System and method for power saving in a user equipment

Abstract

A method for power-saving in a user equipment (UE). The method may include identifying user interface (UI) elements or regions of interest (ROIs) present on a display screen of the UE. The method may include obtaining a pixel map and generating a binary mask, based on mapping pixels in the pixel map with the identified at least one of UI elements or ROIs. Further, the method may include adjusting the brightness of pixels outside of the identified at least one of UI elements or the ROIs, thereby saving power in the UE using adaptive brightness.

Description

SYSTEM AND METHOD FOR POWER SAVING IN A USER EQUIPMENT

[0001] The present disclosure generally relates to power saving, and more particularly relates to a system and a method for power saving by adjusting pixels of a display screen in a user equipment.

[0002] Today's user equipment (UE), particularly smartphones and smart tablets may be infamous for their high energy consumption, a problem that plagues both consumers and device manufacturers alike. Regardless of the underlying display technology, the production of light within a display screen of the UE may stand out as the primary reason for this significant energy usage. For smartphones, this may translate directly into rapid battery drain, thus compromising their usability and lifespan.

[0003] In some related techniques for saving power, the UE may have predominantly revolved around the straightforward strategy of uniformly dimming the entire screen. This method, while somewhat effective in reducing energy consumption, may introduce a critical trade-off between power savings and display performance of the UE. For instance, when the screen brightness of the UE is lowered uniformly, the visibility and readability of the content appearing on the display screen across the entire display may be compromised. Thus, the technique of uniform brightness reduction may lack the sophistication needed to discern which parts of the screen are actively engaging the user and which parts are not.

[0004] The primary goal is to achieve significant power savings in UE without adversely affecting the user experience, however, the related power-saving techniques fall short because they do not consider the context in which the display is used. The related techniques may uniformly control the brightness, thereby affecting areas of the display screen that may be capturing the user's attention. Consequently, some essential features are relegated to low-power mode, leading to a subpar user experience.

[0005] Further, the uniform dimming of the brightness does not differentiate between areas of the display that are being actively viewed by the user and those that are not. For instance, when reading an article on the smartphone, the text is of primary importance, while the background and surrounding interface elements are less critical. However, the related power-saving techniques may dim all areas on the smartphone equally, which may strain the user's eyes and degrade the overall experience.

[0006] Therefore, there is a need for a new generation of power-saving techniques in the UE that aim to enhance user experience by adjusting the brightness of the display screen while preserving overall user experience.

[0007] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the disclosure. This summary is neither intended to identify key or essential inventive concepts of the disclosure nor is it intended for determining the scope of the disclosure.

[0008] According to one embodiment of the present disclosure, a method for power-saving in a user equipment (UE). According to one embodiment of the present disclosure, the method may include identifying at least one of, one or more UI elements or one or more regions of interest (ROIs) present on a display screen of the UE. According to one embodiment of the present disclosure, the method may include obtaining a pixel map corresponding to the identified at least one of the one or more UI elements or the one or more ROIs. According to one embodiment of the present disclosure, the method may include generating a binary mask, based on mapping pixels in the pixel map with the identified at least one of one or more UI elements or the one or more ROI. According to one embodiment of the present disclosure, the method may include adjusting a brightness of a plurality of pixels outside of the identified at least one of one or more UI elements or the one or more the ROIs, based on the binary mask using adaptive brightness.

[0009] According to one embodiment of the present disclosure, a system for power-saving in a user equipment (UE). According to one embodiment of the present disclosure, the system may include memory. According to one embodiment of the present disclosure, the system may include at least one processor in communication with the memory. The one or more processors may be configured to execute the instructions. According to one embodiment of the present disclosure, the system may include the at least one processor may be configured to identify at least one of, one or more UI elements or one or more regions of interest (ROIs) present on a display screen of the UE. According to one embodiment of the present disclosure, the system may include the at least one processor may be configured to obtain a pixel map corresponding to the identified at least one of the one or more UI elements or the one or more ROIs. According to one embodiment of the present disclosure, the system may include the at least one processor may be configured to generate a binary mask, based on mapping pixels in the pixel map with the identified at least one of one or more UI elements or the one or more ROI. According to one embodiment of the present disclosure, the system may include the at least one processor may be configured to adjust a brightness of a plurality of pixels outside of the identified at least one of one or more UI elements or the ROIs, based on the binary mask using adaptive brightness.

[0010] One embodiment provides a machine readable medium containing instructions. The instructions, when executed by at least one processor, may cause the at least one processor to perform the method corresponding.

[0011] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the disclosure and are therefore not to be considered limiting of its scope. The disclosure will be described and explained with additional specificity and detail in the accompanying drawings.

[0012] These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0013] Figure 1A-1B illustrates a schematic block diagram depicting an environment for the implementation of a system for power-saving, according to an embodiment of the present disclosure;

[0014] Figure 2 illustrates a schematic block diagram of modules components of the system for power-saving in the UE, according to an embodiment of the present disclosure;

[0015] Figure 3 illustrates a process flow associated with a display content module of the system, in accordance with various embodiments of the present disclosure;

[0016] Figure 4 illustrates a process flow associated with a binary mask-generating module of the system, in accordance with various embodiments of the present disclosure;

[0017] Figure 5 illustrates a process flow associated with an associating module of the system, in accordance with various embodiments of the present disclosure;

[0018] Figure 6A-6B illustrates an exemplary use-case scenario of the system, in accordance with various embodiments of the present disclosure; and

[0019] Figure 7 illustrates an exemplary process flow comprising a method for power-saving in the UE, according to an embodiment of the present disclosure.

[0020] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0021] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the various embodiments and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as illustrated therein being contemplated as would normally occur to one skilled in the art to which the disclosure relates.

[0022] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the disclosure and are not intended to be restrictive thereof.

