Abstract: This document relates to creating and/or updating a chatbot using a graphical user interface. For example, training dialogs for a chatbot can be displayed in a tree form on a graphical user interface. Based at least on interactions between a developer and the graphical user interface, the training dialogs can be modified in the tree form, and training dialogs can be updated based on the modifications provided on the tree form via the graphical user interface.

Abstract: The present disclosure provides a method, device, computer apparatus, and storage medium for training recognition model and recognizing fundus features. The method includes: obtaining a color fundus image sample associated with a label value, inputting the color fundus image sample into a preset recognition model containing initial parameters; extracting a red channel image; inputting the red channel image into the first convolutional neural network to obtain a first recognition result and a feature image of the red channel image; combining the color fundus image sample with the feature image to generate a combined image, and inputting the combined image into the second convolutional neural network to obtain a second recognition result; obtaining a total loss value through a loss function, and when the total loss value is less than or equal to a preset loss threshold, ending the training of the preset recognition model.

Abstract: A graph database for outbreak tracking and management is disclosed. In an example embodiment, an outbreak management system includes a memory device storing instructions that define a graph database for disease outbreak tracking. The instructions specify for a given host that a host node is created and an episode node is connected to the host node via a ‘case’ link. The episode node is associated with episode parameters that are related to a disease classification of the host. In addition, the instructions specify that an outbreak node is connected to the episode node via a ‘part of’ link to indicate that the host has become part of an outbreak of the disease. The outbreak node is connected to a definition node via a ‘defined as’ link. The definition node specifies disease parameters of the disease that is related to the outbreak node.

Abstract: A tracking system for quantifying retinal traction on a retina of a patient eye includes an indicator device, a stereo camera, and an electronic control unit (ECU). The stereo camera collects and outputs stereo image data. The ECU, which is in communication with the indicator device, executes a method by receiving the stereo image data from the stereo camera during an ophthalmic procedure and thereafter assigning tracking points as coinciding pixels within stereo image pairs. The ECU also automatically performs a digital image correlation (DIC) process using the stereo image pairs to ascertain relative motion of the tracking points, and associates relative motion of the tracking points with the retinal traction using a traction map. A numeric traction quotient is generated that is indicative of magnitude of retinal traction. The ECU executes a control action using the indicator device based on the numeric traction quotient.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for customizing digital content tutorials for a user within a digital editing application based on user experience with editing tools. The disclosed system determines proficiency levels for a plurality of different portions of a digital content tutorial corresponding to a digital content editing task. The disclosed system generates tool proficiency scores associated with the user in a digital editing application in connection with the portions of the digital content tutorial. Specifically, the disclosed system generates the tool proficiency scores based on usage of tools corresponding to the portions. Additionally, the disclosed system generates a mapping for the user based on the tool proficiency scores associated with the user and the proficiency levels of the portions of the digital content tutorial. The disclosed system provides a customized digital content tutorial for display at a client device according to the mapping.

Abstract: A method for quantitative magnetic resonance imaging (MRI) includes [800] performing an MRI scan using a conventional pulse sequence to obtain a qualitative MR image; and [802] applying the qualitative MR image as input to a deep convolutional neural network (CNN) to produce a quantitative magnetic resonance (MR) relaxation parametric map. The qualitative MR image is the only image input to the deep neural network to produce the quantitative MR relaxation parametric map. The conventional pulse sequence may be a Spoiled Gradient Echo sequence, a Fast Spin Echo sequence, a Steady-State Free Precession sequence, or other sequence that is commonly used in current clinical practice.

Abstract: Embodiments herein describe an automated process for identifying tasks that can be converted from primarily being driven by a human agent into bot-driven RPAs. This disclosure describes techniques for automatically generating RPAs by monitoring the actions of the agent and identifying corresponding events. These events can be performed on unstructured data sources and structured data sources. The events are clustered into different tasks where pattern detection techniques are used to identify common (or overlapping) events and causal relationships between the events. Using these causal relationships, the system can map events performed on unstructured data sources to events performed on structured data source. The system can then generate respective bot-RPAs for the tasks. The system can monitor, in real-time, data received from unstructured and/or structured data sources and when it identifies data for one of the bot-RPAs, automatically execute the RPA to perform the task.

Abstract: To facilitate use of a vast help content, while a modeling application is running, user interface actions to the modeling application are monitored, at least for an automatic help. When it is detected that consecutive user interface actions fulfill at least one of a plurality of predefined criteria for automatic help, help content is retrieved from online helping information. The online helping information comprises at least helping information of the modeling application and helping information created by a user community. In the retrieving of the help content at least a portion of the consecutive user interface actions are used.

Abstract: A network node of a collaboration system is provided to establish communication with other network nodes. The network node comprises a display having a physical display space. The network node can store collaboration data and render on the local client screen space a local client canvas having locations in the virtual workspace. The network node includes logic to provide a user interface to display a list of markers representing predefined canvases in both the virtual workspace and another virtual workspace. The predefined canvases defining (i) respective areas in the virtual workspace having a location and (ii) an area in the other virtual workspace having a location. The network node includes logic to respond to an input indicating a selected marker from the list of displayed markers to update the location of the local client canvas to match the location of the predefined canvas represented by the selected marker.

