Abstract: One disclosed example method includes a video conference provider establishing a main meeting of a video conference and multiple associated sub-meetings at the request of a host client device associated with a host of the meeting. The method further includes the video conference provider determining that a self-selection mode for the sub-meetings is enabled and transmitting notifications to participant client devices associated with the participants of the meeting. Each notification identifies a list of sub-meetings from which a participant can select a sub-meeting to join. The method further includes the video conference provider receiving and forwarding a request from a participant client device to connect to a selected sub-meeting, and receiving an automatic approval from the host client device. The video conference provider further connects the participant client device to the selected sub-meeting.

Abstract: One example method for mediating participant interactions during a video webinar meeting includes establishing a video webinar meeting; admitting a host and a plurality of participants to the video webinar meeting; not distributing audio streams from the plurality of participants to other participants in the video webinar meeting; receiving, from a first participant, a first submission to be posed during the video webinar meeting; determining a priority for the first submission based on one or more parameters; and distributing an audio stream associated with the first participant to the host and the remaining plurality of participants based on the priority to enable the first participant to pose the first submission.

Abstract: Systems and methods for capturing actions of local participants and conveying those actions to remote participants in a virtual conference are provided. A virtual conference device connects to one or more client devices associated with one or more remote participants in a virtual conference. The virtual conference device is also connected with one or more user devices associated with one or more local participants within a common area. The virtual conference device receives sensor data related to a local participant associated with a user device within the common area during the video conference. The virtual conference device determines a physical action of the local participant associated with the user device at least based on the sensor data. The virtual conference device provides a representation of the physical action to the one or more client devices associated with the one or more remote participants.

Abstract: Provided herein are systems and methods for delta models for providing privatized speech-to-text during virtual meetings. In one embodiment, a system may include a non-transitory computer-readable medium; a communications interface; and a processor. The processor may be configured to execute processor-executable instructions to: join a virtual meeting. Each participant in the virtual meeting may exchange audio streams with other participants in the virtual meeting. The instructions may include receiving, from a video conference provider, a local model for speech recognition. The local model may be a copy of a centralized model. The instructions may include performing speech recognition using the local model on the audio streams.

Abstract: One example method includes receiving, from a first client device, a request to join a video conference, the video conference having a main meeting, creating, in response to the request, a sub-meeting associated with the main meeting, connecting the first client device to the sub-meeting, connecting a host client device to the sub-meeting simultaneously with the host client device being connected to the main meeting, the host client device associated with a host of the main meeting, receiving first multimedia content from the first client device, and providing the first multimedia content to the host client device.

Abstract: Systems and methods for aggregation and distribution of diverse multimedia feeds are provided herein. In an aspect, a method including establishing, by a video conference provider, a virtual meeting having a plurality of participants is provided. Each participant joined to the virtual meeting may use a respective client device to exchange one or more audio or video streams via the virtual meeting. The method may also include receiving, from a first client device, a request to share a multimedia stream from an external source with one or more of the client devices during the virtual meeting. Responsive to the request, the method may include receiving a connection to the multimedia stream from the external source and transmitting, by the video conference provider, the multimedia stream from the external source to the one or more client devices via the virtual meeting.

Abstract: Systems and methods of message filtering in a multi-region multi-active architecture are provided. A client device receives a data message, the data message comprising a region tag and an account tag. The client device determines whether the region tag corresponds to a region server assigned to serve the client device. In response to determining the region tag corresponds to the region server assigned to serve the client device, the client device determines whether an account identification (ID) associated with the client device matches the account tag of the data message. In response to determining the account ID matches the account tag, the client device consumes the data message.

Abstract: One method for multimodal meeting segmentation includes receiving a meeting recording and a transcript, the meeting recording comprising a first media stream; generating, using a trained machine learning (“ML”) model, a first set of embeddings corresponding to the first media stream and a second set of embeddings corresponding to the transcript; generating a first set of segments based on the first set of embeddings and a second set of segments based on the second set of embeddings; generating a final set of segments based on the first and second sets of segments; and associating the final set of segments with the meeting recording and storing the final set of segments.

Abstract: Example methods and systems for automatic task generation is provided. A communication platform receives an instruction to generate one or more task items associated with a virtual communication session related to a user. The communication platform accesses virtual communication data associated with the virtual communication session. The communication platform generates a task item based on the virtual communication data using a generative artificial intelligence (AI) model. The communication platform provides the task item to the user.

Abstract: System and methods for running conference applications before, during, and after a network conference. In an embodiment, a method is provided for running a conference application before joining a network conference. The method includes activating a client application, selecting a conference application from a plurality of conference applications, running the conference application from the client application before joining a network conference, and joining the network conference using the client application.