[0023] Reference throughout this specification to "an aspect," "another aspect" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase "in an embodiment," "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0024] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises... a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

[0025] Figure 1A-1B illustrates a schematic block diagram depicting an environment for the implementation of a system for power-saving in a user equipment 102, according to an embodiment of the present disclosure.

[0026] In an embodiment, referring to Figure 1A-1B, the system may be implemented in the UE 102 via an application installed in the UE 102 and running on an operating system (OS) of the UE 102 that generally defines a first active user environment. The OS typically presents or displays the application through a graphical user interface ("GUI") of the OS. In an example, the UE 102 may be a laptop computer, a desktop computer, a Personal Computer (PC), a notebook, a smartphone, a tablet, a smartwatch, or any device capable of displaying electronic media.

[0027] In an embodiment, the UE 102 comprising of a display screen 104, presents one or more user interface (UI) elements 106 and a one or more regions of interest (ROIs) 108. In an example, the display screen 104 may be the primary output component of the UE 102, responsible for rendering all visual content to a user via a user interface. In an advantageous aspect, the display screen 104 may be designed to provide clear, high-resolution images and text, ensuring that users may easily interact with the UE 102. The display screen 104 may serve as an area on which the one or more UI elements 106 and the one or more ROIs 108 may be presented.

[0028] In an example, the one or more UI elements 106 are the interactive components that may allow the users to control and interact with the UE 102. For instance, icon, text, navigation bar, status bar, and buttons on the display screen 104 of the UE 102. In an advantageous aspect, the one or more UI elements 106 are designed to be intuitive and easy to use, thus ensuring that the users may navigate the UE 102 efficiently without extensive training or instructions.

[0029] In an example, the one or more ROIs 108 may refer to specific areas of the display screen 104 that hold particular significance or require special attention from the user. The ROIs 108 may be dynamically identified based on user interactions and contextual relevance. For instance, sections of the display screen 104 where important information is displayed, such as articles, messages, instructions, or any other pop-up window.

[0030] In an example scenario, referring to Figure 1A, the UE 102 may have an initial current consumption, for instance, the current consumption of 143.82 mAH, while presenting the one or more UI elements 106 and the one or more ROIs 108 on the display screen 104. In the example, the one or more UI elements 106 and the one or more ROIs 108 presented on the display screen 104 may be identified. In an example, the one or more UI elements 106 and the one or more ROIs 108 may be identified based on capturing an image of the display screen 104. The image capturing may be done periodically for instance by taking screenshots or continuously monitoring the screen content. Further, the captured image may be preprocessed for normalization by adjusting contrast and applying filters to enhance the clarity of the one or more UI elements 106 and the one or more ROIs 108. Thereafter, once the one or more UI elements 106 and / or the one or more ROIs 108 are identified, boundaries corresponding to the one or more UI elements 106 and / or the one or more ROIs 108 may be required to be defined.

[0031] Further, thus, pixel data or a pixel map may be extracted corresponding to the one or more UI elements 106 and / or the one or more ROIs 108. The pixel data may outline the exact position and size of each element or region on the display screen 104 based on defining boundaries around the one or more UI elements 106 and / or the one or more ROIs 108 using pixel coordinate information. Consequently, the pixel coordinate information captures the precise coordinates of pixels that forms the boundary of the one or more UI elements 106 and / or the one or more ROIs 108. For example, pixel coordinates are used to outline icons, text, navigation / status bars, buttons, and active / focused or non-active content windows on the display screen 104. Furthermore, in an example, various sensor data may be correlated with the pixel coordinates. For instance, touch sensors may provide real-time data on where the user is touching the display screen 104, thus, helping to identify active interaction zones. For instance, light sensors may measure ambient light conditions, thus, aiding in adjusting brightness appropriately.

[0032] Furthermore, in an embodiment, a binary mask is generated for pixels that maps to the one or more UI elements 106 and / or the one or more ROIs 108. The binary mask may correspond to a map that distinguishes between different areas of the display screen 104, thus allowing the system to apply selective brightness adjustments. In an example, pixels within the one or more UI elements 106 and / or the one or more ROIs 108 may be assigned a binary value, 0 and 1, for subsequent processing. In an example, the binary value of '1' may be assigned to pixels that are part of the one or more UI elements 106 and / or the one or more ROIs 108, while a value of '0' may be assigned to all other pixels. Thus the binary mask mapping creates differentiation between the important areas of the display screen 104 from less critical ones.

[0033] In an example, the binary mask may be generated using spatially adaptive convolution, which adjusts brightness values according to the pixel's position or coordinates relative to the one or more UI elements 106 and / or the one or more ROIs 108 and correlating the assigned binary value. Furthermore, the binary mask may be further refined based on touch sensor data indicating the user's interaction.

[0034] Furthermore, in an embodiment, the binary mask is used to selectively adjust the brightness of the display screen 104 as depicted in the Figure 1B. In an example, pixels within the one or more UI elements 106 and / or the one or more ROIs 108 (assigned the binary value as '1') are kept at a higher brightness level to ensure they remain visible and legible. Similarly, pixels outside the one or more UI elements 106 and / or the one or more ROIs 108 (assigned the binary value as '0') are dimmed to reduce power consumption of the UE 102. Consequently, the selective adjustment of brightness or dimming pixels based on the binary mask value helps conserve battery life without compromising the visibility of essential screen elements. In an advantageous aspect, thus, keeping the user experience intact while saving power of the UE 102.

[0035] In the example scenario, referring to Figure 1B, the brightness of pixels outside of the one or more UI elements 106 and / or the one or more ROIs 108 may be adjusted to save power of the UE 102. Thus, after adjusting, particularly reducing the brightness of the pixels outside of the one or more UI elements 106 and / or the one or more ROIs 108, the output current consumption may decrease in comparison to the initial current consumption. For instance, the output current consumption of the UE 102 may be reduced to 124.70 mAH.

