Abstract: A method for virtual meeting content sharing comprises, during a virtual meeting, receiving a request to share visual interface content including one or more visual content elements rendered by a client computing device with one or more remote participant devices. For each of the one or more visual content elements, an element feature vector is determined. Each of the one or more element feature vectors are sent to a remote meeting server. From the remote meeting server, an indication is received that a specified visual content element is flagged as potentially subject to filtering, based at least in part on a difference between (1) a meeting feature vector and (2) the element feature vector for the specified visual content exceeding a content filter threshold, the meeting feature vector quantifying a plurality of meeting context parameters of the virtual meeting.

Abstract: A method for one or more meeting-facilitating machines to provide access to a remote meeting comprises assessing a capability metric of a meeting-participant computer device; selecting an access-option set including a combination of mutually compatible access modes, each access mode characterized by (a) an expense metric comparable to the capability metric and (b) a richness metric indicating a relative level of richness the access mode contributes to the remote meeting, the access-option set selected to maximize a net richness of the remote meeting while preventing a net expense of the access-option set from exceeding the capability metric; and providing the meeting-participant computer device access to the remote meeting using the access-option set.

Abstract: A computer-implemented method for recalling user-specific interactions is disclosed. User-specific application data for each of a plurality of different computer application programs is received at a computing system. The user-specific application data is translated into different content vectors representing different user-specific interactions between a user and one or more other users while using the plurality of different computer application programs. Each content vector includes parameters quantifying interaction attributes of the corresponding user-specific interaction. The content vectors are mapped to a high-dimensional content space. A query is received at the computing system and translated into a query vector. Geometric mathematical operations are performed to compare content vectors in the high-dimensional content space to the query vector to identify a content vector that correlates to the query vector.

Abstract: An audio stream is subjected to speech-to-text processing in order to obtain a textual representation of the audio stream. Hierarchical topic extraction is performed on the textual representation to obtain a multi-level hierarchical topic representation of the textual representation. A user interface actuator is generated, which allows a user to search through the audio stream. Different levels of the multi-level hierarchical topic representation are displayed to the user, based upon the speed of actuation of the user interface actuator.

Abstract: A method for one or more meeting-facilitating machines to provide access to a remote meeting comprises assessing a capability metric of a meeting-participant computer device; selecting an access-option set including a combination of mutually compatible access modes, each access mode characterized by (a) an expense metric comparable to the capability metric and (b) a richness metric indicating a relative level of richness the access mode contributes to the remote meeting, the access-option set selected to maximize a net richness of the remote meeting while preventing a net expense of the access-option set from exceeding the capability metric; and providing the meeting-participant computer device access to the remote meeting using the access-option set.

Abstract: A computer-implemented method for automatically personalizing a computing experience to enhance user productivity within a computing environment is disclosed. One or more proficiency parameters and one or more workload parameters are provided to a machine learning model previously-trained to assess user-specific overload criteria based at least on the one or more proficiency parameters and the one or more workload parameters. A notification-generating event in the computing environment is recognized. A notification to the user is suppressed based at least on the notification-generating event satisfying the user-specific overload criteria. The notification is supplied to the user based at least on the notification-generating event failing to satisfy the user-specific overload criteria.

Abstract: A method for virtual meeting content sharing comprises, during a virtual meeting, receiving a request to share visual interface content including one or more visual content elements rendered by a client computing device with one or more remote participant devices. For each of the one or more visual content elements, an element feature vector is determined. Each of the one or more element feature vectors are sent to a remote meeting server. From the remote meeting server, an indication is received that a specified visual content element is flagged as potentially subject to filtering, based at least in part on a difference between (1) a meeting feature vector and (2) the element feature vector for the specified visual content exceeding a content filter threshold, the meeting feature vector quantifying a plurality of meeting context parameters of the virtual meeting.

Abstract: A computer-implemented conferencing method is disclosed. A conference session between a user and one or more other conference participants is initiated via a computer conference application. An attribute-specific pronunciation of the user's name is determined via one or more attribute-specific-pronunciation machine-learning models previously trained based at least on one or more attributes of the one or more other conference participants. The attribute-specific pronunciation of the user's name is compared to a preferred pronunciation of the user's name via computer-pronunciation-comparison logic. Based on the attribute-specific pronunciation of the user's name being inconsistent with the preferred pronunciation of the user's name, a pronunciation learning protocol is automatically executed to convey, via the computer conference application, the preferred pronunciation of the user's name to the one or more other conference participants.

Abstract: An intrusion detection system detects when an unexpected person enters the environment of a user who is in a meeting. A privacy protection action which is an action that is to be taken in response to the detected intrusion, is identified. Audio and/or video systems are then controlled to perform the privacy protection action. Machine learning can be used, based upon user interactions, to improve intrusion detection and other parts of the system.

Abstract: Computerized systems are provided for applying data indicative of a personal style to a feature of a user represented in one or more images based on determining or estimating the personal style. In operation, embodiments can receive a first image of a first user that indicates the personal style of the first user. The first image can then be fed to one or more machine learning models in order to learn and capture the personal style of the first user. Subsequently, some embodiments capture the first user in another image or set of images. Some embodiments can then detect one or more features of the first user in these other images and based on the determining of the user's personal style in the first image, can apply data indicative of the personal style of the first user to the one or more features of the user in these other images.

