Interface display method and electronic equipment

Abstract

The invention provides an interface display method and electronic equipment, and relates to the technical field of terminals. After the game application is started, the electronic equipment can obtain current scene information and current equipment state information. The current scene information represents the current game scene of the game application, such as a magnification lens scene and a game hall scene. The electronic device may then determine a prediction probability using the current scene information and the current device state information. The prediction probability refers to the probability of starting the super-resolution rendering function. Afterwards, when the prediction probability is greater than a preset probability threshold, it is indicated that a super-resolution rendering function needs to be started, and the electronic device can render the game interface by using a super-resolution rendering technology to obtain a target interface. The resolution of the target interface is not equal to the set resolution corresponding to the game application, so that the super-resolution rendering function is automatically started, the image quality of the game interface is improved, the immersive experience of a user is ensured, or the power consumption of the electronic equipment is reduced.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of terminals, and in particular, to an interface display method and an electronic device. Background Art

[0002] After an application (APP) of an electronic device is launched, the electronic device needs to render the interface (or referred to as an image) of the application. Specifically, the electronic device can determine a resolution according to requirements, and then use the resolution to render the interface of the application. For example, after a game application is launched, the user can select a resolution, and the electronic device can render the game interface according to the resolution selected by the user.

[0003] However, the resources of the electronic device required to render interfaces with different resolutions are different. For example, when the electronic device renders a high-resolution interface, the resources consumed by the electronic device are relatively high, resulting in a relatively high power consumption of the electronic device. Therefore, how to better render the interface of the application has become an urgent problem to be solved. Summary of the Invention

[0004] Embodiments of the present application provide an interface display method and an electronic device for implementing the rendering of an application interface, so that the power consumption of the electronic device is relatively low and the quality of the rendered interface is ensured.

[0005] To achieve the above object, the embodiments of the present application adopt the following technical solutions:

[0006] In a first aspect, the present application provides an interface display method applied to an electronic device. The electronic device receives a first operation (i.e., a start operation) of a first application input by a user. In response to the first operation, the electronic device starts the first application.

[0007] After that, the electronic device can obtain the current scene information of the first application and the current device state information of the electronic device. Among them, the current scene information of the first application can represent the scene where the first application is currently located. The current device state represents the current running situation of the electronic device.

[0008] After that, the electronic device can render a to-be-rendered interface (or referred to as a to-be-rendered image) of the first application based on the current scene information and the current device state information to obtain a target interface.

[0009] Among them, when the prediction probability corresponding to the current scene information and the current device state information is greater than a preset probability threshold, the target interface is rendered by the electronic device based on the set resolution corresponding to the first application and in combination with a super-resolution rendering algorithm, and the resolution of the target interface is not equal to the set resolution. The prediction probability represents the probability of predicting to turn on the super-resolution rendering function. The higher the prediction probability, the more suitable the electronic device is currently for turning on the super-resolution rendering function.

[0010] In this application, after the first application is launched, the electronic device can determine the probability of enabling the super-resolution rendering function by using the current scene information and the current device status information of the first application. When the probability is relatively high, it indicates that the electronic device is suitable for enabling the super-resolution rendering function. The electronic device can use the super-resolution rendering algorithm to render the interface to be rendered of the first application to obtain a target interface, thereby realizing the automatic enabling of the super-resolution rendering function. When the resolution of the rendered target interface is less than the set resolution corresponding to the first application, it indicates that fewer resources are consumed during the rendering process of the electronic device, avoiding unnecessary resource consumption, thereby reducing the power consumption of the electronic device and further avoiding the problem of overheating of the electronic device. When the resolution of the rendered target interface is greater than the set resolution corresponding to the first application, it indicates that the image quality of the target interface is relatively high, improving the user's immersive experience and better realizing the rendering of the application interface. Moreover, since the prediction probability is determined by the electronic device using the current scene information and the current device status information, it is determined from the overall situation of the electronic device, ensuring the accuracy of the determined prediction probability, and avoiding deviation in the determined prediction probability due to a single factor, thereby realizing an accurate judgment on whether to enable the super-resolution rendering function.

[0011] In a possible design, when the above prediction probability is less than or equal to the preset probability threshold, the above target interface is rendered based on the set resolution, and the resolution of the target interface is equal to the set resolution.

[0012] In this application, when the prediction probability is less than or equal to the preset probability threshold, it indicates that the current performance of the electronic device supports normal rendering. The electronic device can turn off the super-resolution rendering function and continue to render the interface to be rendered of the first application based on the set resolution, thereby obtaining a target interface with a resolution equal to the set resolution and avoiding unnecessary loss of image quality.

[0013] Among them, the above set resolution can be the resolution corresponding to the first application automatically set by the electronic device or the resolution set by the user.

[0014] In a possible design, the above current device status information includes at least one of device form, device window status, temperature, jitter rate, remaining battery power, charging status, network latency, screen refresh rate, screen resolution, frame rate, and load.

[0015] Among them, the device form refers to the folded state, the unfolded state, and the non-folded device state. When the electronic device is a foldable device, the device form of the electronic device can be the folded state or the unfolded state. When the electronic device is not a foldable device, the device form of the electronic device can be the non-folded device state (or called the straight-board machine form).

[0016] Among them, the device window state refers to a multi-window state or a single-window state. Optionally, the multi-window state may include a split-screen state and a floating display state. The floating display state includes that the first application is in a floating state (i.e., the window of the first application is floating above the windows of other applications), or the first application is in a non-floating state (i.e., the windows of other applications are floating above the window of the first application). The window is used to display the interface of the application.