[0036] Furthermore, in an embodiment, the binary mask may be dynamically updated based on changes in user interaction and a content of the display screen 104. For instance, if the user moves their focus to a different part of the display screen 104, the binary mask may be adjusted to reflect the new ROIs. In an advantageous aspect, real-time updates may ensure that the display screen remains adaptive and responsive to the user's needs. Thus, when the user interaction indicates a shift in focus or attention, the previously adjusted pixels or dimmed pixels are restored to their original brightness. In an advantageous aspect, this ensures that the user interface remains intuitive and user-friendly, adapting to the user's behaviour.

[0037] Thus, advantageously, by adjusting the brightness or dimming non-essential areas of the display screen 104, the binary mask helps significantly reduce the power consumption of the UE 102, thereby extending the device's battery life. Furthermore, important UI elements and ROIs may remain bright and easily readable, ensuring that users interact with the device effectively. Furthermore, the use of a binary mask allows for context-aware adjustments, where the display adapts in real time based on user interaction and environmental conditions.

[0038] Further, the power-saving in the UE 102 may be achieved using modules of the system as explained in forthcoming paragraphs of Figure 2-5.

[0039] Figure 2 illustrates a schematic block diagram of modules components of the system 200 for power-saving in the UE 102, according to an embodiment of the present disclosure.

[0040] The UE 102 may include but is not limited to, a processor 202, memory 204, modules 206, and data 208. The modules 206 and the memory 204 may be coupled to the processor 202.

[0041] The processor 202 can be a single processing unit or several units, all of which could include multiple computing units. The processor 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor 202 is adapted to fetch and execute computer-readable instructions and data stored in the memory 204.

[0042] The memory 204 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and / or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. The memory 204 may alternatively be referred to as the database 204 in the present disclosure, within the scope of the disclosure.

[0043] The modules 206, amongst other things, include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement data types. The modules 206 may also be implemented as, signal processor(s), state machine(s), logic circuitries, and / or any other device or component that manipulates signals based on operational instructions.

[0044] Further, the modules 206 can be implemented in hardware, instructions executed by a processing unit, or by a combination thereof. The processor 202 can comprise a computer, a processor, a state machine, a logic array, or any other suitable devices capable of processing instructions. The processing unit can be a general-purpose processor (e.g., processor 202) which executes instructions to cause the general-purpose processor to perform the required tasks or, the processing unit can be dedicated to performing the required functions. In an embodiment of the present disclosure, the modules 206 may be machine-readable instructions (software) which, when executed by the processor 202 / processing unit, perform any of the described functionalities / methods, as discussed throughout the present disclosure.

[0045] Furthermore, the modules 206 may be implemented through an artificial intelligence (AI) model. A function associated with AI may be performed through the non-volatile memory, the volatile memory, and the processor.

[0046] The processor 202 may include one or a plurality of processors. At this time, one or a plurality of processors may be a general purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU).

[0047] The one or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

[0048] Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or AI model of a desired characteristic is made. The learning may be performed in a device itself in which AI according to an embodiment is performed, and may be implemented through a separate server / system.

[0049] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through the calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

[0050] The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0051] In an embodiment, the modules 206 may include a display content module 210, a binary mask generating module 212, and an adjusting module 214. The display content module 210, the binary mask generating module 212, and the adjusting module 214 may be in communication with each other. The data 208 serves, amongst other things, as a repository for storing data processed, received, and generated by one or more of the modules 206. Figure 3, Figure 4, and Figure 5 provide a detailed description of each of the modules 206.

[0052] In an embodiment, the display content module 210 may be configured to identify at least one of, the one or more UI elements 106 and / or one or more ROIs 108 present on the display screen 104 of the UE 102. Further, the display content module 210 may be configured to obtain the pixel map corresponding to the one or more UI elements 106 and / or the one or more ROIs 108.

[0053] In an embodiment, the binary mask generating module 212 may be configured to generate the binary mask, based on mapping pixels in the pixel map with the one or more UI elements 106 and / or the one or more ROIs 108.

[0054] In an embodiment, the adjusting module 214 may be configured to adjust the brightness of the pixels, at least, within and outside of, the identified one or more UI elements 106 and / or the one or more ROIs 108, based on the binary mask thereby saving power in the UE 102 using adaptive brightness. A detailed description of the working of each of the display content module 210, the binary mask generating module 212, and the adjusting module 214 is explained in the forthcoming paragraphs of Figure 3, Figure 4, and Figure 5.

[0055] Figure 3 illustrates a process flow associated with the display content module 210 of the system 200, in accordance with various embodiments of the present disclosure.

[0056] In an embodiment, at step 302, the process flow 300 may include identifying the one or more UI elements 106 and / or the one or more ROIs 108 present on the display screen 104 of the UE 102. In an example, the identification may be performed using image processing techniques or Convolutional Neural Networks (CNNs) to recognize and classify different UI elements and ROIs by analyzing the visual features of the image corresponding to the display screen (current). In an example, the system 200 may be configured to capture the image of the display screen 104 periodically or continuously to ensure up-to-date analysis.

[0057] In an example, an edge detection technique may be used to identify the boundaries of objects within the captured image corresponding to the display screen 104. The edge detection technique may help in predicting and delineating the edges of the one or more UI elements 106 and / or the one or more ROIs 108 on the display screen 104. The edge detection technique may include identifying significant changes in intensity within the captured image. These changes typically correspond to the boundaries of objects (the one or more UI elements 106 and / or the one or more ROIs 108) intending to capture the structural features of the captured image, such as lines, curves, and shapes.

