2021

Abstract

Generating and providing a content feed to a user that surfaces information items that are determined to be interesting or relevant to the user including content that is determined to be “distant” to the user is provided. Explicit user actions are used to discover peers who are not colleagues of the user (e.g., peers with whom the user does not share a close organizational relationship, peers with whom the user does not regularly communicate, etc.), but who the user indicates an interest in via his/her actions. These peers are categorized as elevated peers of the user, and information items associated with and trending around the elevated peers are surfaced to the user in a content feed.

First claim

We claim:

1. A computer-implemented method for surfacing distant relevant information to a user in a content feed, comprising:
querying, by a computer, an organizational graph for activity data associated with the user and one or more individuals with whom the user is not closely related;
analyzing signals between the one or more individuals with whom the user is not closely related and one or more distant information items on which the user has not acted, wherein the one or more distant information items are information items associated with the one or more individuals with whom the user is not closely related;
determining scores for the one or more distant information items by calculating two scores for each of the one or more distant information items, wherein a first score is calculated using a feature weight for a colleague, and a second score is calculated using a feature weight for an elevated peer;
ranking the one or more distant information items for inclusion in the content feed for the user, wherein the ranking is based on the scores, and ranks the one or more distant information items as a possible content feed candidate;
determining, by the computer, whether the one or more distant information items are content feed candidates; and
responsive to a positive determination that a distant information item of the one or more distant information items is a content feed candidate, generating a content card for the distant information item for display in the content feed.

2. The computer-implemented method of claim 1 , wherein the one or more individuals with whom the user is not closely related comprises:
individuals with whom the user does not share a close organizational relationship, or
individuals with whom the user does not regularly communicate.

3. The computer-implemented method of claim 1 , wherein querying, by a computer, an organizational graph for activity data associated with the user and one or more individuals with whom the user is not closely related comprises querying the organizational graph for an edge between the user and an information item associated with one of the one or more individuals with whom the user is not closely related, wherein the edge is a representation of one of:
a read activity signal;
a like activity signal; and
a follow activity signal.

4. The computer-implemented method of claim 1 , wherein querying, by a computer, an organizational graph for activity data associated with the user and one or more individuals with whom the user is not closely related comprises querying the organizational graph for an edge between the user and one of the one or more individuals with whom the user is not closely related, wherein the edge is a representation of a co-attendee activity signal.

5. The computer-implemented method of claim 1 , wherein analyzing signals between the one or more individuals with whom the user is not closely related and one or more distant information items on which the user has not acted comprises querying the organizational graph for at least one of:
an information item authored by one of the one or more individuals with whom the user is not closely related;
an information item modified by one of the one or more individuals with whom the user is not closely related;
an information item recommended by one of the one or more individuals with whom the user is not closely related; and
an information item that is proxy to one of the one or more individuals with whom the user is not closely related.

6. The computer-implemented method of claim 1 , wherein ranking of the one or more distant information items for inclusion in the content feed for the user comprises:
categorizing an individual associated with each of the one or more distant information items as a distant peer of the user.

7. The computer-implemented method of claim 6 , wherein determining whether the one or more distant information items are content feed candidates comprises:
determining a percentage threshold of distant information items to include in the content feed; and
adding one or more of the one or more distant information items to the content feed in order of their ranking starting with a highest ranked distant information item until a percentage of distant information items to include in the content feed is within the percentage threshold.

8. The computer-implemented method of claim 7 , wherein determining a percentage threshold of distant information items to include in the content feed comprises:
analyzing selections made by the user of information items displayed in the content feed;
determining whether each selection is a distant information item, an information item of which the user has ownership, or an information item that is popular with the user's peers;
comparing a percentage of selections of distant information items, information items of which the user has ownership, and information items that are popular with the user's peers;
if the percentage of selections of distant information items is higher than the percentage of selections of information items which the user has ownership of or of information items that are popular with the user's peers, increasing the percentage threshold of distant information items to include in the content feed; and
if the percentage of selections of distant information items is lower than the percentage of selections of information items which the user has ownership of or of information items that are popular with the user's peers, decreasing the percentage threshold of distant information items to include in the content feed.

9. The computer-implemented method of claim 1 , wherein generating a content card for the distant information item for display in the content feed comprises generating a content card comprising at least one of:
a header;
a title;
a preview image of the distant information item;
information associated with why the distant information is relevant to the user; and
a selectable link to access the information item.

10. The computer-implemented method of claim 9 , further comprising:
receiving an indication of a selection to display the content feed;
displaying the content feed;
receiving an indication of a selection of a distant information item; and
providing access to the distant information item.

11. The computer-implemented method of claim 10 , further comprising:
determining, by the computer, that the selection of the distant information item is an indication of interest of the user in an individual associated with the distant information item; and
continuing to include distant information items associated with an individual in the user's content feed.

12. A system for surfacing distant relevant information to a user in a content feed, comprising:
one or more processors;
memory storing one or more engines executable by the one or more processors, the one or more engines comprising:
an analysis processing engine operable to:
query, an organizational graph for activity data associated with the user and one or more individuals with whom the user is not closely related;
analyze signals between the one or more individuals with whom the user is not closely related and one or more distant information items on which the user has not acted, wherein the one or more distant information items are information items associated with the one or more individuals with whom the user is not closely related;
determine scores for the one or more distant information items by calculating two scores for each of the one or more distant information items, wherein a first score is calculated using a feature weight for a colleague, and a second score is calculated usin

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Helvik Torbjørn
• Taylor Michael James
• Vinay Vishwa
• Vikjord Vidar
• Shah Viral
• Kuppusamy Ashok
• Lilleby Bjørnstein

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q10/10 Primary

  Office automation; Time management · CPC title

• G06F16/24575

  using context · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/24578

  using ranking · CPC title