[0017] The charging state indicates whether the electronic device is charging. The charging state may include a charging state and a non-charging state.

[0018] The load may include a CPU load and / or a GPU load.

[0019] In a possible design, the electronic device may use the target model to determine the above prediction probability. The electronic device may use the current scene information and the current device state information as input parameters of the target model, run the target model, and obtain the prediction probability corresponding to the current scene information and the current device state information.

[0020] Among them, the above target model is obtained by training an initial model based on multiple training samples. Each training sample in the multiple training samples includes scene sample information, device state sample information, and an expected result corresponding to the scene sample information and the device state sample information. The expected result indicates whether to enable the super-resolution rendering function.

[0021] In this application, the electronic device may directly input the current scene information and the current device state information of the first application into the target model, obtain the prediction probability matching the current scene and the current device state, and achieve the fast and accurate determination of the prediction probability, so as to achieve the fast and accurate determination of the start and stop of the super-resolution rendering function.

[0022] Among them, the above expected result may include an expected start of the super-resolution rendering function. Optionally, the expected result may further include an expected stop of the super-resolution rendering function.

[0023] Among them, optionally, the above prediction probability may include a first prediction probability, the preset probability threshold includes a first preset probability threshold, and the target model includes a first target model. The first prediction probability represents the probability of predicting to start the first rendering function (or called the high-resolution rendering function) in the super-resolution rendering function. The first target model can predict the probability of starting the first rendering function.

[0024] The above first rendering function represents the function of rendering an interface with a resolution higher than the set resolution. The expected result in the above training sample may include an expected result of starting the first rendering function.

[0025] Correspondingly, the electronic device can use the current scene information and the current device status information as input parameters of the first target model, run the first target model, and obtain the first prediction probability corresponding to the current scene information and the current device status information.

[0026] After that, the electronic device can determine whether the first prediction probability is greater than the first preset probability threshold.

[0027] When the first prediction probability is greater than the first preset probability threshold, it indicates that the electronic device is currently suitable for enabling the first rendering function. Then, the electronic device can render the interface to be rendered based on the set resolution and in combination with the super-resolution rendering algorithm to obtain a target interface. The resolution of the target interface is greater than the set resolution, improving the image quality of the application interface, enhancing the user's visual experience, and avoiding excessive power consumption of the electronic device, thereby improving the user's satisfaction.

[0028] Optionally, the above prediction probability may include a second prediction probability, the preset probability threshold includes a second preset probability threshold, and the target model includes a second target model. This second prediction probability represents the probability of predicting the activation of the second rendering function (or called the low-resolution rendering function) in the super-resolution rendering function. The second target model can predict the probability of activating the second rendering function.

[0029] The above second rendering function refers to the function of rendering an interface with a resolution lower than the set resolution. The expected result in the above training sample may include the expected result of activating the second rendering function.

[0030] Correspondingly, the electronic device can use the current scene information and the current device status information as input parameters of the second target model, run the second target model, and obtain the second prediction probability corresponding to the current scene information and the current device status information.

[0031] After that, the electronic device can determine whether the second prediction probability is greater than the second preset probability threshold.

[0032] When the second prediction probability is greater than the second preset probability threshold, it indicates that the electronic device is currently suitable for enabling the second rendering function. Then, based on the set resolution and in combination with the super-resolution rendering algorithm, the interface to be rendered is rendered to obtain a target interface. The resolution of the target interface is less than the set resolution. Thus, when the current scene of the first application has low requirements for image quality, the electronic device can use the super-resolution rendering algorithm to render the interface of the first application, avoiding unnecessary resource consumption while ensuring the image quality of the interface of the first application, thereby reducing the power consumption of the electronic device and avoiding the problem of overheating of the electronic device.

[0033] Optionally, the above model may be a decision tree, which can accurately achieve classification.

[0034] In another possible design approach, the electronic device may not use the target model to determine the prediction probability, but directly calculate the prediction probability that matches the current scene information and the current device status information. Specifically, for each target feature, the electronic device may calculate the product of the classification value corresponding to the target feature and the weight corresponding to the target feature to obtain the weighted value corresponding to the target feature. Among them, the classification value corresponding to the target feature may be 1 or 0, which is determined according to whether the value of the target feature meets the preset classification condition corresponding to the target feature. The value of the target feature includes the information in the current scene information and the current device status information.

[0035] After that, the electronic device may calculate the sum of the weighted values corresponding to each target feature to obtain the prediction probability, thereby achieving the determination of the prediction probability.

[0036] Among them, optionally, the weight corresponding to the above target feature may be preset or obtained through training with training samples.

[0037] In one possible design approach, the electronic device can not only directly use the model to determine whether to enable the first rendering function (i.e., the high-resolution rendering function) or the second rendering function in the super-resolution rendering function, but also, based on the prediction probability being greater than the preset probability threshold, further determine whether to enable the first rendering function or the second rendering function based on the current scene information. Specifically, if the prediction probability is greater than the preset probability threshold, the electronic device may determine whether the current scene information belongs to the first preset scene information. The first preset scene information represents a scene with relatively high requirements for image quality that is preset in advance.

[0038] When the current scene information belongs to the first preset scene information, the electronic device may enable the first rendering function, use the super-resolution rendering algorithm to render the above-mentioned interface to be rendered, and obtain a target interface, the resolution of which is greater than the set resolution, thereby improving the image quality of the interface of the first application.

