Abstract: A server identifies, by parsing through code of an online page associated with a contact center system, information related to offerings associated with the online page. The server identifies a set of intents based on the information, at least a portion of the set of intents corresponding to at least one of headers or menu items of the online page. The server updates the set of intents based on supplemental information accessible via a hyperlink from the online page. The server transmits the updated set of intents to a first user device. The server receives an acceptance of a subset of the updated set of intents from the first user device. The server stores, in an intent data repository, the accepted subset of the updated set of intents.

Abstract: A conference system enables a communication session between two or more participants. During the communication session, a participant device displays a visual code that is scanned by the device in which the identity is unknown. Based on the scan of the visual code, the conference system transfers the communication session such that it is continued between the device in which the identity is unknown and the one or more devices of the remaining participants of the conference.

Abstract: Respective devices of conference participants are connected to a conference hosted by a conferencing server. Respective commands are transmitted to the respective devices to initiate distributed recording. Subsequent to a termination of the conference, respective high-resolution media files are received from the respective devices. At least a subset of the respective high-resolution media files are composited into a high-resolution output media file. Subsequent to the termination of the conference, respective audio media files and/or screen content media file corresponding to at least the subset of the respective high-resolution media files may also be received.

Abstract: The present teachings provide a method and device of virtually sharing physical contents across multiple sessions. The teachings provide retrieving, from a data store, virtual whiteboard content derived from a first whiteboard session. The virtual whiteboard content includes first physical data from a physical surface, first virtual data from a virtual whiteboard, first metadata corresponding to one or both of the first virtual data or the first physical data. The virtual content is categorized based on the first metadata. The categorized virtual content is transmitted as an image stream according to the retrieved virtual whiteboard content to a client device in a location of the physical surface to cause the image stream to be presented on the physical surface or a second physical surface during a second whiteboard session. The data store is updated with second content elements obtained from the physical surface during the second whiteboard session.

Abstract: System and methods for transmitting conference application content during a network conference. In an embodiment, a method is provided for transmitting conference application content during a network conference. The method includes participating in a network conference using a client application, selecting a conference application from a plurality of conference applications, and running the conference application from the client application during the network conference. The method also includes identifying application content from the conference application, and transmitting the application content and a conference application identifier to attendees of the network conference.

Abstract: A sentiment-based score is determined for a contact center engagement between a first contact center service operator and a contact center user. The sentiment-based score is indicated within a graphical user interface displaying information associated with multiple contact center engagements at a device of a second contact center service operator. Based on a request to participate in the contact center engagement received from the device of the second contact center service operator via the graphical user interface, information associated with the contact center engagement is transmitted to the device of the second contact center service operator, and a contact center session involving a device of the contact center user and the device of the second contact center service operator is established.

Abstract: A conferencing system transmits a graphical output associated with a conference that is in progress to a client device for display without requiring the client device to connect to the conference. Prior to the client device connecting to the conference, the conferencing system grants the client device access to an in-conference communication application based on a request to communicate with a participant device. The conferencing system receives a chat message from the client device via the in-conference communication application. The conferencing system updates a topic of the conference based on the chat message.

Abstract: Respective video streams of participants of a video conference are received. A first video stream of the respective video streams is determined to be unstitchable into a unified stream of the video conference. A request for a stitching image is transmitted to a participant of the participants corresponding to the first video stream. The stitching image is received from the participant. The first video stream is stitched into the unified stream by stitching the first video stream with at least one other video stream of the respective video streams. The unified stream is transmitted for display at a device connected to the video conference.

Abstract: A server transmits a query received from a user device to multiple deployment engines, each deployment engine being associated with an intent. The server receives, from each of a subset of the multiple deployment engines, a score representing a likelihood that the query matches to the associated intent. The server transmits, to the user device, a message comprising representations of intents for which the score is within a predefined range.

Abstract: Access to functionality of a software service is enabled at a first device associated with a user based on the first device being in a primary mode. A connection may thereafter be established between the software service and a second device associated with the same user. In response to that connection, access to a subset of the functionality of the software service is limited at the second device based on the second device being in a secondary mode determined based on the second device. Because the first device and the second device are used by the same user, the software service does not represent those devices as separate users of the software service, but rather identifies only the first device, as the primary mode device, in connection with the user to other users of the software service.