[0058] Further, the captured image, which may be in Red, Green, Blue (RGB) format, is converted to a grayscale image by removing the color information and preserving the intensity of light. Thus, pixels in the grayscale image may represent the intensity of light in the corresponding pixel of the original RGB image. The grayscale image is then converted to a binary (black and white) image. This step further simplifies the captured image by converting it to two colors i.e., black (representing the background) and white (representing the foreground or edges).

[0059] Furthermore, in an example, the binary image is processed using the Canny edge detection algorithm technique. Thereafter detecting edges, bounding boxes may be created around these edges. Bounding boxes may correspond to rectangular shapes that enclose the detected edges, providing a clear and defined boundary for each of the one or more UI elements 106 and / or the one or more ROIs 108. Thus, the bounding boxes help in visualizing and isolating the edges of different elements on the display screen 104. Furthermore, lines are drawn along the detected edges, enhancing the visibility of the edges and helping to define the direction of the edges more clearly. Thus, effectively outlining the shape and structure of each of the one or more UI elements 106 and / or the one or more ROIs 108.

[0060] Consequently, the output may be a visual representation where each of the one or more UI elements 106 and / or the one or more ROIs 108 on the display screen 104 is enclosed within the rectangular bounding box. In an advantageous aspect, the output helps in identifying and isolating different components of the display for further processing or analysis.

[0061] At step 304, the process flow 300 may include predicting the coordinates of the one or more UI elements 106 and / or one or more ROIs 108.

[0062] In an embodiment, an object detection artificial intelligence (AI) model such as YOLOv8m may be used to predict the coordinates of bounding boxes around the one or more UI elements 106 and / or the one or more ROIs 108.

[0063] In an example, the object detection AI model may use a single neural network to process the captured image. The captured image may be divided into a grid and predicts bounding boxes. The object detection AI model may be trained to recognize various objects (the one or more UI elements 106 and / or the one or more ROIs 108) and predict their bounding boxes. For each detected object, the object detection AI model may predict the coordinates of the bounding box. These coordinates are represented as tensors in the form of [x1, y1, x2, y2], wherein:

[0064] x1, y1: Coordinates of the top-left corner of the bounding box.

[0065] x2, y2: Coordinates of the bottom-right corner of the bounding box.

[0066] Further, in an example, the predicted coordinates of all bounding boxes may be stored as the dependent variables. The results are stored in a structured format, where each detected object (the one or more UI elements 106 and / or the one or more ROIs 108) has a corresponding tensor containing the bounding box coordinates.

[0067] At step 306, the process flow 300 may include obtaining a pixel map corresponding to the one or more UI elements 106 and / or the one or more ROIs 108.

[0068] In an embodiment, based on the bounding box coordinates of the previous step, as provided by the object detection AI model, pixel data corresponding to each of the one or more UI elements 106 and / or the one or more ROIs 108 is extracted based on selecting the pixels within the boundaries defined by the bounding boxes.

[0069] In an example, pixels within the identified boundaries (i.e., the bounding boxes) may be mapped to its respective UI element or ROI. For instance, pixels corresponding to an icon, text, navigation bar, status bar, buttons, or other interactive elements may be identified and grouped accordingly.

[0070] Consequently, the pixel map is created by mapping pixels in the extracted pixel data to a matrix or file that represents or corresponds to the one or more UI elements 106 and / or the one or more ROIs 108. In an advantageous aspect, the pixel map may effectively serve as a spatial representation of the display screen 104, highlighting the areas of interest.

[0071] Figure 4 illustrates a process flow associated with the binary mask generating module 212 of the system 200, in accordance with various embodiments of the present disclosure.

[0072] In an embodiment, at step 402, the process flow 400 may include generating the binary mask corresponding to the display screen 104. The binary mask corresponds to a technique in image processing and computer vision that represents a spatial selection or segmentation of regions within the captured image of the display screen 104. The binary mask may include a matrix or an array where pixels is assigned the binary value of 0 or 1. The primary purpose of the binary mask is to selectively manipulate or analyze specific regions within the captured image of the display screen 104. The binary mask may act as a spatial filter or mask that isolates parts of the captured image based on predefined criteria. The generation of the binary mask based on mapping pixels in the pixel map with the one or more UI elements 106 and / or the one or more ROIs 108 involves a process that integrates the outputs from the UI element identification (the display content module 210).

[0073] In an example, the binary mask generating module 212 may be configured to receive the tensors from the display content module 210, created during the identification of the one or more UI elements 106 and / or the one or more ROIs 108. The tensors includes coordinates that specify where the one or more UI elements 106 and / or the one or more ROIs 108 are located within the captured image of the display screen 104.

[0074] Further, based on the coordinates provided by the tensors, the binary mask generating module 212 may be configured to create rectangle objects that may define the shape and position of each of the one or more UI elements 106 and / or the one or more ROIs 108 in the captured image of the display screen 104. Each rectangle outlines distinct UI elements and / or the ROI, such as a button, text area, or icon, based on its coordinates.

[0075] Consequently, to generate the binary mask for each of the one or more UI elements 106 and / or the one or more ROIs 108, the binary mask generating module 212 may be configured to take the rectangle object as input and generate the binary image where pixels within / inside the rectangle are assigned the binary value of 1 (indicating presence of at least one of, the one or more UI elements 106 and / or the one or more ROIs 108) and pixels outside are assigned the binary value of 0 (indicating absence of the one or more UI elements 106 and / or the one or more ROIs 108).

[0076] In an advantageous aspect, the generation of the binary mask thus effectively isolates each of the one or more UI elements 106 and / or the one or more ROIs 108 within the captured image of the display screen 104. Consequently, facilitates targeted processing and analysis based on their spatial locations.