[0039] When the current scene information does not belong to the first preset scene information, the electronic device may enable the second rendering function, use the super-resolution rendering algorithm to render the above-mentioned interface to be rendered, and obtain a target interface, the resolution of which is less than the set resolution, thereby reducing the power consumption of the electronic device.

[0040] In one possible design approach, the above-mentioned first application may include a game application. Correspondingly, the above-mentioned current scene information represents a game scene, which may include at least one of a telescopic sight scene, an airplane scene, a shooting scene, a battle scene, and a game hall scene.

[0041] In a possible design, before obtaining the current scene information and the current device status information, the electronic device may first determine whether it is necessary to obtain them. The electronic device may first determine whether the first application belongs to a preset application. The preset application refers to an application that can trigger the electronic device to use the super-resolution rendering algorithm for rendering.

[0042] If the first application belongs to the preset application, the electronic device may continue to obtain the above-mentioned current scene information and the current device status information. If the first application does not belong to the preset application, the electronic device does not need the current scene information and the current device status information, and can directly render the interface to be rendered based on the set resolution corresponding to the above-mentioned first application, avoiding unnecessary judgments on the start and stop of the super-resolution rendering function.

[0043] In a second aspect, the present application provides an interface display method, which is applied to an electronic device. The electronic device receives a first operation (i.e., a start operation) of the first application of the electronic device input by the user. In response to the first operation, the electronic device starts the first application.

[0044] After that, the electronic device may obtain the current scene information of the first application and the current device status information of the electronic device. Among them, the current scene information of the first application may represent the scene where the first application is currently located. The current device status represents the current operating condition of the electronic device.

[0045] After that, the electronic device may determine a prediction probability based on the current scene information and the current device status information. The prediction probability represents the probability of predicting to turn on the super-resolution rendering function.

[0046] After that, the electronic device may determine whether the prediction probability is greater than a preset probability threshold.

[0047] If the prediction probability is greater than the preset probability threshold, it indicates that in the current scene and device status, the electronic device is suitable for turning on the super-resolution rendering function. Then, the electronic device may render the interface to be rendered of the first application based on the super-resolution rendering algorithm, combined with the set resolution corresponding to the first application, to obtain a target interface (here the target interface can also be called the first target interface, or target interface 1).

[0048] Among them, the resolution of the above-mentioned target interface is less than or equal to the set resolution

[0049] In a possible design, if the prediction probability is greater than the preset probability threshold, it indicates that in the current scene and device status, the electronic device is not suitable for turning on the super-resolution rendering function. Then, the electronic device may render the interface to be rendered of the first application based on the set resolution corresponding to the first application, to obtain a target interface. The resolution of this target interface is equal to the set resolution (here the target interface can also be called the second target interface, or target interface 2).

[0050] In a third aspect, the present application provides an electronic device, which includes a display screen, a memory, and one or more processors; the display screen, the memory, and the processors are coupled; the display screen is configured to display an image generated by the processors, the memory is configured to store computer program code, and the computer program code includes computer instructions; when the processors execute the computer instructions, the electronic device is caused to execute the interface display method according to any one of the above first aspects.

[0051] In a fourth aspect, the present application provides an electronic device, which includes a display screen, a memory, and one or more processors; the display screen, the memory, and the processors are coupled; the display screen is configured to display an image generated by the processors, the memory is configured to store computer program code, and the computer program code includes computer instructions; when the processors execute the computer instructions, the electronic device is caused to execute the interface display method according to any one of the above second aspects.

[0052] In a fifth aspect, the present application provides a computer-readable storage medium, including computer instructions, which when running on an electronic device, cause the electronic device to execute the interface display method according to any one of the above first aspects.

[0053] In a sixth aspect, the present application provides a computer-readable storage medium, including computer instructions, which when running on an electronic device, cause the electronic device to execute the interface display method according to any one of the above second aspects.

[0054] In a seventh aspect, the present application provides a computer program product, which when running on an electronic device, causes the electronic device to execute the interface display method according to any one of the above first aspects.

[0055] In an eighth aspect, the present application provides a computer program product, which when running on an electronic device, causes the electronic device to execute the interface display method according to any one of the above second aspects.

[0056] It can be understood that for the beneficial effects that can be achieved by the interface display method described in the above second aspect, the electronic devices described in the third and fourth aspects, the computer-readable storage media described in the fifth and sixth aspects, and the computer program products described in the seventh and eighth aspects, reference may be made to the beneficial effects in the first aspect and any of its possible design manners, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1ASchematic diagram one of the interface for starting a game application provided by an embodiment of this application;

[0058] Figure 1B Schematic diagram of the interface for starting a game application provided by an embodiment of this application Figure 2 ;

[0059] Figure 1C Schematic diagram of the interface for starting a game application provided by an embodiment of this application Figure 3 ;

[0060] Figure 1D Schematic diagram one of the interface display provided by an embodiment of this application;

[0061] Figure 1E Schematic diagram of the interface display provided by an embodiment of this application Figure 2 ;

[0062] Figure 1F Schematic diagram of the interface display provided by an embodiment of this application Figure 3 ;

[0063] Figure 1G Schematic diagram of the interface display provided by an embodiment of this application Figure 4 ;

[0064] Figure 1H Schematic diagram of the interface display provided by an embodiment of this application Figure 5 ;

[0065] Figure 2 Schematic diagram of the resolution selection provided by an embodiment of this application;

[0066] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of this application;

[0067] Figure 4 Schematic diagram of the framework of an electronic device provided by an embodiment of this application;