Abstract: A computer-implemented method for recalling user-specific interactions is disclosed. User-specific application data for each of a plurality of different computer application programs is received at a computing system. The user-specific application data is translated into different content vectors representing different user-specific interactions between a user and one or more other users while using the plurality of different computer application programs. Each content vector includes parameters quantifying interaction attributes of the corresponding user-specific interaction. The content vectors are mapped to a high-dimensional content space. A query is received at the computing system and translated into a query vector. Geometric mathematical operations are performed to compare content vectors in the high-dimensional content space to the query vector to identify a content vector that correlates to the query vector.

Abstract: A method and system for responding to a message directed to a recipient includes receiving the message including a query from a sender, receiving an indication that the recipient is unavailable to respond to the query, and providing the query to as an input to a machine-learning (ML) model to identify information requested in the query. The method further includes obtaining the information requested as an output from the ML model, determining if access to the information requested is available to the sender, based on a confidentiality group to which the sender belongs with respect to the information requested, upon determining that access to the information requested is available, generating a response to the query that includes the information requested, and providing the response to the sender. The confidentiality group to which the sender belongs may be determined based on a degree of association between the sender and the information requested.

Abstract: Computerized systems are provided for determining an identity of one or more users that use a same audio source, such as a microphone. The identity of one or more users that use a same audio source can based on generating a list of participant candidates who are likely to participate in an associated event, such as a meeting. For instance, embodiments can generate one or more network graphs of a meeting invitee any only voice input samples of the meeting invitee's N closest connections are compared to an utterance to determine the identity of the user associated with the utterance. One or more indicators that identify the users who are using the same audio source, as well as additional information or metadata associated with the identified user can be caused to be presented.

Abstract: An audio stream is subjected to speech-to-text processing in order to obtain a textual representation of the audio stream. Hierarchical topic extraction is performed on the textual representation to obtain a multi-level hierarchical topic representation of the textual representation. A user interface actuator is generated, which allows a user to search through the audio stream. Different levels of the multi-level hierarchical topic representation are displayed to the user, based upon the speed of actuation of the user interface actuator.

Abstract: A method and system for responding to a message directed to a recipient includes receiving the message including a query from a sender, receiving an indication that the recipient is unavailable to respond to the query, and providing the query to as an input to a machine-learning (ML) model to identify information requested in the query. The method further includes obtaining the information requested as an output from the ML model, determining if access to the information requested is available to the sender, based on a confidentiality group to which the sender belongs with respect to the information requested, upon determining that access to the information requested is available, generating a response to the query that includes the information requested, and providing the response to the sender. The confidentiality group to which the sender belongs may be determined based on a degree of association between the sender and the information requested.

Abstract: In the present disclosure, artificial intelligence (AI) processing is trained and leveraged to learn user-specific insights that are contextually relevant to a state of a user communication. Contextual information about a state of a user communication may be collected and analyzed. That contextual information may be cross-referenced with an extensive knowledge graph that is constructed from user context data. Exemplary AI processing may further be trained to apply a relevance analysis to assist with processing described herein including generation and curation of data insights that are most relevant to a state of a user communication. In some examples, the data insight generation process may be augmented by pre-generating data insights that may be relevant to a user communication prior to occurrence of the user communication. Further technical examples pertain to the rendering and presentation of representations of data insights through a graphical user interface (GUI).

Abstract: An audio stream is subjected to speech-to-text processing in order to obtain a textual representation of the audio stream. Hierarchical topic extraction is performed on the textual representation to obtain a multi-level hierarchical topic representation of the textual representation. A user interface actuator is generated, which allows a user to search through the audio stream. Different levels of the multi-level hierarchical topic representation are displayed to the user, based upon the speed of actuation of the user interface actuator.

Abstract: An intrusion detection system detects when an unexpected person enters the environment of a user who is in a meeting. A privacy protection action which is an action that is to be taken in response to the detected intrusion, is identified. Audio and/or video systems are then controlled to perform the privacy protection action. Machine learning can be used, based upon user interactions, to improve intrusion detection and other parts of the system.

Abstract: Computerized systems are provided for determining an identity of one or more users that use a same audio source, such as a microphone. The identity of one or more users that use a same audio source can based on generating a list of participant candidates who are likely to participate in an associated event, such as a meeting. For instance, embodiments can generate one or more network graphs of a meeting invitee any only voice input samples of the meeting invitee's N closest connections are compared to an utterance to determine the identity of the user associated with the utterance. One or more indicators that identify the users who are using the same audio source, as well as additional information or metadata associated with the identified user can be caused to be presented.

Abstract: In the present disclosure, artificial intelligence (AI) processing is trained and leveraged to learn user-specific insights that are contextually relevant to a state of a user communication. Contextual information about a state of a user communication may be collected and analyzed. That contextual information may be cross-referenced with an extensive knowledge graph that is constructed from user context data. Exemplary AI processing may further be trained to apply a relevance analysis to assist with processing described herein including generation and curation of data insights that are most relevant to a state of a user communication. In some examples, the data insight generation process may be augmented by pre-generating data insights that may be relevant to a user communication prior to occurrence of the user communication. Further technical examples pertain to the rendering and presentation of representations of data insights through a graphical user interface (GUI).