[0077] Further, after generating binary masks for the one or more UI elements 106 and / or the one or more ROIs 108, the binary mask generating module 212 may be configured to integrate the binary masks into a unified pixel map. The pixel map now includes the assigned binary values (0 or 1) that indicate the presence or absence of the one or more UI elements 106 and / or the one or more ROIs 108 across the entire captured image of the display screen 104.

[0078] At step 404, the process flow 400 may include creating a map based on the binary mask and the display screen (the captured image) of the UE 102, such that the binary mask (which masks important UI elements and ROIs) aligns with the captured image of the display screen 104.

[0079] In an embodiment, the binary mask generating module 212 may be configured to perform mapping that associates pixels in the binary mask with its corresponding pixel in the original display screen 104 (the captured image) of the UE 102. In an advantageous aspect, the mapping may be essential for maintaining a reference between the processed binary mask and the actual visual content of the display screen 104. Thus, by creating the map that links pixels identified in the binary mask to its corresponding pixel location in the display screen (the captured image), the process allows for precise reference and retrieval of visual data.

[0080] In an example, the map associates or links pixels in the binary mask to its corresponding pixel in the display screen 104 (the captured image) of the UE 102. The association thus, ensures that for every pixel identified as part of the one or more UI elements 106 or the one or more ROIs 108 in the binary mask, there is a direct reference to its location in the actual visual content displayed on the UE 102 (on the display screen 104).

[0081] In an example, the mapping may be implemented using data structures such as dictionaries or arrays, where each entry stores the coordinates or indices of pixels in the binary mask and their corresponding positions in the captured image of the display screen 104. In an example, for every pixel position marked or with the assigned value as 1 in the binary mask i.e., indicating the presence of the one or more UI elements 106 and / or the one or more ROIs 108, the binary mask generating module 212 may be configured to determine its exact coordinates or indices within the binary mask. Thus, the binary mask generating module 212 may be configured to locate the corresponding pixel in the display screen (the captured image) using the same coordinates or indices.

[0082] In an example scenario, the binary mask may identify a rectangular ROI encompassing a button on the smartphone (UE 102) screen. The binary mask would have the assigned binary value of 1s in the pixels that make up the button and 0s elsewhere. Thus, the mapping ensures that pixels' position in the binary mask (where it is 1) corresponds directly to the pixel's position in the actual image of the button on the display screen.

[0083] Thus, in an advantageous aspect, the binary mask generating module 212 by creating mapping ensures that accurate alignment exists between the binary mask and the display screen (the captured image), which may be crucial for subsequent processing tasks such as adaptive brightness control and power-saving. Further, the creation of the map facilitates efficient retrieval and utilization of visual data. The mapping allows quick access to specific regions of interest without needing to reanalyze the entire screen image repeatedly.

[0084] Further, the map generated may be stored in the memory 204. Thus, the memory 204 may hold key-value pairs i.e., the key may correspond to the binary mask, and may be serialized into a string format for storage efficiency; the value may correspond to the original display screen (the captured image). In an advantageous aspect, the storage of the key-value pairs may allow for efficient retrieval and utilization of the binary masks and their associated images for various applications such as real-time analysis, user interaction tracking, or system optimization.

[0085] At step 406, the process flow 400 may include processing the map using U-net convolutional neural network (CNN).

[0086] In an embodiment, in image processing, convolution may include applying a filter or kernel to the captured image of the display screen 104 to extract features or modify its characteristics. Further, the U-net architecture is a type of CNN which is commonly used for image segmentation tasks. It includes an attention technique that focuses on relevant parts of the captured image of the display screen 104 while filtering out less critical / important areas. The U-net attention technique ensures that during convolution, more emphasis or attention is given to regions identified by the binary mask as containing the one or more UI elements 106 and / or the one or more ROIs 108 (where the binary mask value is assigned as 1).

[0087] In an example, the input to the U-net CNN may include the display screen (the captured image) and the binary mask that highlights the one or more UI elements 106 and / or the one or more ROIs 108 (with the binary value assigned as 1). Consequently, using the attention U-net architecture, convolutional layers are applied to the captured image of the display screen 104. The convolutional layers are configured to focus on relevant areas i.e., indicated by the binary mask (where the binary mask value is assigned as 1) receive more attention during convolution. In an example, during convolution, the U-net CNN may adjust the pixels according to the attention mechanism guided by the binary mask. This ensures that changes or enhancements are targeted specifically at the one or more UI elements 106 and / or the one or more ROIs 108, thus, optimizing display quality and user interaction.

[0088] Consequently, the pixel values may be adjusted in these regions to enhance or adapt them based on the application's requirements e.g., adaptive brightness adjustment.

[0089] At step 408, the process flow 400 may include obtaining a light sensor value from a light sensor of the UE 102. Thus, based on input (the light sensor value) from the light sensors, adjustments are made to the background or areas of the display screen that are not covered by the one or more UI elements 106 and / or the one or more ROIs 108 (where binary mask value is assigned as 0). The light sensor value may correspond to lux levels i.e., illumination intensity, and may be pre-classified using a multi-class classifier such as RandomForestClassifier. The multi-class classifier may categorize incoming light sensor readings (the light sensor value) into predefined classes based on the lux levels. This classification helps in determining the appropriate brightness adjustment required for the display screen.

[0090] For instance, if the light sensor detects low ambient light in the environment, the convolutional process may enhance brightness in areas not covered by the one or more UI elements 106 to improve visibility without affecting the UI elements themselves.

[0091] At step 410, the process flow 400 may include storing the map of association of binary mask and the display screen in the memory 204.

[0092] Figure 5 illustrates a process flow associated with the adjusting module 214 of the system 200, in accordance with various embodiments of the present disclosure.