[0068] Figure 5 Schematic diagram one of the process of the interface display method provided by an embodiment of this application;

[0069] Figure 6A Schematic diagram one of the interface of a window state provided by an embodiment of this application;

[0070] Figure 6B Schematic diagram of the interface of a window state provided by an embodiment of this application Figure 2 ;

[0071] Figure 6C Schematic diagram of the interface of a window state provided by an embodiment of this application Figure 3 ;

[0072] Figure 7 A schematic diagram of a decision tree training process provided by an embodiment of the present application;

[0073] Figure 8 A schematic diagram of a decision tree structure provided by an embodiment of the present application;

[0074] Figure 9A A schematic diagram of a game scenario one provided by an embodiment of the present application;

[0075] Figure 9B A schematic diagram of a game scenario provided by an embodiment of the present application Figure 2 ;

[0076] Figure 10 A flowchart of an interface display method provided by an embodiment of the present application Figure 2 ;

[0077] Figure 11 A schematic diagram of a GUE service provided by an embodiment of the present application. Detailed implementation manners

[0078] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this embodiment, unless otherwise stated, the meaning of "a plurality" is two or more.

[0079] For the convenience of understanding the present application, some terms related to the embodiments of the present application will be introduced first below.

[0080] Super-resolution (SR) rendering technology: Also known as the super-resolution rendering algorithm, it refers to reconstructing a corresponding high-resolution image from a low-resolution image.

[0081] Information gain: An index used to evaluate the contribution degree of a feature to a classification task. In the embodiments of the present application, information gain can be used to evaluate the correlation (or called the degree of correlation) between a feature and the function of enabling super-resolution rendering.

[0082] Overfitting: It refers to the situation where the target decision tree performs well on the training samples but poorly on the new samples. Simply put, in the embodiments of the present application, the target decision tree cannot accurately predict whether to enable the super-resolution rendering function.

[0083] Processor frequency point: It refers to the clock frequency when the processor is working, usually in hertz (Hz). The higher the processor frequency point, the faster the processor processes data and instructions.

[0084] Frame rate: It refers to the number of image frames displayed per unit of time (such as 1 second). It is usually expressed in frames per second (FPS).

[0085] Refresh rate: It refers to the number of times the screen is refreshed per unit of time.

[0086] During the operation of an electronic device (such as a mobile phone), it is often necessary to render images (i.e., interfaces and screens) of different applications. For example, when the user clicks on the icon 10 of a game application as shown in Figure 1A the mobile phone responds to the click operation on the icon 10 of the game application and starts the game application. During the startup process, the mobile phone can display the loading startup content (such as the startup animation 11 as shown in Figure 1B ), and there are no controls available for the user to operate in this startup content. After the startup content is loaded, it indicates that the game application has started successfully, and the mobile phone can display the login interface 12 as shown in Figure 1C . This login interface 30 can be used to input user account, password and other information. After successful login, the mobile phone can display the game hall interface 13 as shown in Figure 1D . This game hall interface 13 can include user information such as the user's avatar 14, name 15 and level 16, and can also include game mode information such as online mode and single-player mode. The user can select a game mode by clicking on any game mode. After that, the electronic device can render and display the interface corresponding to the game mode (such as the game screen in the scope scene as shown in Figure 1E ) to enable the user to experience the game.

[0087] For another example, the mobile phone renders and displays the image of a video application. For example, when the video application on the mobile phone plays the XX movie, it displays the picture in the XX movie (as shown in Figure 1F ). For another example, the mobile phone renders and displays the image of a short video application. For example, the mobile phone renders and displays the image in the short video (as shown in Figure 1G ).

[0088] For another example, the mobile phone renders and displays the image of a camera application. As shown in Figure 1H , the mobile phone is in the video recording state and renders and displays the image in the recorded video. Optionally, this image can be a preview image.

[0089] With the development of technology, the resolution of the applied images has evolved to a higher level. For example, the resolution of images has evolved from 720P (1280×720) to 1080P (1920×1080), and then from 1080P to 2K (2560×1440). However, when an electronic device renders images with high resolutions (such as 1080P, 2K, etc.), the computing power resources of the electronic device are consumed excessively, resulting in an increase in the power consumption of the electronic device, thereby causing the electronic device to have a heat problem.

[0090] To solve the problem of reducing the power consumption of an electronic device, the electronic device can render low-resolution images through a graphics processing unit (GPU). Then, the electronic device (such as the accelerated processing unit (APU) in the electronic device) can continue to reconstruct the corresponding high-resolution image from the low-resolution image based on the super-resolution rendering technology, thereby reducing the power consumption of the electronic device while obtaining a high-resolution image. For example, to improve the clarity of the game screen, the user can select the resolution of the game screen to be 1080P (as Figure 2 shown). In response to the resolution selection operation input by the user, the mobile phone can first render a game screen with a resolution of 720P, and then the mobile phone uses the super-resolution rendering technology to increase the resolution of the game screen to be close to 1080P.

[0091] It should be understood that the image quality of the game screen with a resolution close to 1080P rendered using the super-resolution rendering technology is lower than that of the 1080P game screen normally rendered without using the super-resolution rendering technology (or described as lower than the image quality of the game with the original resolution).

