Chat channel management for a virtual conference service

1 . A method for managing messages within a virtual conference service comprising:

accessing, by a channel management service of the virtual conference service, a message in a database of the virtual conference service;

identifying, by the channel management service of the virtual conference service, one or more features of the message, wherein the one or more features of the message comprise a keyword and first information about a first user account associated with the message; and

for each chat channel of a plurality of chat channels:

identifying, by the channel management service of the virtual conference service, one or more features of a particular chat channel, wherein the one or more features of the particular chat channel comprise a second keyword and second information about a second user account associated with the particular chat channel; and

determining, by the channel management service of the virtual conference service, whether to classify the message as belonging to the particular chat channel based on the one or more features of the message and the one or more features of the particular chat channel;

assigning, by the channel management service of the virtual conference service, a channel score to each of the plurality of chat channels based on the classification;

determining, by the channel management service of the virtual conference service, an order for the plurality of chat channels, wherein the order is determined based on the channel score for each of the plurality of chat channels; and

presenting, via a graphical user interface of the virtual conference service, the plurality of chat channels in the order.

2 . The method of claim 1 , wherein classifying the message comprises:

for each chat channel:

providing, by the channel management service of the virtual conference service, the one or more identified features of the message and one or more features of the particular chat channel as input to a machine learning model;

receiving, by the channel management service of the virtual conference service, a message score as output from the machine learning model;

comparing, by the channel management service of the virtual conference service, the message score to a message threshold; and

classifying, by the channel management service of the virtual conference service, the message as belonging to the particular chat channel based on the message score exceeding the message threshold.

3 . The method of claim 1 , wherein classifying the message comprises: for each chat channel:

accessing, by the channel management service of the virtual conference service, a set of rules corresponding to the particular chat channel;

comparing, by the channel management service of the virtual conference service, the one or more features of the message and the one or more features of the particular chat channel to set of rules; and

classifying, by the channel management service of the virtual conference service, the message as belonging to the particular chat channel based on the comparing.

4 . The method of claim 1 , wherein the plurality of chat channels comprise one or more aggregated chat channels, wherein an aggregated chat channel includes at least one message that was initially sent in a direct chat channel.

5 . The method of claim 4 , wherein the direct chat channel comprises a sequential list of messages that were sent in the direct chat channel.

6 . The method of claim 4 , wherein a message sent in the direct chat channel is addressed to one or more user accounts associated with the direct chat channel.

7 . The method of claim 4 , wherein the direct chat channel is associated with at least two user accounts and the aggregated chat channel is associated with a single user account.

8 . A computing device, comprising:

one or more memories; and

one or more processors in communication with the one or more memories and configured to execute instructions stored in the one or more memories to perform operations comprising:

accessing a message in a database of a virtual conference service;

identifying one or more features of the message, wherein the one or more features of the message comprise a keyword and first information about a first user account associated with the message;

for each chat channel of a plurality of chat channels:

identifying one or more features of a particular chat channel, wherein the one or more features of the particular chat channel comprise a second keyword and second information about a second user account associated with the particular chat channel; and

classifying the message as belonging to the plurality of chat channels based on the one or more features of the message and the one or more features of the particular chat channel;

assigning a channel score to each of the plurality of chat channels based on the classification;

determining an order for the plurality of chat channels, wherein the order is determined based on the channel score for each of the plurality of chat channels; and

presenting the plurality of chat channels in the order.

9 . The device of claim 8 , wherein classifying the message comprises:

for each chat channel:

providing the one or more identified features of the message and one or more features of the particular chat channel as input to a machine learning model;

receiving a message score as output from the machine learning model;

comparing the message score to a message threshold; and

classifying the message as belonging to the particular chat channel based on the message score exceeding the message threshold.

10 . The device of claim 8 , wherein classifying the message comprises: for each chat channel:

accessing a set of rules corresponding to the particular chat channel;

comparing the one or more features of the message and the one or more features of the particular chat channel to set of rules; and

classifying the message as belonging to the particular chat channel based on the comparing.

11 . The device of claim 8 , wherein the plurality of chat channels comprise one or more aggregated chat channels, wherein an aggregated chat channel includes at least one message that was initially sent in a direct chat channel.

12 . The device of claim 11 , wherein the direct chat channel comprises a sequential list of messages that were sent in the direct chat channel.

13 . The device of claim 11 , wherein a message sent in the direct chat channel is addressed to one or more user accounts associated with the direct chat channel.

14 . The device of claim 11 , wherein the direct chat channel is associated with at least two user accounts and the aggregated chat channel is associated with a single user account.

15 . A non-transitory computer-readable medium storing a plurality of instructions that, when executed by one or more processors of a computing device, cause the one or more processors to perform operations comprising:

accessing a message in a database of a virtual conference service;

identifying one or more features of the message, wherein the one or more features of the message comprise a keyword and first information about a first user account associated with the message;

for each chat channel of a plurality of chat channels:

identifying one or more features of a particular chat channel, wherein the one or more features of the particular chat channel comprise a second keyword and second information about a second user account associated with the particular chat channel; and

classifying the message as belonging to the plurality of chat channels of the first user account or the second user account based on the one or more features of the message and the one or more features of the particular chat channel;

assigning a channel score to each of the plurality of chat channels based on the classification;

determining an order for the plurality of chat channels, wherein the order is determined based on the channel score for each of the plurality of chat channels; and

presenting the plurality of chat channels in the order.

16 . The medium of claim 15 , wherein classifying the message comprises: for each chat channel:

providing the one or more identified features of the message and one or more features of the particular chat channel as input to a machine learning model;

receiving a message score as output from the machine learning model;

comparing the message score to a message threshold; and

classifying the message as belonging to the particular chat channel based on the message score exceeding the message threshold.

17 . The medium of claim 15 , wherein classifying the message comprises: for each chat channel:

accessing a set of rules corresponding to the particular chat channel;

comparing the one or more features of the message and the one or more features of the particular chat channel to set of rules; and

classifying the message as belonging to the particular chat channel based on the comparing.

18 . The medium of claim 15 , wherein the plurality of chat channels comprise one or more aggregated chat channels, wherein an aggregated chat channel includes at least one message that was initially sent in a direct chat channel.

19 . The medium of claim 18 , wherein the direct chat channel comprises a sequential list of messages that were sent in the direct chat channel.

20 . The medium of claim 18 , wherein a message sent in the direct chat channel is addressed to one or more user accounts associated with the direct chat channel.