[0093] In an embodiment, at step 502, the process flow 500 may include adjusting the brightness of the pixels based on the light sensor value. In an embodiment, the pixels of the display screen 104 having the binary mask value assigned as 0 are adjusted. In an embodiment, at step 502a, the process flow 500 may include dimming pixels with the binary mask value of 0 (less important areas) to save power. In an embodiment, at step 502b, the process flow 500 may include no dimming for pixels with the binary mask value of 1 (UI / ROI). Furthermore, the adjustment of the brightness is implemented in real-time thereby optimizing the display quality and user experience of the UE 102.

[0094] In an example, the adjusting module 214 may be configured to adjust the brightness based on light sensor values involves dynamically modifying the luminance of the display screen 104 in response to ambient lighting conditions to ensure optimal visibility and user comfort under varying ambient light levels.

[0095] In an example scenario, when the user is indoors during daytime, sitting near a window where sunlight intermittently affects the ambient light levels, the light sensor may continuously measure the light sensor value or the lux values around the UE 102. For instance, the light sensor may detect, high light sensor values when exposed to direct sunlight or bright indoor lighting. Similarly, the light sensor value may detect, low light sensor values when in dimly lit environments or during nighttime. The binary mask, generated from the binary mask generating module 212, identifies regions of interest (such as active UI elements like buttons or text) on the display screen 104 of the UE 102. The attention U-net CNN technique, trained to recognize and adjust based on the light sensor values, may selectively adjust the brightness of the pixels within and / or outside the identified one or more UI elements 106 and / or the one or more ROIs 108.

[0096] In an example scenario, during the high light sensor values, the pixels within the one or more UI elements 106 and / or the one or more ROIs 108 may be dimmed to reduce glare and improve readability.

[0097] In an example scenario, during the low light sensor values, the pixels outside the one or more UI elements 106 and / or the one or more ROIs 108 may be brightened to ensure visibility without affecting the overall user experience negatively.

[0098] In an example scenario, the system 200 may continuously monitor the light sensor values and dynamically adjust the brightness by adjusting the pixels in real time. In an advantageous aspect, as lighting conditions change e.g., moving from a bright room to a darker corridor, the display brightness adjusts promptly to maintain optimal visibility. Thereby, this dynamic adjustment of brightness enhances user comfort by reducing eye strain and optimizing the readability of displayed content.

[0099] At step 504, the process flow 500 may include receiving a touch input from the user. At step 506, the process flow 500 may include restoring the brightness of the pixels of the display screen having the binary mask value of 0.

[0100] In an embodiment, the touch input obtained via a touch sensor on the UE 102 detects and registers user interactions, such as taps or swipes on the display screen 104. For instance, when the user touches the display screen 104 to interact with an application or navigate menus, the touch sensor records these inputs as the touch-input. After dynamically adjusting the brightness of pixels on the display screen 104 based on say, environmental factors e.g., light sensor data and user interactions e.g., touch inputs, the adjusting module 214 may be configured to restore the adjustments.

[0101] In an example, when the system 200 receives the touch-sensor value corresponding to the user interaction i.e., touching the display screen 104 to interact with the application, the adjusting module 214 may be configured to correlate the touch-input value with the stored map. In the example, if the user taps on a non-UI area of the display screen 104 (i.e., with binary mask value assigned as 0), the system 200 notes this interaction. Subsequently, if the system 200 receives a second touch-sensor value indicating another user input e.g., a different tap or swipe, it checks whether the second touch-sensor input corresponds to an area of the display screen 104 previously adjusted for brightness. The brightness adjustments made based on the initial touch-sensor input are temporary, ensuring optimal visibility and user comfort during interaction with the UE 102. Upon receiving the second touch-sensor value, the adjusting module 214 may be configured to reference the created map to restore the brightness of pixels which were previously adjusted, for instance, pixels outside the one or more UI elements 106 and / or the one or more ROIs 108 (i.e., with binary mask value assigned as 0) to their original levels.

[0102] In an example scenario, if the user taps outside the UI element (binary mask value assigned as 0 area) to dismiss a pop-up window, the brightness of the background area may revert to its default setting after the interaction is completed.

[0103] Figure 6 illustrates an exemplary use-case scenario of the system, in accordance with various embodiments of the present disclosure.

[0104] In an example scenario referring to Figure 6A, the UE 102 screen displays an application-1 (app) 602, say, a Contacts app, which is within the region of interest (ROI), thus the pixel values are maintained. Consequently, the initial current consumption, which was say, 145.23 mAH, may be reduced to the final current consumption say, 125.69 mAH.

[0105] Furthermore, in an example scenario, the App-2 604, say, a messages app, may be located to the left of the app-1 602, and is outside the ROI, resulting in its pixel values being adjusted based on light sensor data to save power. When the user scrolls the applications to the right, as illustrated in Figure 6B, each of the apps shifts to the right, causing the app-2 604 to enter the ROI, thereby restoring its pixel values. Consequently, the pixel values of the app-1 602 and the app-3 606 may be adjusted according to the light sensor data for power saving, as they are no longer within the ROI. Consequently, the initial current consumption, which was say, 146.05 mAH, may be reduced to the final current consumption say, 125.75 mAH.

[0106] Figure 7 illustrates an exemplary process flow comprising a method 700 for power-saving in the UE 102, according to an embodiment of the present disclosure.

[0107] The method 700 may be a computer-implemented method executed, for example, by the UE 102 and the modules 206. For the sake of brevity, constructional and operational features of the system 200 that are already explained in the description of Figure 1, Figure 2, Figure 3, Figure 4, Figure 5, and Figure 6 are not explained in detail in the description of Figure 7.

[0108] At step 702, the method 700 may include identifying at least one of, the one or more UI elements 106 and the one or more regions of interest (ROIs) 108 present on the display screen 104 of the UE 102.