[0092] In some embodiments, the effective mode of the applied super-resolution rendering function is either full-scene effective or full-scene ineffective. Among them, full-scene effective can be that, through pre-configuration (such as configuration before the electronic device leaves the factory), after setting the application to use the super-resolution rendering technology, then when the electronic device renders the images of this application, it will use the super-resolution rendering technology for rendering. Full-scene ineffective can be that if the application is configured not to use the super-resolution rendering technology, then when the electronic device renders the images of this application, it will not use the super-resolution rendering technology for rendering. However, for the full-scene effective mode, during the operation of the application, the load of the electronic device may be relatively low, but at this time, the electronic device will still use the super-resolution rendering technology to render the images of the application, resulting in unnecessary image quality loss. Or, in some scenarios (such as the game hall scenario), the user has a lower requirement for image quality, but the electronic device still uses the super-resolution rendering technology to render a high-resolution image, thereby causing unnecessary power consumption loss.

[0093] In view of the above problems, the present application provides an interface display method. During the operation of an application, an electronic device can, based on the scene information of the application at the current time (i.e., the current scene information), integrate the current device state information of the electronic device to evaluate whether it is necessary to enable the super-resolution rendering function, so as to achieve the adaptive enabling or disabling of the super-resolution rendering function. After determining to enable the super-resolution rendering function, the mobile phone can use the super-resolution rendering technology to render the image to be rendered of the application to obtain a target image. Then, the mobile phone can display the target image. The resolution of the target image is less than or greater than the set resolution corresponding to the application, and the set resolution can be the resolution selected by the user or the resolution automatically selected by the mobile phone. When the resolution of the target image is less than the set resolution, unnecessary power consumption loss of the electronic device can be avoided, the power consumption of the electronic device can be reduced, the battery life of the electronic device can be extended, the risks of the electronic device having heat problems and lags can be reduced, and to a certain extent, the image quality of the application can be ensured. When the resolution of the target image is greater than the set resolution, the image quality requirements in specific scenarios can be met, the immersive experience of the user can be ensured, and the user satisfaction can be improved.

[0094] Exemplarily, the electronic device in the embodiments of the present application can be a mobile phone, a tablet computer, a wearable device (such as a smart watch), a personal digital assistant (PDA), a notebook computer, a desktop computer, a vehicle-mounted device, an Internet of Things device, etc., which can install application programs. The embodiments of the present application do not impose special restrictions on the specific form of the electronic device.

[0095] Exemplarily, Figure 3 shows a schematic structural diagram of an electronic device 200. As Figure 3 shown, the electronic device 200 may include a processor 210, an external memory interface 220, an internal memory 221, a universal serial bus (USB) interface 230, a charging management module 211, a power management module 212, a battery 213, an antenna 1, an antenna 2, a mobile communication module 240, a wireless communication module 250, an audio module 270, a speaker 270A, a receiver 270B, a microphone 270C, a headphone interface 270D, a sensor module 280, a key 290, a motor 291, an indicator 292, a camera 293, a display screen 294, and a subscriber identification module (SIM) card interface 295, etc.

[0096] It can be understood that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on the electronic device 200. In some other embodiments of the present application, the electronic device 200 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0097] The processor 210 may include one or more processing units. For example, the processor 210 may include an application processor (AP), a modem processor, a GPU, an image signal processor (ISP), an APU, a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0098] Among them, the above-mentioned processor 210 may further include a central processing unit (CPU).

[0099] Among them, the controller may be the nerve center and command center of the electronic device 200. The controller can generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.

[0100] A memory may also be provided in the processor 210 for storing instructions and data. In some embodiments, the memory in the processor 210 is a cache memory. This memory can save the instructions or data that the processor 210 has just used or recycled. If the processor 210 needs to use the instruction or data again, it can directly call it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 210, and thus improves the efficiency of the system.

[0101] In some embodiments, the processor 210 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0102] It can be understood that the interface connection relationships among the modules illustrated in the embodiments of the present invention are only illustrative and do not constitute a structural limitation on the electronic device 200. In some other embodiments of the present application, the electronic device 200 may also adopt different interface connection manners in the above embodiments, or a combination of multiple interface connection manners.

[0103] The charging management module 211 is configured to receive a charging input from a charger. In some embodiments of wireless charging, the charging management module 211 may receive a wireless charging input through the wireless charging coil of the electronic device 200. While charging the battery 213, the charging management module 211 may also supply power to the electronic device through the power management module 212.

[0104] The wireless communication function of the electronic device 200 may be implemented by antenna 1, antenna 2, the mobile communication module 240, the wireless communication module 250, the modulation and demodulation processor, and the baseband processor, etc.

[0105] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in the electronic device 200 may be used to cover a single or multiple communication frequency bands. Different antennas may also be multiplexed to improve the utilization rate of the antennas.

[0106] The mobile communication module 240 may provide solutions for wireless communications such as 2G / 3G / 4G / 5G applied to the electronic device 200. The mobile communication module 240 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc. The mobile communication module 240 may receive electromagnetic waves through antenna 1, filter, amplify, and perform other processing on the received electromagnetic waves, and then transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 240 may also amplify the signal modulated by the modulation and demodulation processor and convert it into electromagnetic waves through antenna 1 for radiation. In some embodiments, at least some functional modules of the mobile communication module 240 may be disposed in the processor 210. In some embodiments, at least some functional modules of the mobile communication module 240 and at least some modules of the processor 210 may be disposed in the same device.

[0107] The modulation and demodulation processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. Subsequently, the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After being processed by the baseband processor, the low-frequency baseband signal is transmitted to the application processor. The application processor outputs a sound signal through an audio device (not limited to the speaker 270A, receiver 270B, etc.), or displays an image or video through the display screen 294. In some embodiments, the modulation and demodulation processor may be an independent device. In other embodiments, the modulation and demodulation processor may be independent of the processor 210 and disposed in the same device as the mobile communication module 240 or other functional modules.

