Abstract:
An electronic device is provided. The electronic device includes a touch sensor, a processor, and a memory. The processor may determine a touch input from a user as at least one of a force-touch input or a long-touch input, based on received touch data, determine whether a result of determining the touch data matches an intention of the user, store data that does not match the intention of the user as a result of determination among the touch data in the memory, and determine a type of an artificial intelligence (AI)-based pre-learning model to be used in the electronic device, based on touch input accuracy and the data that does not match the intention of the user.
Abstract:
An electronic apparatus and controlling method thereof is provided. The electronic apparatus includes a processor configured to, based on receipt of a command to execute an application, execute the application based on the boosting level information, based on a difference between a loading time according to the application being executed and a reference loading time being equal to or greater than a threshold value, identify another boosting level information of the electronic apparatus based on the reference loading time, and update the stored boosting level information to the identified other boosting level information.
Abstract:
An electronic apparatus is provided. The electronic apparatus includes a communication interface, a memory storing log data with respect to external devices connected to the electronic apparatus, and a processor configured to identify a plurality of external devices having a history of being connected to the same internet protocol (IP) based on the log data, acquire, based on the log data, a first feature vector with respect to a relationship between the plurality of external devices and a second feature vector with respect to each of the plurality of external devices, acquire a graph of the relationship between the plurality of external devices based on the first feature vector and the second feature vector, and define at least one group configured by the plurality of external devices based on the graph.
Abstract:
Disclosed herein is a method of operating an electronic device having a camera. The electronic device includes a camera, a display unit, a sensor unit configured to detect an external event value, an image processor configured to process data received through the camera into a preview image, and a main processor. The main processor is configured to switch from a preview mode to a ready mode when the external event value is detected by the sensor unit, wherein the preview mode comprises activation of the camera, the image processor to display the preview image on the display unit, and the ready mode comprises deactivation of the camera and the image processor and display of a ready mode image on the display unit.
Abstract:
According to various embodiments, an electronic device includes a memory storing deep learning models for determining a force touch, a touchscreen, and a processor configured to identify a touch input of a user through the touchscreen, receive touch pixel data for frames having a time difference based on the touch input, and identify whether the touch input is a force touch based on the touch pixel data. The processor is configured to identify whether the touch input is the force touch using a first determination model among the deep learning models in response to identifying that the touch input is reinputted a designated first number of times or more within a designated time, and otherwise, identify whether the touch input is the force touch using a determination model having a lower computation load than the first determination model among the deep learning models.
Abstract:
An example electronic device according to various embodiments may include a fingerprint sensor, a touch sensor, a memory storing at least one instruction, and a processor operatively connected to the fingerprint sensor, the touch sensor, and the memory. The processor may determine whether a touch input is generated in a fingerprint recognition area in which a fingerprint sensor is disposed using a touch sensor, may determine whether the generated touch input continues for a given time or more, may generate first data by accumulating the touch input generated based on the touch input continuing for the given time or more, may determine whether an inputted fingerprint corresponds to a registered fingerprint of a registered user by analyzing the touch input in the fingerprint recognition area, using the fingerprint sensor, may analyze the first data using a first AI model based on the inputted fingerprint corresponding to the fingerprint of a registered user, may analyze the first data using a second AI model based on the inputted fingerprint not corresponding to the fingerprint of a registered user, may identify a form of the touch input based on analysis of the first data, and may perform a function corresponding to the identified form of the touch input and/or executing a user interface corresponding to the identified form of the touch input.
Abstract:
An electronic device is provided. The electronic device includes a memory, and a processor including a resource management unit and a neural processing unit. The processor may be configured to obtain an execution request for a specific function operating based on a specific neural network model, identify an available bandwidth of the memory through the resource management unit, and quantize the specific neural network model based on the available bandwidth of the memory through the neural processing unit.
Abstract:
An electronic device and control method for selecting a scaler based on image characteristics are provided. The electronic device includes at least one processor, a display, and a plurality of scalers including a first scaler and a second scaler. The at least one processor generates a first temporary upscaling image of an image by using an algorithm of the first scaler and generate a second temporary up scaling image of the image by using an algorithm of the second scaler. The at least one processor identifies a difference value of a pixel between the first temporary upscaling image and the second temporary upscaling image. The at least one processor selects one scaler based on the identified difference value and a preconfigured threshold value. The at least one processor upscales the image and controls the display to display the upscaled image.
Abstract:
According to certain embodiments, an electronic device comprises: a processor and memory storing instructions; and wherein the instructions, when executed by the processor, further cause the electronic device to: load and compile an artificial intelligence model stored in the memory; determine whether the compiled artificial intelligence model includes a first-type activation function; when the first-type activation function is included in the compiled artificial intelligence model, skip a calculation with respect to a designated value when the designated value exists in a feature map and calculate a value to be calculated subsequent to the designated value; and when the first-type activation function is not included in the compiled artificial intelligence model, perform a calculation with respect to input values of the feature map.
Abstract:
According to various embodiments, an electronic device includes a memory storing deep learning models for determining a force touch, a touchscreen, and a processor configured to identify a touch input of a user through the touchscreen, receive touch pixel data for frames having a time difference based on the touch input, and identify whether the touch input is a force touch based on the touch pixel data. The processor is configured to identify whether the touch input is the force touch using a first determination model among the deep learning models in response to identifying that the touch input is reinputted a designated first number of times or more within a designated time, and otherwise, identify whether the touch input is the force touch using a determination model having a lower computation load than the first determination model among the deep learning models.