Techniques for feature engineering pipeline generation for machine learning using decoupled dataset analysis and interpretation are described. A feature engineering engine obtains a dataset and utilizes a number of analyzers to generate data facts associated with the columnar values of the dataset. The data facts are consolidated together as a set of data statements that are used by multiple interpretation engines that implement different strategies for treating the data in order to generate feature engineering pipeline code.

The present disclosure provides a conference device, a method of controlling the conference device, and a computer storage medium. The conference device includes a display, an image sensor, a holographic projector, and a controller configured to identify, by using an image data from the image sensor, a modification action performed at a target location for a holographic image projected by the holographic projector, modify holographic projection data based on the modification action, and convert modified holographic projection data into modified two-dimensional imaging data.

The present disclosure provides a conference device, a method of controlling the conference device, and a computer storage medium. The conference device includes a display, an image sensor, a holographic projector, and a controller configured to identify, by using an image data from the image sensor, a modification action performed at a target location for a holographic image projected by the holographic projector, modify holographic projection data based on the modification action, and convert modified holographic projection data into modified two-dimensional imaging data.

The technology disclosed herein enables narration of occurrences in a telecommunications soft client operating in a GUI-less mode. In a particular embodiment, a method includes, in a user system, operating the telecommunications soft client in a first mode. In the first mode, the user system does not present a GUI to a user for the telecommunications soft client. A screen reader application is also executing on the user system. While in the first mode, the method includes audibly describing a first occurrence for the telecommunications soft client and receiving global user input into the telecommunications soft client. The screen reader application describes a second occurrence for a first application executing, and displaying an application window, on the user system.

The technology disclosed herein enables narration of occurrences in a telecommunications soft client operating in a GUI-less mode. In a particular embodiment, a method includes, in a user system, operating the telecommunications soft client in a first mode. In the first mode, the user system does not present a GUI to a user for the telecommunications soft client. A screen reader application is also executing on the user system. While in the first mode, the method includes audibly describing a first occurrence for the telecommunications soft client and receiving global user input into the telecommunications soft client. The screen reader application describes a second occurrence for a first application executing, and displaying an application window, on the user system.

Techniques for image-based search using touch controls are described. An apparatus may comprise: a processor circuit; a gesture component operative on the processor circuit to receive gesture information from a touch-sensitive screen displaying an image and generate a selection area corresponding to the gesture information; a capture component operative on the processor circuit to extract an image portion of the image corresponding to the selection area; and a search component operative on the processor circuit to perform an image-based search using the extracted image portion. Other embodiments are described and claimed.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for evaluating interactions with a user interface of an application are disclosed. In one aspect, a method includes, for each of a plurality of different user sessions of a native application, accessing frame bundles that each include data representing content presented by a frame of a user interface of the native application at a given time. Each frame bundle includes at least a portion of a view tree of the native application used to generate the user interface at the given time and data specifying content presented by each view of the portion of the view tree. Based on the frame bundles, playback data are generated that present visual changes of the user interface corresponding to changes to the view trees.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for evaluating interactions with a user interface of an application are disclosed. In one aspect, a method includes, for each of a plurality of different user sessions of a native application, accessing frame bundles that each include data representing content presented by a frame of a user interface of the native application at a given time. Each frame bundle includes at least a portion of a view tree of the native application used to generate the user interface at the given time and data specifying content presented by each view of the portion of the view tree. Based on the frame bundles, playback data are generated that present visual changes of the user interface corresponding to changes to the view trees.

A method for controlling a display device that includes a touch screen is provided. The method includes establishing a plurality of window display spaces in the touch screen, wherein each of the plurality of window display spaces displays a window for running an application, displaying a launcher application in one of the plurality of window display spaces, the launcher application presenting at least one icon to run at least one application, receiving in the launcher application a new application run command to run a new application, and displaying a new window for running the new application in one of the other window display spaces than the window display space where the launcher application is displayed, in response to the new application run command.

A touch sensor system includes touch sensors, drive-sense circuits (DSCs), memory, and a processing module. A DSC drives a first signal via a single line coupling to a touch sensor and simultaneously senses, when present, a second signal that is uniquely associated with a user. The DSC processes the first signal and/or the second signal to generate a digital signal that is representative of an electrical characteristic of the touch sensor. The processing module executes operational instructions (stored in the memory) to process the digital signal to detect interaction of the user with the touch sensor and to determine whether the interaction of the user with the touch sensor compares favorably with authorization. When not authorized, the processing module aborts execution of operation(s) associated with the interaction of the user with the touch sensor. Alternatively, when authorized, the processing module facilitates execution of the operation(s).