[0108] The wireless communication module 250 can provide solutions for wireless communications applied to the electronic device 200, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. The wireless communication module 250 can be one or more devices integrating at least one communication processing module. The wireless communication module 250 receives electromagnetic waves via the antenna 2, performs frequency modulation and filtering processing on the electromagnetic wave signals, and sends the processed signals to the processor 210. The wireless communication module 250 can also receive the signals to be sent from the processor 210, perform frequency modulation and amplification on them, and convert them into electromagnetic waves through the antenna 2 and radiate them out.

[0109] The electronic device 200 realizes the display function through the GPU, the display screen 294, and the application processor, etc. The GPU is a microprocessor for image processing, and is connected to the display screen 294 and the application processor. The GPU is used to execute mathematical and geometric calculations and for graphics rendering. The processor 210 may include one or more GPUs, which execute program instructions to generate or change display information.

[0110] The display screen 294 is used to display images, videos, etc. The display screen 294 includes a display panel. The display panel can adopt a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-OLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 200 may include 1 or N display screens 294, where N is a positive integer greater than 1.

[0111] The electronic device 200 can realize the shooting function through the ISP, the camera 293, the video codec, the GPU, the display screen 294, and the application processor, etc.

[0112] The ISP is used to process the data fed back by the camera 293. In some embodiments, the electronic device 200 may include one or N cameras 293, where N is a positive integer greater than 1.

[0113] The digital signal processor is used to process digital signals. In addition to processing digital image signals, it can also process other digital signals. For example, when the electronic device 200 is selecting a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy, etc.

[0114] The video codec is used to compress or decompress digital videos. The electronic device 200 can support one or more video codecs. In this way, the electronic device 200 can play or record videos in multiple encoding formats, such as: Moving Picture Experts Group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0115] The NPU is a neural-network (NN) computing processor. By learning from the structure of biological neural networks, such as learning from the transmission mode between human brain neurons, it can quickly process input information and can also continuously self-learn. Through the NPU, applications such as intelligent cognition of the electronic device 200 can be realized, such as: image recognition, face recognition, voice recognition, text understanding, etc.

[0116] The external memory interface 220 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 200.

[0117] The internal memory 221 can be used to store computer-executable program code, and the executable program code includes instructions. The processor 210 executes various functional applications and data processing of the electronic device 200 by running the instructions stored in the internal memory 221. The internal memory 221 can include a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as the sound playback function, the image playback function, etc.). The data storage area can store the data created during the use of the electronic device 200 (such as sound, phone book, etc.). In addition, the internal memory 221 can include high-speed random access memory and can also include non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0118] The electronic device 200 can implement audio functions through the audio module 270, speaker 270A, receiver 270B, microphone 270C, headphone jack 270D, and application processor, etc. For example, music playback, recording, etc.

[0119] The keys 290 include a power-on key, volume keys, etc. The keys 290 can be mechanical keys or touch keys.

[0120] The indicator 292 can be an indicator light, which can be used to indicate the charging state, power change, and can also be used to indicate messages, missed calls, notifications, etc.

[0121] The sensor module 280 can include a pressure sensor, gyroscope sensor, barometric pressure sensor, magnetic sensor, acceleration sensor, distance sensor, proximity light sensor, fingerprint sensor, temperature sensor, touch sensor, ambient light sensor, bone conduction sensor, etc.

[0122] The software system of the electronic device 200 can adopt a layered architecture, event-driven architecture, microkernel architecture, microservices architecture, or cloud architecture. In the embodiments of the present invention, the Android system with a layered architecture is taken as an example to exemplarily illustrate the software structure of the electronic device 200.

[0123] Figure 4 It is a structural block diagram of the electronic device 200 in the embodiments of the present invention.

[0124] The layered architecture divides the software into several layers, and each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into five layers, from top to bottom are the application layer, application framework layer, native and lib (Libraries) layer, user-mode driver layer, and driver layer.

[0125] The application layer can include a series of application packages.

[0126] Such as Figure 4 As shown, the application packages can include applications such as video, camera, short video, game applications, calendar, etc.

[0127] The application framework layer provides application programming interfaces (APIs) and programming frameworks for the applications in the application layer. The application framework layer includes some predefined functions.

[0128] Such as Figure 4 As shown, the application framework layer can include a screen information determination module (APS module), thermal module, game kit module, and load calculation module.

[0129] Among them, as Figure 4 shown, the APS module can be used to determine the screen resolution and the screen refresh rate of the electronic device 200. Among them, the screen resolution can be automatically determined by the electronic device 200 after the intelligent resolution switch is turned on, or it can be a custom resolution.

[0130] The thermal module can be used to determine the application configuration information and the temperature of the electronic device 200. The application configuration information indicates whether the target application is started, so that the thermal module can accurately obtain the temperature of the electronic device 200 after the target application is started. Among them, the target application can represent an application that the electronic device 200 can use the super-resolution rendering technology to render, that is, after the target application is started, the electronic device 200 needs to determine whether to turn on the super-resolution rendering function. Application scenarios such as the above-mentioned video, camera, short video, and game applications can be target applications. The calendar may not be a target application.

[0131] Optionally, the above-mentioned target application may include a game application, and the application configuration information may include game configuration information.