Abstract: Example methods and systems provide automatic audio equalization for online conferences. A target, ideal, audio frequency response for use in online conferencing audio can be designed and preset for reference, and the equalizer can operate in real time to reach the target frequency response for any input. The equalizer can selectively apply per-band equalization to the audio signal as needed to adjust an energy value for each of multiple frequency bands to produce an output audio signal that that can be, as an example, routed through meeting servers or other infrastructure to other conference participants. The equalization can compensate for conditions local to a speaker that would otherwise adversely affect audio quality.

Abstract: One example method includes executing a video conference application at a client device; determining, at the client device, based on one or more of a plurality of real time performance measures or a user input, the presence of a fault associated with a currently-active video conference executed in the video conference application, and determining, at the client device by the video conference application, a plurality of potential causes of the fault based at least in part on the plurality of real time performance measures. The example method further includes providing, at the client device by the video conference application, a notification of the presence of the fault to the user, and generating, at the client device by the video conference application, a list of potential actions to alleviate the fault in real time, the list of potential actions based at least in part on the plurality of potential causes of the fault.

Abstract: Systems and methods for providing a communication portal including an information space provided during a video conference are disclosed. In an example method, a computing system receives, from a first client device, a request to create a communication portal including one or more information spaces, each information space being filterable by category and including one or more information cards, each information card associated with one or more categories. The computing system receives a first indication to create a first information space associated with a first category. The computing system receives first information to be posted as a first information card within the first information space, in which the first information is related to the category. The computing system receives, from a second client device, a second indication to access the information space. The computing system provides the first information card to the second client device.

Abstract: Example methods and systems for automatic suggestion and generation of meeting schedules are provided. A communication platform accesses virtual interaction data associated with a virtual interaction. The communication platform detects a meeting intent based on the virtual interaction data. The communication platform also predicts multiple meeting attendees, determines one or more meeting times, and generates a meeting title based on the virtual interaction data and other related data. The communication platform provides a meeting schedule suggestion to a participant in the virtual interaction. The meeting schedule suggestion includes the meeting title, identifications of the multiple attendees, and the one or more meeting times.

Abstract: One example method includes receiving, by a virtual assistant, a task from a remote client device; transmitting a first prompt to a large language model (“LLM”), the first prompt comprising the task and a request to process the task; receiving, from the LLM in response to the first prompt, a plurality of sub-tasks and an ordering of the plurality of sub-tasks; obtaining descriptions of a plurality of available services; for each sub-task: transmitting a second prompt to the LLM, the second prompt comprising a description of the respective sub-task and the descriptions of the available services; receiving, from the LLM in response to the respective second prompt, an identification of one or more available services; and initiating, for the respective sub-task, the one or more identified available services; and after completion of the plurality of sub-tasks, generating and providing a response to the task to the remote client device.

Abstract: A client device may receive a meeting link for a meeting hosted by a video conference provider. The meeting link may include information associated with a suggested application. In response to a selection of the meeting link, the client device may join the meeting via the video conference provider utilizing a video conference application and execute the suggested application. The suggested application may be controlled by the client device from the video conference application. The client device may receive application content from a meeting participant via the video conference provider and display the application content using the suggested application.

Abstract: Techniques may include receiving a first set of video streams having available video streams for a videoconference. Each of the video streams in the first set of video streams may be provided to a videoconferencing service by a respective client device. In addition, the techniques may include receiving one or more settings for one or more video streams of a second set of video streams, the one or more settings indicating one or more video feed properties. The techniques may include producing the second set of video streams from the first set of video streams, where each video stream of the second set of video streams is produced by changing a video stream of the first set of video streams according to the one or more video feed properties. Moreover, the techniques may include outputting one or more video streams of the second set of video streams.

Abstract: System and methods for associating conference application content with an instance of a network conference. In an embodiment, a method is provided for associating conference application content with an instance of a network conference. The method includes activating a client application, selecting a conference application from a plurality of conference applications, running the conference application from the client application, attaching content from the conference application to an instance of a network conference to generate a conference invitation, and transmitting the conference invitation a network server.

Abstract: One example method for virtual expo booth previews includes joining a virtual expo hosted by a video conference provider, the virtual expo including a plurality of virtual expo booths; presenting a graphical representation of the virtual expo and one or more virtual expo booths of the plurality of virtual expo booths; receiving an input indicating a first expo booth of the plurality of virtual expo booths; receiving, from the video conference provider, one or more multimedia streams associated with the first virtual expo booth; and presenting the one or more multimedia streams.