System and graphical user interface for generating document space recommendations for an event feed of a content collaboration platform

Patent metadata

Field	Value
Publication number	US-11748431-B2
Application number	US-202217957718-A
Country	US
Kind code	B2
Filing date	Sep 30, 2022
Priority date	Dec 23, 2021
Publication date	Sep 5, 2023
Grant date	Sep 5, 2023

Abstract

A method for recommending feed sources in an event feed includes generating an event feed comprising a plurality of feed items associated with a user. The event feed includes a recommendation feed item comprising one or more feed item sources, which may include a document space not currently followed by the user. The method further includes causing at least a portion of the event feed to be displayed to the user in the event feed. In accordance with a determination that the user is viewing a graphical user interface associated with a first software application, the recommendation feed item includes feed item sources associated with the first software application. In accordance with a determination that the user is viewing a graphical user interface associated with a second software application different from the first, the recommendation feed item includes feed item sources associated with the second software application.

First claim

What is claimed is:

1. A computer-implemented method for recommending feed sources in an event feed, the computer-implemented method comprising:
at an event feed service in communication with a collaborative document system:
generating an event feed comprising a plurality of feed items associated with a first user, including:
generating a first feed item associated with a user-generated document being followed by the first user, the user-generated document stored by the collaborative document system;
generating a second feed item associated with a second user followed by the first user; and
generating a recommendation feed item comprising one or more feed item sources not being followed by the first user, the recommendation feed item including a recommendation to follow a recommended document space managed by the collaborative document system, the recommended document space selected from a group of multiple document spaces managed by the collaborative document system based on a user-to-space classifier computed based on past interactions between the user and the recommended document space, the each space of the group of multiple document spaces comprising:
a set of documents having a first hierarchical relationship to each other defined by a document tree;
a set of blog posts having a second hierarchical relationship to each other defined by a blog tree; and
a space administrator identifying a user account for the recommended space, the user account granted permission to determine a set of permissions for the set of documents and the set of blog posts with respect to users of the collaborative document system.

2. The computer-implemented method of claim 1 , wherein:
the collaborative document system is configured to cause display of the event feed in a graphical user interface on a client device;
the first feed item is displayed as a first tile in the graphical user interface;
the second feed item is displayed as a second tile in the graphical user interface; and
the recommendation feed item is displayed as a third tile in the graphical user interface, the third tile includes a space recommendation card that corresponds to the recommended document space; and
in response to a user selection of the space recommendation card, the event feed service is configured to generate space-based feed items in response to selected events occurring with respect to the recommended space.

3. The computer-implemented method of claim 2 , wherein the selected events include:
an addition of a calendar item to the recommended space;
an addition of an administrator to the recommended space; and
an update to a document of the set of documents of the recommended space.

4. The computer-implemented method of claim 1 , wherein:
the user-to-space classifier is based, at least in part, on an event vector comprising a set of vector elements comprising:
a first vector element corresponding to a number of pages created by the user within the recommended space;
a second vector element corresponding to a number of updates performed to the set of documents of the recommended space by the user;
a third vector element corresponding to a number of mentions of the user within the recommended space; and
a fourth vector element corresponding to a number of pages viewed by the user within the recommended space over a threshold amount of viewing time.

5. The computer-implemented method of claim 4 , wherein:
the user-to-space classifier is based, at least in part, on weighted event vector which is computed by weighting each vector element of the event vector;
the weighted event vector comprises:
a first weighted element determined by applying a first weight factor to the first vector element of the event vector;
a second weighted element determined by applying a second weight factor to the second vector element of the event vector;
a third weighted element determined by applying a third weight factor to the third vector element of the event vector; and
a fourth weighted element determined by applying a fourth weight factor to the fourth vector element of the event vector.

6. The method of claim 5 , wherein:
the first weight factor is greater than the second, third and fourth weight factors; and
the second weight factor is greater than the third and fourth weight factors.

7. The computer-implemented method of claim 1 , wherein:
the recommended document space is selected based on an output from a recommendation model; and
the user-to-space classifier is provided to the recommendation model as an input.

8. The computer-implemented method of claim 7 , wherein:
the recommendation model is trained using a training set comprising:
a first data set comprising a set of user-to-space classifiers;
a second data set comprising a set of document spaces, each user-to-space classifier of the set of user-to space classifiers correspond to a respective document space of the set of document spaces.

9. A computer-implemented method of generating a recommended feed item for an event feed, the computer-implemented method comprising:
determine a first user-to-space classifier for a first user account and a first document space, the first user-to-space classifier based on a first set of user interaction events with respect to the first user account and the first document space;
determine a second user-to-space classifier for the first user account and a second document space, the second user-to-space classifier based on a second set of user interactions events with respect to a second user account and the second document space;
in response to the first user-to-space classifier satisfying a classifier criteria, generate a first recommendation feed item including a recommendation to follow the first document space;
in response to the second user-to-space classifier satisfying the classifier criteria, generate a second recommendation feed item including a recommendation to follow the second document space;
at an event feed service in communication with a collaborative document system, generate the event feed comprising a plurality of feed items including:
a first feed item associated with a first user-generated document being followed by the first user account;
a second feed item associated with the second user account followed by the first user account; and
a recommendation feed item comprising one or more of the first recommendation feed item or the second recommendation feed item;

cause display of the event feed in a graphical user interface of a client device associated with the first user account.

10. The computer-implemented method of claim 9 , wherein:
the event feed service is in communication with an issue tracking system that is separate from the collaborative document system; and
the plurality of feed items further comprises a third feed item associated with an issue being followed by the first user account, the issue associated with an issue ticket in the issue tracking system.

11. The computer-implemented method of claim 9 , wherein:
the first user-to-space classifier is based, at least in part, on an event vector comprising a set of vector elements comprising:
a first vector element corresponding to a number of pages created by the first user account within the first document space; and
a second vector element corresponding to a number of updates performed to a set of documents of the first document space by the first user account.

12. The computer-implemented method of claim 9 , wherein:
the first user-to-space classifier is based, at least in part, on weighted event vector which is computed by weighting each vector element of the event vector;
the

Assignees

• Atlassian Pty Ltd
• Atlassian Us Inc

Inventors

• Saha Rudra
• Katta Swati
• Jetmundsen Henry
• Dasdan Ali
• Clipsham Timothy
• Nagy Balazs
• Cao Shawn

Classifications

• G06F16/9538 Primary

  Presentation of query results · CPC title

• G06F16/93 Primary

  Document management systems · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/9536

  Search customisation based on social or collaborative filtering · CPC title

• H04N21/25891

  being end-user preferences (retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18) · CPC title