[0109] At step 704, the method 700 may include obtaining a pixel map corresponding to the identified at least one of the one or more UI elements 106 or the one or more ROIs 108.

[0110] At step 706, the method 700 may include generating the binary mask, based on mapping pixels in the pixel map with the identified at least one of one or more UI elements 106 or the one or more ROIs 108.

[0111] At step 708, the method 700 may include adjusting the brightness of the plurality of pixels outside of the identified at least one of one or more UI elements 106 or the one or more ROIs 108, based on the binary mask thereby saving power in the UE 102 using adaptive brightness.

[0112] The present disclosure provides various advantages:

[0113] The present disclosure provides enhanced power efficiency of the UE 102 by identifying specific UI elements and / or ROIs and adjusting the brightness only in those areas. This targeted approach contrasts with conventional methods that dim the entire screen uniformly.

[0114] The present disclosure dynamically adjusts the brightness based on the binary mask, ensuring that only the necessary parts of the screen are brightened or dimmed according to real-time usage. This adaptive control conserves energy and extends battery life.

[0115] The present disclosure provides context-aware adjustments as users interact primarily with UI elements and / or ROIs, such as buttons, text, and active windows. By maintaining optimal brightness in these critical areas while dimming the background, the present disclosure enhances readability and usability without compromising on power saving.

[0116] The present disclosure provides a response in real-time to changes in ambient light and user interactions, providing a seamless and comfortable viewing experience. For example, when ambient light levels drop, the present disclosure may automatically adjust brightness to maintain visibility without user intervention.

[0117] The present disclosure provides optimized visual comfort, based on adjusting the brightness intelligently based on the context.

[0118] The present disclosure maintains visual appeal based on keeping essential UI elements well-lit and clear, which is crucial for user satisfaction and engagement.

[0119] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0120] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0121] According to an embodiment of the disclosure, the adjusting the brightness may comprise creating a map based on the binary mask and the display screen of the UE, wherein the map indicates association of each of the plurality of pixels in the binary mask with a corresponding pixel in the display screen of the UE. According to an embodiment of the disclosure, the adjusting the brightness may comprise convolving the map using an attention U-net technique to convolve the display screen based on the binary mask, wherein attention is assigned to at least one of the one or more UI elements or the one or more ROI having a binary mask value of 1. According to an embodiment of the disclosure, the adjusting the brightness may comprise obtaining a light sensor value from a light sensor of the UE. According to an embodiment of the disclosure, the adjusting the brightness may comprise adjusting the brightness of the plurality of pixels based on the light sensors value, wherein the plurality of pixels of the display screen having the binary mask value of 0 are adjusted. According to an embodiment of the disclosure, the adjusting the brightness may comprise implementing the brightness adjustments in real-time thereby optimizing display quality and user experience.

[0122] According to an embodiment of the disclosure, the adjusting the brightness of the plurality of pixels of the display screen having the binary mask value of 0 may be indicative of background areas of the display screen.

[0123] According to an embodiment of the disclosure, the adjusting brightness of plurality of pixels may comprise adjusting brightness of a plurality of pixels within the identified at least one or more UI elements or the one or more ROIs, based on light sensor value.

[0124] According to an embodiment of the disclosure, the method for power-saving in a user equipment may include obtaining a touch-sensor value based on a user-input while the UE is operated and automatically restoring the brightness of the adjusted plurality of pixels based on correlation with the touch-sensor value.

[0125] According to an embodiment of the disclosure, the restoring the brightness may comprise restoring the brightness of the plurality of pixels of the display screen having the binary mask value of 0 based on the created map, in response to receiving a second touch-sensor value corresponding to a second user-input while the UE is operated.

[0126] According to an embodiment of the disclosure, the generating the binary mask may comprise performing spatial adaptive pixel convolution thereby adjusting brightness of the each mapped pixel based on the binary mask value corresponding to the identified at least one of the one or more UI elements or the one or more ROIs, the touch-sensor value and the light sensor value such that adaptive display brightness saves power in the UE.

[0127] According to an embodiment of the disclosure, the pixel map may include one or more spatial coordinates of at least one of the one or more UI elements or the one or more ROIs.

[0128] According to an embodiment of the disclosure, the one or more UI elements may include icon, text, navigation bar, status bar, and buttons on the display screen of the UE and the one or more ROIs may include at least one of an active window or non-active window on the display screen of the UE.

[0129] According to an embodiment of the disclosure, to adjust the brightness, the at least one processor may be configured to create a map based on the binary mask and the display screen of the UE, wherein the map indicates association of each of the plurality of pixels in the binary mask with a corresponding pixel in the display screen of the UE. According to an embodiment of the disclosure, to adjust the brightness, the at least one processor may be configured to convolve the map using an attention U-net technique to convolve the display screen based on the binary mask, wherein attention is assigned to at least one of the one or more UI elements or the one or more ROI having a binary mask value of 1. According to an embodiment of the disclosure, to adjust the brightness, the at least one processor may be configured to obtain a light sensor value from a light sensor of the UE. According to an embodiment of the disclosure, to adjust the brightness, the at least one processor may be configured to adjust the brightness of the plurality of pixels based on the light sensors value, wherein the plurality of pixels of the display screen having the binary mask value of 0 are adjusted. According to an embodiment of the disclosure, to adjust the brightness, the at least one processor may be configured implement the brightness adjustments in real-time thereby optimizing display quality and user experience.

[0130] According to an embodiment of the disclosure, adjusting the brightness of the plurality of pixels of the display screen having the binary mask value of 0 may be indicative of background areas of the display screen.

