Abstract: The present embodiments relate to metadata value-based mapping during a data load in a data integration job. A computing device can receive a first data set from a source system and computer-readable instructions to load data into a target system. The device can receive a first metadata set from the target system that describe destinations. The computing device can identify a first data value of the first data set that matches a metadata value of the first metadata set. The device can receive a data integration mapping of the second data value of the first data set to a data field associated with the matching metadata value of the first metadata set. The device can load the second data value of the first data set from the source system into the target system pursuant to the mapping and the computer-readable instructions.

Abstract: Methods and systems for analysis of a plurality of channels that provide a remote desktop session are described herein. Channel metrics for each of a plurality of communication channels may be received. Each of the plurality of communication channels may be configured to deliver, to a computing device and via a network, different aspects of a remote desktop session. A plurality of channel scores may be determined for each communication channel of the plurality of communication channels. Based on the plurality of channel scores, an aggregate score may be determined. Based on the aggregate score satisfying a threshold, a notification may be transmitted. For example, an indication of one or more executable scripts predicted to improve a performance of one or more of the plurality of communication channels may be transmitted.

Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.

Abstract: This disclosure describes systems and methods for improved transaction platforms. An example method may include receiving, by a processor and from a user, a selection of a first vehicle from a user interface. The example method may also include determining, by the processor and based on the first vehicle, a second vehicle. The example method may also include sending, by the processor, data associated with the first vehicle and data associated with the second vehicle to one or more entities. The example method may also include receiving, by the processor, first payment information for the first vehicle and second payment information for the second vehicle. The example method may also include determining, by the processor and based on the first payment information and the second payment information, third payment information for a third vehicle.

Abstract: Techniques for determining attributable data in a natural language user input that can be used to identify a specific user are described. A system may use various data signals determined using different components. The system may process the various signals to make a final determination on whether the input includes attributable data. The system may use a first component to detect user-identifiable data in the input. The system may use a second component to determine whether the input is potentially attributable to a particular user.

Abstract: An automated workflow process for integration of services with a data estate of an external entity. A plurality of application data models are obtained that are associated with of a plurality of applications on a cloud-based platform. A data model is obtained that corresponds to a collection of data to be processed. Mappings are determined between the data model and the plurality of application data models. A candidate application of the plurality of applications is identified for processing the collection of data based on the mappings. A communication suggesting the candidate application for processing the collection of data is sent to the external entity over one or more networks.

Abstract: A framework for enhanced search is provided to enable the user to contextually search documents, based on specified events. A management framework provides systems for obtaining a user's contextual data and the user's interaction data for which a Context Graph and an Interaction Graph are created, respectively. The user's context data include the various events associated with the user. The user's interaction data include times and locations the user interacted with a particular document, which device was used, the type of interaction, etc. The data from the two graphs are correlated and joined into an event graph. Upon receiving a natural language query from a user, one or more contextual query elements are identified, and the event graph is spanned to identify matching results which are then provided to the requesting user device.

Abstract: An ultrasound imaging system includes a thermally conductive frame and a number of electronic components and a display that are sealed within the frame. The frame further includes a plenum extending through the frame with surfaces that are thermally coupled to the electronic components and the display. An active cooling mechanism, such as one or more fans, moves air through the plenum to remove heat generated by the electronic components and display. The plenum is environmentally sealed so that moisture, dust, air or other contaminants drawn into the plenum do not contact the sealed electronic components and display in the frame.

Abstract: Described embodiments provide systems and methods for determining bounce-able machines. One or more processors can be coupled to memory. The one or more processors can identify data associated with a history of actions performed on a plurality of machines. The one or more processors can determine, using the data, a change in performance of the plurality of machines if a sequence of actions were applied to one or more of the plurality of machines. The one or more processors can select a machine of the plurality of machines based on at least on the change in performance of the machine satisfying a threshold. The one or more processors can initiate, responsive to the selection, the sequence of actions on the machine.

Abstract: An input buffer circuit includes a tracking circuit that produces a tracking signal and an inverter including a cascade of low voltage switching devices coupled to an output of the tracking circuit. The tracking signal follows a first signal during a first time period and a second signal during a second time period. The tracking circuit is configured to reduce an input high voltage/input low voltage (VIH/VIL) spread.