Abstract: A machine transmits a message to one or more client devices indicated in a destination tag of the message to configure the one or more client devices to display the message. The machine determines that a client device of the one or more client devices is not connected to a local network that includes a computing node configured to create a message pipe. The machine creates the message pipe from a server to the client device upon the client device joining a video conference in response to determining that the client device is not connected to the local network. The message pipe transmits the message to the client device upon a latter of the client device joining the video conference or accessing the message at the server.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media provide for the intelligent configuration of personal endpoint devices for video communication. The system identifies, within a room, a personal endpoint device to be used in a video communication session, then authenticates the personal endpoint device. The system then performs one or more diagnostic operations to receive diagnostic output from the personal endpoint device. The system processes the diagnostic output to determine a unique broadcasting signature of the room, and determines whether an existing optimal settings configuration of the personal endpoint device can be detected for the room. If an optimal settings configuration is detected, the setup dynamically configures one or more parameters of the personal endpoint device to match the optimal settings configuration. If not, then the system determines a new optimal settings configuration and stores it for future video communication in the room.

Abstract: For online audio/video conferencing applications deployed in an open office environment, using shared conference devices, it can be advantageous to define an acoustic fence. A non-participant audio received from outside the acoustic fence can be considered noise and filtered out before transmission of an audio signal to a far end recipient. Three suppression stages are used to filter the non-participant audio. The first suppression stage uses beamformers for suppression. The second suppression stage is mask-based, and the third suppression stage is reference-based. The three suppression stages filter out non-participant audio signals, having a wide range of frequencies.

Abstract: A recording of a call is authenticated using a distributed transaction ledger. A call between two or more participants is recorded to generate a call recording. A record of the call recording is stored within a distributed transaction ledger. At a later time, such as in response to an access request for auditing or an authentication request, the call recording is authenticated based on information associated with the record within the distributed transaction ledger. An indication of the authentication is then output, such as for further processing or display.

Abstract: Systems and methods for identification of a client device location during an emergency are provided herein. In an example, a method includes receiving, by a video conference provider, a request to initiate an emergency beacon and determining, by the video conference provider, a first client device associated with the request. The method may also include activating, by the video conference provider, the emergency beacon for the first client device and establishing, by the video conference provider, a virtual session based on the emergency beacon. The method may also include joining, by the video conference provider, the first client device to the virtual session without input from the first client device and transmitting, by the video conference provider, a request to join an authorized device to the virtual session.

Abstract: The accuracy of automatic speech recognition (ASR) tasks is improved using trained models. A speech recognition model is applied in a noisy environment where speech is spoken at a distance from the microphones. The techniques may include extracting speech features, data augmentation by adding feature perturbation, and/or a multi-domain end-to-end speech recognition model. In some implementations, the described technology includes using a teacher-group knowledge distillation strategy to train a deep end-to-end speech recognition model on original speech samples and the sample speech augmentation of the original speech samples, that outputs recognized text transcriptions corresponding to speech detected in the original speech samples and the sample speech augmentation.

Abstract: A conference system transmits a first graphical output for display on a panel interface associated with a conference. Prior to the client device joining the conference, the conference system determines participant information based on a request. The conference system transmits a second graphical output to the client device to display the participant information without the client device having to join the conference.

Abstract: Audio, video conferencing with a dynamic, configurable mesh network is disclosed. A mesh reliability variable can condition the design of the mesh network between a high resiliency mode and a bandwidth saving mode. Artificial intelligence techniques and ranking techniques are provided to design the mesh network and determine which client machines are to act as parent nodes and/or child nodes. A Media Distribution Server (MDS) can provide the audio, video conference stream to the assigned parent nodes in the mesh network. The parent nodes can provide the stream to one or more child nodes over the local area network, conserving the external bandwidth of a recipient of the audio, video conference stream.

Abstract: Methods and systems provide for user-prompted group actions in a shared space hosted by a communication platform. In one embodiment, the system detects, by a processing device within a space, a client device within the space, the client device being associated with a participant of a current communication session; receives, at the processing device, a user input corresponding to the client device, the user input indicating a change in function for the current communication session; correlates, at the processing device, the user input with one or more additional user inputs corresponding to other client devices within the space; and applies the change in function based on the correlation to modify one or more aspects of the communication session.

Abstract: Automatic spotlighting of participant video feeds in a video conference are based on one or more triggers detected in the participant video feeds. Participant video feeds are added to a spotlight video queue. The participant video feeds are elevated to an active spotlight status based on certain criteria. The participant video feeds that are elevated to the active spotlight status are displayed adjacent to a host video feed on a display.