[0131] According to an embodiment of the disclosure, the at least one processor may be configured to obtain a touch-sensor value based on a user-input while the UE is operated and automatically restoring the brightness of the adjusted plurality of pixels based on correlation with the touch-sensor value.According to an embodiment of the disclosure, to restore the brightness, the at least one processor may be configured to restore the brightness of the plurality of pixels of the display screen having the binary mask value of 0 based on the created map, in response to receiving a second touch-sensor value corresponding to a second user-input while the UE is operated.

[0132] According to an embodiment of the disclosure, to generate the binary mask, the at least one processor may be configured to perform spatial adaptive pixel convolution thereby adjusting brightness of the each mapped pixel based on the binary mask value corresponding to the identified at least one of the one or more UI elements or the one or more ROIs, the touch-sensor value and the light sensor value such that adaptive display brightness saves power in the UE.

[0133] According to an embodiment of the disclosure, the pixel map may include one or more spatial coordinates of at least one of the one or more UI elements or the one or more ROIs.

[0134] According to an embodiment of the disclosure, the one or more UI elements may include icon, text, navigation bar, status bar, and buttons on the display screen of the UE and the one or more ROIs may include at least one of an active window or non-active window on the display screen of the UE.

Claims

A method for power-saving in a user equipment (UE), the method comprising:identifying at least one of, one or more user interface (UI) elements or one or more regions of interest (ROIs) present on a display screen of the UE;obtaining a pixel map corresponding to the identified at least one of the one or more UI elements or the one or more ROIs;generating a binary mask, based on mapping pixels in the pixel map with the identified at least one of one or more UI elements or the one or more ROIs; andadjusting brightness of a plurality of pixels outside of the identified at least one of one or more UI elements or the one or more ROIs, based on the binary mask using adaptive brightness.The method as claimed in claim 1, wherein adjusting the brightness comprises:creating a map based on the binary mask and the display screen of the UE, wherein the map indicates association of each of the plurality of pixels in the binary mask with a corresponding pixel in the display screen of the UE;convolving the map using an attention U-net technique to convolve the display screen based on the binary mask, wherein attention is assigned to at least one of the one or more UI elements or the one or more ROI having a binary mask value of 1;obtaining a light sensor value from a light sensor of the UE;adjusting the brightness of the plurality of pixels based on the light sensor value, wherein the plurality of pixels of the display screen having the binary mask value of 0 are adjusted; andimplementing the brightness adjustments in real-time.The method as claimed in claim 2, wherein adjusting the brightness of the plurality of pixels of the display screen having the binary mask value of 0 is indicative of background areas of the display screen.The method any one of claims 1 to 3, wherein adjusting brightness of plurality of pixels comprises:adjusting brightness of a plurality of pixels within the identified at least one or more UI elements or the one or more ROIs, based on light sensor value.The method any one of claims 1 to 4, further comprising:obtaining a touch-sensor value based on a user-input while the UE is operated and automatically restoring the brightness of the adjusted plurality of pixels based on correlation with the touch-sensor value.The method as claimed in claim 5, wherein restoring the brightness comprises:restoring the brightness of the plurality of pixels of the display screen having the binary mask value of 0 based on the created map, in response to receiving a second touch-sensor value corresponding to a second user-input while the UE is operated.The method any one of claims 1 to 6, wherein generating the binary mask comprises:performing spatial adaptive pixel convolution based on the binary mask value corresponding to the identified at least one of the one or more UI elements or the one or more ROIs, the touch-sensor value and the light sensor value.The method any one of claims 1 to 7, wherein the pixel map includes one or more spatial coordinates of at least one of the one or more UI elements or the one or more ROIs.The method any one of claims 1 to 8, wherein the one or more UI elements include icon, text, navigation bar, status bar, and buttons on the display screen of the UE and the one or more ROIs include at least one of an active window or non-active window on the display screen of the UE.A system for power-saving in a user equipment (UE), the system comprising:memory storing instructions; andat least one processor in communication with the memory, the at least one processor is configured to execute the instructions to:identify at least one of, one or more user interface (UI) elements or one or more regions of interest (ROIs) present on a display screen of the UE;obtain a pixel map corresponding to the identified at least one of the one or more UI elements or the one or more ROIs;generate a binary mask, based on mapping pixels in the pixel map with the identified at least one of one or more UI elements or the one or more ROIs; andadjust brightness of a plurality of pixels outside of the identified at least one of one or more UI elements or the one or more ROIs, based on the binary mask using adaptive brightness.The system as claimed in claim 10, wherein to adjust the brightness, the at least one processor is configured to execute the instructions to:create a map based on the binary mask and the display screen of the UE, wherein the map indicates association of each of the plurality of pixels in the binary mask with a corresponding pixel in the display screen of the UE;convolve the map using an attention U-net technique to convolve the display screen based on the binary mask, wherein attention is assigned to at least one of the one or more UI elements or the one or more ROI having a binary mask value of 1;obtain a light sensor value from a light sensor of the UE;adjust the brightness of the plurality of pixels based on the light sensor value, wherein the plurality of pixels of the display screen having the binary mask value of 0 are adjusted; andimplement the brightness adjustments in real-time.The system as claimed in claim 11, wherein adjusting the brightness of the plurality of pixels of the display screen having the binary mask value of 0 is indicative of background areas of the display screen.The system any one of claims 10 to 12, wherein to generate the binary mask, the at least one processor is configured to execute the instructions to:perform spatial adaptive pixel convolution thereby adjusting brightness of the each mapped pixel based on the binary mask value corresponding to the identified at least one of the one or more UI elements or the one or more ROIs, the touch-sensor value and the light sensor value.The system any one of claims 10 to 13, wherein the pixel map includes one or more spatial coordinates of at least one of the one or more UI elements or the one or more ROIs.A machine readable medium containing instructions, wherein the instructions, when executed by at least one processor, cause the at least one processor to perform the method of any one of claims 1 to 9.

Images