Context-based channel recommendation and management

Patent metadata

Field	Value
Publication number	US-2025379844-A1
Application number	US-202519310606-A
Country	US
Kind code	A1
Filing date	Aug 26, 2025
Priority date	Dec 20, 2023
Publication date	Dec 11, 2025
Grant date	—

Abstract

Example methods and systems for context-based channel recommendation and management are provided. A communication platform creates a user embedding representation for a user based on a set of user data associated with the user on a communication platform. The communication platform creates a plurality of channel embedding representations for a plurality of chat channels on the communication platform based on channel data associated with the plurality of chat channels. The communication platform determines a similarity score corresponding to each of the plurality of chat channels with respect to the user based on the user embedding representation and the plurality of channel embedding representations to obtain a plurality of similarity scores. The communication platform generates a recommendation of one or more chat channels to the user based on the plurality of similarity scores. The communication platform provides the recommendation of one or more chat channels to the user.

First claim

That which is claimed is:

1 . A method comprising:
creating a user embedding representation for a user based on a set of user data associated with the user on a communication platform; creating a plurality of channel embedding representations for a plurality of chat channels on the communication platform based on channel data associated with the plurality of chat channels; determining a similarity score corresponding to each of the plurality of chat channels with respect to the user based on the user embedding representation and the plurality of channel embedding representations to obtain a plurality of similarity scores; generating a recommendation of one or more chat channels to the user based on the plurality of similarity scores; and providing the recommendation of one or more chat channels to the user.

2 . The method of claim 1 , further comprising:
ranking the plurality of chat channels based on corresponding similarity scores to generate a ranked list of chat channels; and selecting the one or more chat channels from the ranked list of chat channels whose similarity scores are above a predetermined threshold to generate the recommendation.

3 . The method of claim 1 , further comprising:
updating the user embedding representation for the user based on an updated set of user data associated with the user to obtain an updated user embedding representation for the user; updating the plurality of channel embedding representations for the plurality of chat channels based on updated channel data associated with the plurality of chat channels to obtain a plurality of updated channel embedding representations; determining an updated similarity score corresponding to each of the plurality of chat channels with respect to the user based on the updated user embedding representation and the plurality of updated channel embedding representations to obtain a plurality of updated similarity scores; generating an updated recommendation of one or more chat channels to the user based on the plurality of updated similarity scores; and providing the updated recommendation of one or more chat channels to the user.

4 . The method of claim 1 , further comprising:
creating a plurality of user embedding representations for a plurality of other users; determining a user similarity score corresponding to each of the plurality of other users with respect to the user based on the user embedding representation and the plurality of user embedding representations to obtain a plurality of user similarity scores; selecting one or more other users whose corresponding user similarity scores are above a predetermined threshold; identifying one or more channels that the one or more other users actively participate in; and recommending the one or more channels to the user.

5 . The method of claim 1 , further comprising:
accessing a social graph representing relationships between the user and a plurality of other users on the communication platform based on the set of user data and a plurality of sets of user data associated with the plurality of other users; selecting one or more other users whom the user actively interacts with based on the social graph; identifying one or more channels that the one or more other users actively participate in; and recommending the one or more channels to the user.

6 . The method of claim 1 , further comprising:
determining an activity level for each of the plurality of chat channels based on an amount of chat messages and an amount of active users during a period of time; identifying one or more channels whose activity level is above a predetermined threshold; and recommending the one or more channels to the user.

7 . The method of claim 1 , further comprising:
generating a customized description for each recommended channel; and providing the recommendation of one or more chat channels and corresponding customized descriptions to the user.

8 . A system comprising:
a communications interface; a non-transitory computer-readable medium; and one or more processors communicatively coupled to the communications interface and the non-transitory computer-readable medium, the one or more processors configured to execute processor-executable instructions stored in the non-transitory computer-readable medium to: create a user embedding representation for a user based on a set of user data associated with the user on a communication platform; create a plurality of channel embedding representations for a plurality of chat channels on the communication platform based on channel data associated with the plurality of chat channels; determine a similarity score corresponding to each of the plurality of chat channels with respect to the user based on the user embedding representation and the plurality of channel embedding representations to obtain a plurality of similarity scores; generate a recommendation of one or more chat channels to the user based on the plurality of similarity scores; and provide the recommendation of one or more chat channels to the user.

9 . The system of claim 8 , wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to:
rank the plurality of chat channels based on corresponding similarity scores to generate a ranked list of chat channels; and select the one or more chat channels from the ranked list of chat channels whose similarity scores are above a predetermined threshold to generate the recommendation.

10 . The system of claim 8 , wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to:
update the user embedding representation for the user based on an updated set of user data associated with the user to obtain an updated user embedding representation for the user; update the plurality of channel embedding representations for the plurality of chat channels based on updated channel data associated with the plurality of chat channels to obtain a plurality of updated channel embedding representations; determine an updated similarity score corresponding to each of the plurality of chat channels with respect to the user based on the updated user embedding representation and the plurality of updated channel embedding representations to obtain a plurality of updated similarity scores; generate an updated recommendation of one or more chat channels to the user based on the plurality of updated similarity scores; and provide the updated recommendation of one or more chat channels to the user.

11 . The system of claim 8 , wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to:
create a plurality of user embedding representations for a plurality of other users; determine a user similarity score corresponding to each of the plurality of other users with respect to the user based on the user embedding representation and the plurality of user embedding representations to obtain a plurality of user similarity scores; select one or more other users whose corresponding user similarity scores are above a predetermined threshold; identify one or more channels that the one or more other users actively participate in; and recommend the one or more channels to the user.

12 . The system of claim 8 , wherein the one or more processors are configured to execute further processor-executable instructions stored in the non-transitory computer-readable medium to:
access a social graph repres

Assignees

• Zoom Communications Inc

Inventors

• Bulmer Bryan James
• Gervais Lisa Ann
• Han Lin
• Lu Ying
• Ni Kai
• Tai Longdong
• Tian Wang
• Zhang Yingying
• Zhao Huilian

Classifications

• H04L51/212

  using filtering or selective blocking · CPC title

• H04L51/52 Primary

  for supporting social networking services · CPC title

• H04L51/216 Primary

  Handling conversation history, e.g. grouping of messages in sessions or threads · CPC title