Abstract: Various embodiments are provided for providing intelligent dialog re-elicitation in a dialog system in a computing environment by a processor. Information, provided during a dialog using the dialog system, may be detected that has been subsequently revised. One or more variables impacted by the revised information provided during the dialog may be dynamically re-elicited.

Abstract: A communication server facilitates a video call between client devices of a plurality of participants. During the video call, the communication server identifies an in-call activity to recommend to the plurality of participants in the video call based on user information. The in-call activity is selected to be relevant to each of the plurality of participants and jointly recommended to the plurality of participants of the video call. To identify the recommended in-call activity, the communication server may determine common interests among the plurality of participants and select an in-call activity that is associated with the common interests. After the recommended in-call activity is selected, an indication of the recommended in-call activity is provided to the client devices to enable the client devices to display a user interface including the in-call activity to the participants during the video call.

Abstract: Embodiments of the present disclosure relate to generation of natural language expression variants. In an embodiment, a computer-implemented method is disclosed. According to the method, a structured expression is determined for a source expression in a natural language by replacing a source key entity in the source expression with a predetermined symbol. At least one template structured expression is selected from a set of template structured expressions based on respective similarities between the structured expression and respective template structured expressions in the set. Each of the set of template structured expressions comprises the predetermined symbol to represent a key entity. At least one variant expression is generated for the source expression by replacing the predetermined symbol in the at least one selected template structured expression with the source key entity. In other embodiments, a system and a computer program product are disclosed.

Abstract: The present disclosure provides a method and device for waking up a voice recognition function in a mobile terminal. The method includes: receiving a trigger instruction of an input interface, and activating the input interface; acquiring a rotation angle of the mobile terminal in a first rotation direction with an x-axis as a rotation axis, in which the x-axis is a widthwise direction of a screen of the mobile terminal; and activating the voice recognition function when the rotation angle of the mobile terminal in the first rotation direction with the x-axis as the rotation axis is greater than or equal to a first trigger threshold.

Abstract: A system, method and program product that provides a conversational AI platform using a declarative graph model. A system is included having a natural language (NL) interface the receives NL user inputs from a message queue; an intent analyzer that determines an intent of a received NL user input and loads a graph associated with the intent; and a graph traversal manager having traversal logic to first traverse the graph first along a start path from an intent node to a dialog node, then traverse an ask path to a question node to obtain missing entity data, then traverse a contacts path to a service node to execute an external service and return a fulfillment response based on submitted entity data, then traverse a replies with path to a response node to create a formatted fulfillment response that is forwarded to the message queue.

Abstract: A communication system and method for displaying text captions corresponding to voice communications between an assisted user's mobile wireless device and a separate hearing user's device includes at least one communication component configured to enable the appliance to communicate with a relay, a display, and a processor operably coupled to the at least one communication component and the display. The processor is configured to enable the assisted user to establish an association between the appliance and the mobile device, receive text originating at the relay, the text corresponding to a transcript of the hearing user's voice signal originating at the hearing user's device, and cause text captions corresponding to the received text to be displayed on the display.

Abstract: In one general aspect, a computer-implemented method includes identifying current choices with different verbosity levels for a current turn in a conversation; normalizing multi-dimensional verbosity vectors for each of the current choices to obtain a normalized value for each of the current choices; determining a state definition for the current turn in the conversation, utilizing the normalized values for each of the current choices; providing the state definition for the current turn in the conversation and the normalized values for each of the current choices to a trained reinforcement learning module; receiving, from the trained reinforcement learning module, a score associated with each of the current choices for the current turn in the conversation; and selecting one of the current choices to be entered for the current turn in the conversation, based on the score associated with each of the current choices for the current turn in the conversation.

Abstract: Systems and methods provide a notification of a connectivity problem of a video doorbell to a smartphone. A first communication link between the video doorbell and a backend server is determined unavailable, such as when a password used by the video doorbell to access a local area network (LAN) is not accepted by the LAN. A Bluetooth transceiver of the video doorbell is activated and a Bluetooth signal transmitted from the smartphone is detected. A second communication link between the video doorbell and the smartphone via the Bluetooth transceiver is established and a message is sent to the smartphone, via the Bluetooth transceiver, indicating that the password used by the video doorbell to access the LAN is not accepted by the LAN. The message causes an application running on the smartphone to display a notification on a display of the smartphone indicating the communication problem.

Abstract: A method and system for sending messages in a telecommunications network, in which digital messages which contain information on the desired reply address are mass sent, and messages, which are sent on the basis of the reply-address information are received. The reply-address information of each mass-sent message is converted to correspond to a predefined dialogue, in which the stage of the dialogue defines unequivocally the reply-address information, so that the transmission and reception of the messages are implemented in different parts of the telecommunications system.