Abstract: The present disclosure provides a method and system to perform integration and monitoring of one or more intelligent conversational agents. The system creates an online chatbot marketplace to enable one or more vendors to upload the one or more intelligent conversational agents. The system integrates the one or more intelligent conversational agents to generate a mega bot in real-time. The system generates the mega bot based on integration of the one or more intelligent conversational agents. The system collects a first set of data. The system receives one or more queries from a plurality of users for the mega bot. The system selects a suitable intelligent conversational agent having a trust score above a threshold level based on a plurality of factors and the first set of data. The system creates a primary response for the one or more queries at the mega bot.

Abstract: Interface and mode selection for digital action execution is provided. For example, a system loads a script library embedded in an electronic resource. The system determines a historic level of engagement between a client computing device and one or more digital assistants. The system selects, based on a first property of the client computing device and the historic level of engagement, a type of digital interface. The system generates, based on the type of digital interface, a digital interface with the call-to-action. The system determines, responsive to an instruction to execute the call-to-action, a mode of execution. The system selects a digital assistant and a second client device to execute the call-to-action. The system transmits the call-to-action to the second client device for execution.

Abstract: A system and method for creating custom music/video messages to facilitate and/or improve social interaction. The music/video messages may include at least portions of: music, video, pictures, slideshows, and/or text. Custom music/video messages may be created by a user in communication with a music/video provider and a music/video messaging system. The music/video messaging system and/or a distribution network send the music/video messages to one or more intended recipient(s). The custom music/video messages are representative of feelings or emotions to be communicated by the user to the one or more recipient(s).

Abstract: Various methods and systems for providing a user interface (UI) generation system for processing UI generation data based on a multi-layer architecture and hierarchically interrelated and supervised scene processes are provided. The UI generation system supports generating UIs based on a scene layer, a viewport layer, and a driver layer that each use protocols and data structures to support UI generation, UI fault recovery operations, and distributed UI generation for UI viewing devices. In operation, scene configuration data is communicated to a viewport engine from a scene engine, the viewport engine uses the scene configuration data to construct a scene management data structure that is defined based on hierarchically arranging and supervising different scene processes. The scene management data structure is used to define scene rendering data that is accessed by a driver engine to cause generation of UI display content, locally or remotely based on the scene rendering data.

Abstract: Informational system for a mobility vehicle, comprising an automotive user interface configured to allow a driver and other occupants of the mobility vehicle to interact with the informational system; and automotive storage and processing resources designed to cooperate with the automotive user interface to implement an informational functionality designed to provide the driver of the mobility vehicle with notifications aimed at promoting learning of features of the mobility vehicle. The automotive storage and processing resources are further designed to monitor exploitation of features of the mobility vehicle, and to suggest to the driver exploitation of those features of the mobility vehicle that are seldom exploited or completely unexploited by the driver.

Abstract: Semantic zoom techniques are described. In one or more implementations, techniques are described that may be utilized by a user to navigate to content of interest. These techniques may also include a variety of different features, such as to support semantic swaps and zooming “in” and “out.” These techniques may also include a variety of different input features, such as to support gestures, cursor-control device, and keyboard inputs. A variety of other features are also supported as further described in the detailed description and figures.

Abstract: A personal digital assistant for supporting inspection of at least one device disposed in an inspection target area includes: an abnormality acquisition unit configured to acquire information about an abnormality in the at least one device; a guidance information storage unit configured to store guidance information which at least includes at least one response procedure for each abnormal event in the at least one device and information about response capability required to execute the at least one response procedure; and a display unit configured to refer to the guidance information stored in the guidance information storage unit, and display the guidance information for responding to an abnormal device which is the device where the abnormality is acquired by the abnormality acquisition unit.

Abstract: According to an exemplary embodiment of the present disclosure, disclosed is a computer program stored in a computer readable storage medium. When the computer program is executed by one or more processors of a computing device, the computer program provides a user interface (UI) to display design information, and the user interface may include: a design group generation layer for generating a design group, and the design group generation layer includes one or more design file regions each of which are associated with a design file, and the design file region may include: a first sub region displaying a design image; and a second sub region displaying one or more design attribute objects, which allows user selection input for at least some of one or more design attributes included in the design file.

Abstract: In embodiments of multi-device pairing and combined display, mobile devices have device touchscreens, and housing bezels of the mobile devices can be positioned proximate each other to form a combined display from the respective device touchscreens. An input recognition system can recognize an input to initiate pairing the mobile devices, enabling a cross-screen display of an interface on the respective device touchscreens, such as with different parts of the interface displayed on different ones of the device touchscreens. The input to initiate pairing the mobile devices can be recognized as the proximity of the mobile devices, as a gesture input, as a sensor input, and/or as a voice-activated input to initiate the pairing of the mobile devices for the cross-screen display of the interface.

Abstract: A method for task mobilization may include a server receiving user inputs from a desktop application. A user input may correspond to a respective function performed by a user on the desktop application. A processor may identify the respective functions of the user inputs. Further, the method may include translating the respective functions into respective mobile view functions. Based on the respective mobile view functions, the processor may generate a mobile application and provide the mobile application to a mobile user device.

Abstract: There is a need for more effective and efficient data evaluation. This need can be addressed by, for example, techniques for data evaluation in accordance with a shared decision tree data object. In one example, a method includes generating, using a plurality of feature extraction threads, shared evidentiary data; generating, based on a selected shared evidentiary data subset of the shared evidentiary data that correspond to one or more selected nodes of the shared decision tree data object, refined evidentiary data; processing the refined evidentiary data in accordance with the shared decision tree data object to generate an evaluation output and an explanation output; and displaying an evaluation output user interface comprising user interface data describing the evaluation output and the explanation output.