[0132] The game toolkit module can be used to identify the current scene of the game application (or called the game scene), such as the shooting scene, the scope scene, the game hall scene, the battle scene, etc., and this scene can be used as the current scene information. And the game toolkit module can also obtain the resolution set by the user (as shown above Figure 2 shown, the user sets the resolution of the game application to 1080P).

[0133] The load calculation module is used to calculate the load size of the electronic device 200. Optionally, the load of the electronic device 200 may include GPU load and / or CPU load. Among them, the above-mentioned load calculation module may include a U3d (unity3D) / UE (unrealengine) module.

[0134] As Figure 4 shown, the native and lib layers may include services for the accelerate graphical port (AGP), rendering services, and the game super engine GUE service.

[0135] Among them, the AGP service is used to detect the frame rate and perform frame rate control. Frame rate control means automatically adjusting the frame rate.

[0136] The rendering service can be used to implement the AI Rendering function, that is, to render the image of the target application using the super-resolution rendering technology.

[0137] The GUE service can be used to implement scenario recognition, model decision-making, dynamic start / stop, and status management. Among them, status management refers to obtaining the current device status information of the electronic device 200, such as temperature, load, etc.

[0138] Scenario recognition is used to identify the scenario where the application is currently located. Among them, the current scenario information can be recognized by the GUE service or recognized by the above-mentioned game toolkit module.

[0139] Model decision-making refers to obtaining a prediction result adapted to the current scenario and device status based on the current device status information, current scenario information, and in combination with the target decision tree model. Optionally, the prediction result can include a prediction probability, which represents the probability of enabling the super-resolution rendering function.

[0140] Dynamic start / stop refers to determining whether to enable the super-resolution rendering function based on the prediction result.

[0141] As Figure 4 shown, the user-mode driver layer can include a graphics system layer (graphics system layer, GSL) and a hardware composer (hw composer).

[0142] Among them, the graphics system layer is used to manage graphics display and the drawing of the user interface.

[0143] Hw composer is a component in the Android system and is responsible for combining the graphics elements of the application into the final image.

[0144] As Figure 4 shown, the driver layer can include processor drivers, such as GPU drivers (driver) and display drivers.

[0145] In some embodiments, the software layer can communicate with the hardware layer of the electronic device 200. For example, the software layer can drive the GPU to render the application interface through the GPU driver.

[0146] In some embodiments, the above-mentioned native and lib layers, as well as the above-mentioned user-mode driver layer, can also serve as the runtime and system library layers, and the above-mentioned driver layer can also serve as the kernel layer.

[0147] It should be understood that the structure of the software layer introduced above is only an example, and the present application does not limit the structure of the software layer, that is, the software layer can include one or more of the above-mentioned application layer, application framework layer, native and lib layers, user-mode driver layer, and driver layer, or the software layer can also include other layers.

[0148] An embodiment of the present application provides an interface display method, which can be applied to a scenario of rendering an image of an application. For example, the application can be a game application, a short video application, a video application, a camera application, a social application, or other applications. After the application is started, the electronic device can use active scenario information (or referred to as scenario information, which represents the running stage of the application) and passive scenario information (or referred to as device status information) to decide whether to enable the super-resolution rendering function through a target decision tree, that is, consider whether to enable the super-resolution rendering function from different dimensions, so as to accurately and adaptively start and stop the super-resolution rendering function. To ensure the accuracy of the decision-making, the electronic device needs to pre-train the initial decision model with training samples to obtain a target decision tree that can accurately make decisions.

[0149] Next, taking the above-mentioned electronic device as a mobile phone and the application as a game application as an example, the interface display method provided by the present application will be introduced. As Figure 5 shown, the interface display method may include S301 - S311.

[0150] S301. The mobile phone obtains multiple training samples. Each of the multiple training samples includes scenario sample information corresponding to the game application, device status sample information, and an expected result corresponding to the scenario sample information and the device status sample information.

[0151] The expected result corresponding to the scenario sample information and the device status sample information represents whether the user expects to enable the super-resolution rendering function in the scenario corresponding to the scenario sample information and the device status corresponding to the device status sample information. Exemplarily, the expected result may include an expected result of enabling the super-resolution rendering. Optionally, the expected result may further include an expected result of disabling the super-resolution rendering.

[0152] The application scenario sample information corresponding to the game application in the above training samples represents the scenario in which the game application is located. For example, a scope scene, an airplane scene, a shooting scene, a combat scene (such as a world combat scene, a dungeon combat scene), a game lobby scene, etc. Optionally, the application scenario can be understood as the running stage of the application.

[0153] The device status sample information in the above training samples reflects the status information of the mobile phone in the application scenario corresponding to the scenario sample information in the training sample. Exemplarily, the device status sample information may include at least one of device form, device window status, temperature, jitter rate, remaining battery power, charging status, network latency, load, screen refresh rate, screen resolution, and frame rate.

[0154] Among them, the above device form indicates that the mobile phone is in a folded state, an unfolded state, or a straight-bar phone state. When the mobile phone is a foldable mobile phone, the device form of the mobile phone can be a folded state or an unfolded state. When the mobile phone is not a foldable mobile phone, the device form of the mobile phone is a straight-bar phone state.

[0155] The above device window state includes a multi-window state or a single-window state. The single-window state means that the mobile phone displays the window of the game application without simultaneously displaying the windows of other applications. For example, Figure 1E when the mobile phone displays the window of the game application, the device window state of the mobile phone is the single-window state.