Abstract: A mechanism is provided to implement a text classifier training augmentation mechanism for incorporating unlabeled data into the generation of a text classifier. For each term of a plurality of terms in each document of a plurality of documents in a set of unlabeled data, a term frequency value is determined. The term is normalized by dividing the term frequency value by a total number of terms in the document. An inverse document frequency (idf) value is determined for each term based on the term frequency value. A subset of terms is filtered from the plurality of terms based the determined idf values. The idf values for the remaining terms are transformed into feature weights. Terms from a set of labeled data are re-weighted based on the feature weights determined from the set of unlabeled data. The text classifier is then generated using the re-weighted labeled data.

Abstract: One variation of a method for video conferencing includes, during a setup period: accessing a test video feed; and generating a face model, representing facial characteristics of a first user depicted in the test video feed, based on features detected in the test video feed. The method also includes, during an operating period: accessing a video feed; representing constellations of facial landmarks, detected in frames in the video feed, in a feed of facial landmark containers; representing sets of facial muscle actions, detected in frames in the video feed, in a feed of facial expression containers; and transforming the feed of facial landmark containers, the feed of facial expression containers, and the face model into a feed of synthetic face images according to the synthetic face generator.

Abstract: A device implementing a system for multiway audio-video conferencing includes a processor configured to receive, from a first device, indication of a first channel and a second channel for communicating content for an audio-video conference session. The first channel and the second channel correspond to different types of communication interfaces. The processor is further configured to receive, from the first device, a first request to subscribe to a first content stream for the audio-video conference session via the first channel, and to subscribe to a second content stream for the audio-video conference session via the second channel, and in response to receiving the first request, forward, to the first device, the first content stream via the first channel.

Abstract: Embodiments of a fax system with adaptive protocol selection, and methods for such a system, are disclosed herein. Embodiments of a fax system may be adapted to selectively configure the protocol (both the type of protocol or aspects of a particular protocol) used in association with the transmission or reception of a specific fax. The configuration of the protocol utilized can be based on one or more attributes associated with a sender or a destination. The fax can then be transmitted or received according to those configuration parameters.

Abstract: An electronic apparatus according to an embodiment includes an input receiver configured to receive a user input; a voice receiver configured to receive a voice command; a processor configured to control to, based on a user input corresponding to an execution of a certain function of the electronic apparatus being received instead of an utterance of a first voice command corresponding to the execution of the certain function, carry out the certain function and carry out a guide operation for the utterance of the first voice command.

Abstract: The present invention relates to a method and a system for capping incoming transactions in inbound stateful conversations established between a client and a plurality of conversation servers of a service integrator. For each client, a group of conversation servers is allocated to handle the inbound stateful conversations initiated. Each conversation server in the group broadcasts a local traffic value periodically to the other conversation servers in the group. Each conversation server in the group calculates a transaction capping limit based on a client global transaction capping limit and the broadcasted local traffic values from the other conversation servers in the group. Each conversation server limits the rate of incoming transactions received by the client when exceeding the local transaction capping limit.

Abstract: A system and a method for monitoring a video communication device configured to monitor an activation state of a video capturing module are provided. A detection circuit is configured to detect an operation current input to the video capturing module. A control circuit is electrically connected to the detection circuit and determines whether the video capturing module is activated according to a magnitude of the operation current.

Abstract: Aspects of the subject disclosure may include, for example, an assessment of a context associated with a conference, an identification of an object associated with the conference in accordance with the context, and a presentation of the object as part of the conference. The conference may include a videoconference and the object may include a physical object, a virtual object, or a combination thereof. Other embodiments are disclosed.

Abstract: Methods, systems, and apparatuses are described for context-based speech processing. A current context may be determined. A subset of trigger words or phrases may be selected, from a plurality of trigger words, as trigger words that a computing device is configured to recognize in the determined current context. The computing device may be controlled to listen for only the subset of trigger words during speech recognition.

Abstract: A device for obtaining, storing and displaying information from a remote server, the device has a modem for establishing communication sessions with the remote server. A memory coupled to the modem stores the obtained information, and a display is coupled to the memory for displaying the stored information. The device automatically and periodically communicates with the remote server for obtaining the information.

Abstract: A method of operating a telepresence device is disclosed, which includes capturing images of a local subject using a plurality of cameras to generate a plurality of local captured images. Remote subject point of view (POV) data is received from a remote device. A plurality of tiles is selected from the plurality of local captured images based on the remote subject POV data. Local image data is sent to the remote device. The local image data includes the plurality of selected tiles.