Content collaboration platform with an entity card interface and cross-product topic-based data structures

Patent metadata

Field	Value
Publication number	US-12530659-B2
Application number	US-202418759503-A
Country	US
Kind code	B2
Filing date	Jun 28, 2024
Priority date	Jun 28, 2024
Publication date	Jan 20, 2026
Grant date	Jan 20, 2026

Abstract

Embodiments described herein relate to systems and methods for generating and displaying content for an entity card interface of a collaboration platform. The entity card interface may be displayed in response to a natural language input or inquiry of a search interface or the entity card interface may also be displayed in response to a user selection of text or a designated object within user-generated content of an editor. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and/or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

First claim

What is claimed is:

1 . A computer-implemented method for providing an entity card interface in a content collaboration platform, the method comprising:
subsequent to a successful authentication of a user of a client device, causing display of a graphical user interface of a frontend application of the content collaboration platform on the client device, the graphical user interface including an editor region configured to receive user-generated content for a content item managed by the content collaboration platform; selecting a set of documents associated with an event history log that satisfies an authoritative criteria; extracting text snippets from the set of documents and determine a vector representation for each extracted text snippet; defining a set of multiple clusters of text snippets satisfying a clustering criteria based on the vector representation; extracting a set of representative keywords for a particular cluster of text snippets of the set of multiple clusters of text snippets; generating a prompt comprising the set of representative keywords and predetermined prompt text including a topic query portion; obtaining a generative response from a generative output engine using the generated prompt; analyzing the generative response to obtain a topic text string associated with the set of representative keywords; analyzing the particular cluster of text snippets to identify at least one system user and a set of content items associated with the particular cluster of text snippets; parsing the user-generated content displayed in the graphical user interface for occurrences of text matching a keyword of the set of representative keywords; replacing the matching text with a selectable object, selection of the selectable object causes display of an entity card interface including a first selectable card element corresponding to at least one topic text string, a second selectable card element corresponding to the at least one system user, and a third selectable card element corresponding to the content item of the set of content items associated with the particular cluster of text snippets.

2 . The computer-implemented method of claim 1 , wherein:
analyzing the particular cluster of text snippets further comprises identifying an external content item hosted by an external platform; the entity card interface further comprises a fourth selectable card element corresponding to the external content item; and selection of the fourth selectable card element causes the graphical user interface to be redirected to a view of the external content item on the external platform.

3 . The computer-implemented method of claim 2 , further comprising:
prior to causing display of the entity card interface, causing an authentication of the user with respect to the external platform; in response to an unsuccessful authentication with respect to the external platform, suppressing display of the fourth selectable card element on the entity card interface; and in response to a successful authentication with respect to the external platform, causing display of the fourth selectable card element on the entity card interface.

4 . The computer-implemented method of claim 1 , wherein:
the at least one system user is selected based on an association score computed with respect to the particular cluster of text snippets; and the association score increases in response to increased content creation events with respect to the particular cluster of text snippets.

5 . The computer-implemented method of claim 1 , wherein:
the clustering criteria includes a similarity threshold; defining the set of multiple clusters of text snippets includes performing a similarity analysis on respective vector representations for respective extracted text snippets; and a respective cluster of text snippets is defined based on respective text snippets having a similarity at or above the similarity threshold.

6 . The computer-implemented method of claim 1 , wherein:
the event history log includes comment events; content view events; content share events; and content edit events; and the set of documents are selected based on a number of occurrences the comment events; the content view events; the content share events; and the content edit events.

7 . The computer-implemented method of claim 1 , wherein:
the first selectable card element is selectable to cause redirection to a detailed view of the at least one topic text string; and the detailed view including a list of content items, system user profiles, and keywords associated with the at least one topic text string.

8 . The computer-implemented method of claim 1 , wherein:
the second selectable card element is selectable to cause redirection to a user profile of the at least one system user; and the third selectable card element is selectable to cause redirection to view of the content item of the set of content items associated with the particular cluster of text snippets.

9 . A computer-implemented method for providing a generative answer interface in a content collaboration platform, the method comprising:
causing display of a graphical user interface of a frontend application of the content collaboration platform on a client device, the graphical user interface including an editor region configured to receive user-generated content for a content item managed by the content collaboration platform; in response to a natural language input provided to a search input field of the graphical user interface, analyzing the natural language input to determine an action intent; in response to the action intent corresponding to a request for content items:
submitting a first query to the content collaboration platform for first content items corresponding to the natural language input;
submitting a second query to a separate platform for second content items corresponding to the natural language input; and
causing display of a first response including first query results obtained in response to the first query and second query results obtained in response to the second query;
in response to the action intent corresponding to an interrogatory:
conducting a search of the first content items to extract a set of text blocks each text block satisfying a correlation criteria with respect to the natural language input;
generating a prompt comprising the set of text blocks and predefined query prompt text and providing the prompt to a generative output engine; and
causing display of a generative response produced using a response from the generative output engine; and
in response to the action intent corresponding to a request for an entity:
submitting a third query to an entity service using an entity portion extracted from the natural language input;
identifying a set of content items from the content collaboration platform and the separate platform corresponding to the entity portion; and
causing display of an entity card interface including content obtained using the third query and one or more content items of the set of content items corresponding to the entity portion.

10 . The computer-implemented method of claim 9 , wherein:
the entity card interface further comprises a selectable card element associated with a topic text string; the topic text string is generated by:
selecting a set of documents having an event history log that satisfies an authoritative criteria;
extracting text snippets from the set of documents and defining a set of multiple clusters of text snippets satisfying a clustering criteria;
extracting a set of representative keywords for a particular cluster of text snippets of the set of multiple clusters of tex

Assignees

• Atlassian Pty Ltd

Inventors

• Kolambkar Navin
• Wang Zhaohui
• Shevchenko Yulia
• Kohout Isabelle Jana
• Bhosale Aniket
• Law Stacey
• Huynh Victoria
• Sims Geoff
• Cuenca-Cruz Helena

Classifications

• G06F40/30

  Semantic analysis · CPC title

• G06F40/279 Primary

  Recognition of textual entities · CPC title

• G06F40/205

  Parsing · CPC title

• G06F16/355

  Creation or modification of classes or clusters · CPC title

• G06F21/31

  User authentication · CPC title