Abstract: Computing device state or activity based task reminders and automatic tracking of statuses of task-related activities are provided. Users are enabled to create reminders that are triggered based on a device state of the user’s device or activity signals from the operating system, an application, or a user file. The status of a task item can be inferred from signals collected from one or more sources. The signals provide information associated with tasks that the user performs in various life events. Machine learning, statistical analysis, behavioral analytics, and data mining techniques are applied to the signals, and the user’s activities are mapped to task items that the user has created. An inferred status of a task activity can be shared with other systems, or can be used for a variety of functions (e.g., to automatically update the user’s task list, or to remind the user of an uncompleted task item).

Abstract: An apparatus is provided for selecting an electronic calendar from a plurality of available electronic calendars for saving of an event for a user. The apparatus comprises a data storage storing user-specific inferences pertaining to the user; and a calendar suggestion module. The calendar suggestion module is configured to: apply semantic analysis to an indication of an event received at the apparatus; access the data storage to identify a user-specific inference that is relevant to the received event based on the semantic analysis; and using the relevant user-specific inference, select a calendar from the plurality of calendars to which the event should be stored. A corresponding method and computer program are also provided.

Abstract: Methods and systems are disclosed herein for using anomaly detection in timeseries data of user sentiment to detect incidents in computing systems and identify events within an enterprise. An anomaly detection system may receive social media messages that include a timestamp indicating when each message was published. The system may generate sentiment identifiers for the social media messages. The sentiment identifiers and timestamps associated with the social media messages may be used to generate a timeseries dataset for each type of sentiment identifier. The timeseries datasets may be input into an anomaly detection model to determine whether an anomaly has occurred. The system may retrieve textual data from the social media messages associated with the detected anomaly and may use the text to determine a computing system or event associated with the detected anomaly.

Abstract: Techniques for using a federated learning framework to update machine learning models for spoken language understanding (SLU) system are described. The system determines which labeled data is needed to update the models based on the models generating an undesired response to an input. The system identifies users to solicit labeled data from, and sends a request to a user device to speak an input. The device generates labeled data using the spoken input, and updates the on-device models using the spoken input and the labeled data. The updated model data is provided to the system to enable the system to update the system-level (global) models.

Abstract: A method for preventing a collision between a first object and a second object using a camera. The method includes capturing images of the first object and the second object using the camera, accessing a database of point clouds, and identify a first point cloud corresponding to the first object and a second point cloud corresponding to the second object within the database of point clouds, where the first point cloud corresponds to the first object being a person. The method further includes calculating a distance between the first object and the second object and comparing the distance to a threshold. The method further includes generating a notification when the distance is below the threshold.

Abstract: A transcription service may receive a request from a developer to build a custom speech-to-text model for a specific domain of speech. The custom speech-to-text model for the specific domain may replace a general speech-to-text model or add to a set of one or more speech-to-text models available for transcribing speech. The transcription service may receive a training data and instructions representing tasks. The transcription service may determine respective schedules for executing the instructions based at least in part on dependencies between the tasks. The transcription service may execute the instructions according to the respective schedules to train a speech-to-text model for a specific domain using the training data set. The transcription service may deploy the trained speech-to-text model as part of a network-accessible service for an end user to convert audio in the specific domain into texts.

Abstract: Computing device state or activity based task reminders and automatic tracking of statuses of task-related activities are provided. Users are enabled to create reminders that are triggered based on a device state of the user's device or activity signals from the operating system, an application, or a user file. The status of a task item can be inferred from signals collected from one or more sources. The signals provide information associated with tasks that the user performs in various life events. Machine learning, statistical analysis, behavioral analytics, and data mining techniques are applied to the signals, and the user's activities are mapped to task items that the user has created. An inferred status of a task activity can be shared with other systems, or can be used for a variety of functions (e.g., to automatically update the user's task list, or to remind the user of an uncompleted task item).

Abstract: Methods and systems for analysis of a plurality of channels that provide a remote desktop session are described herein. Channel metrics for each of a plurality of communication channels may be received. Each of the plurality of communication channels may be configured to deliver, to a computing device and via a network, different aspects of a remote desktop session. A plurality of channel scores may be determined for each communication channel of the plurality of communication channels. Based on the plurality of channel scores, an aggregate score may be determined. Based on the aggregate score satisfying a threshold, a notification may be transmitted. For example, an indication of one or more executable scripts predicted to improve a performance of one or more of the plurality of communication channels may be transmitted.

Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.