[0156] The multi-window state means that the mobile phone simultaneously displays the windows of multiple applications, and the multiple applications include the game application and at least one other application. Optionally, the multi-window state can include a split-screen state (as Figure 6A shown, the mobile phone simultaneously displays the window 31 of the game application and the window 30 of the Q&A application) and a floating display state. Among them, the floating display state means that the window of the game application floats above the windows of other applications (as Figure 6B shown, the window 32 of the game application floats above the window 33 of the Q&A application), or the window of other applications floats above the window of the game application (as Figure 6C shown, the window 34 of the Q&A application floats above the window 35 of the game application).

[0157] The above temperature represents the temperature of the mobile phone. The jitter rate represents the stability of the mobile phone. A high jitter rate of the mobile phone indicates that the rendering is discontinuous and unstable, that is, there is a lag problem.

[0158] The charging state indicates whether the mobile phone is charging, and it can include a charging state and a non-charging state.

[0159] The network delay time represents the time difference from when the network sends data to when the receiving party receives the data. Simply put, it represents the time required for data to be transmitted in the network.

[0160] The load can include the GPU load and / or the CPU load of the mobile phone.

[0161] For example, a training sample includes a battle scene, the GPU load is 80, the temperature is 45 degrees, the charging state, and the super-resolution rendering function is enabled. Among them, the battle scene represents the scene sample information, the GPU load, the temperature, and the charging state are the device state sample information, and the expected enabling of the super-resolution rendering function refers to the expected result. This training sample means that when the game application is in the battle scene, when the GPU load of the mobile phone is 50, the temperature is 37 degrees, and it is in the charging state, it indicates that the load of the mobile phone is relatively large, and the power consumption of the mobile phone needs to be reduced to avoid the problem of the mobile phone getting hot, and the user expects the mobile phone to enable the super-resolution rendering function.

[0162] In some embodiments, the directions in which the super-resolution rendering technology is applied are mainly divided into two types. One direction is to render an image with a quality close to the original resolution based on "subtraction first and addition later", so that even when the user selects a high resolution, the power consumption of the mobile phone is relatively low, thereby avoiding heat generation and power consumption problems. The other direction is to provide a higher resolution to obtain an image with a quality higher than the original resolution. For example, if the resolution selected by the user is 2K resolution, the mobile phone uses the super-resolution rendering technology to render an image with a resolution higher than 2K.

[0163] Correspondingly, the expected activation of the super-resolution rendering function in the above expected results may include the expected activation of the low-resolution rendering function and the expected activation of the high-resolution rendering function. Among them, the expected activation of the low-resolution rendering function corresponds to the above one direction and is mainly used to render an image with a resolution lower than the original resolution to reduce power consumption. The expected activation of the high-resolution rendering function corresponds to the above other direction and is mainly used to render an image with a resolution higher than the original resolution to improve the image quality and ensure the user's immersive experience.

[0164] The above scene sample information and device state sample information may be features (or called factors) related to whether to activate the super-resolution rendering function. For example, the game hall scene has relatively low requirements for image quality. Therefore, the super-resolution rendering function can be activated to reduce power consumption and avoid occupying unnecessary resources. While the scope scene has relatively high requirements for image quality. Therefore, the super-resolution rendering function (such as activating the improvement) can be activated to improve the image quality of the game and enhance the user's immersive gaming experience.

[0165] For another example, compared with the folded state and the straight-bar state, the unfolded state has a larger screen size, higher requirements for resolution, and a greater demand for activating the super-resolution rendering function (such as activating the high-resolution rendering function) to obtain a higher resolution.

[0166] For another example, compared with the single-window state, when the device window state of the mobile phone is in the multi-window state, the image quality can be reduced. Correspondingly, the user has a greater demand for activating the super-resolution rendering function to obtain an image close to the original resolution.

[0167] Among them, optionally, when the multi-window state is the split-screen state or the window of the game application is in the floating state (that is, the window of the game application floats above the windows of other applications), the window size of the game application is relatively small, the requirements for image quality are relatively low, and there is a greater demand for activating the super-resolution rendering function (such as activating the low-resolution rendering function) to obtain a lower image quality.

[0168] For another example, when the temperature of the mobile phone is relatively high, the mobile phone has a greater demand for enabling the super-resolution rendering function (such as enabling the low-resolution rendering function) to reduce the power consumption of the mobile phone, thereby reducing the temperature of the mobile phone.

[0169] For another example, when the remaining battery power of the mobile phone is relatively low, the mobile phone has a greater demand for enabling the super-resolution rendering function to reduce the power consumption of the mobile phone. For another example, when the charging state of the mobile phone is the non-charging state, the mobile phone has a greater demand for enabling the super-resolution rendering function to reduce the power consumption of the mobile phone.

[0170] For another example, when the network latency time of the mobile phone is relatively large, the user has a greater demand for enabling the super-resolution rendering function to reduce the network latency time required for downloading the images of the game application. It can be understood that after the mobile phone enables the super-resolution rendering function, the mobile phone can download low-resolution images from the server corresponding to the game application, and then the mobile phone can use the super-resolution rendering technology to render the low-resolution images to obtain images close to the original resolution based on the low-resolution images. Thereby reducing the network latency time for transmitting the images of the game application.

[0171] For another example, when the jitter rate of the mobile phone is relatively high, it indicates that the possibility of the mobile phone experiencing lag is relatively high, and the user has a greater demand for enabling the super-resolution rendering function to reduce the load. For another example, when the load of the mobile phone is relatively large, the mobile phone has a greater demand for enabling the super-resolution rendering function to reduce the load of the mobile phone.

[0172] It should be noted that the scenarios included in the above scenario sample information and the status information included in the device status information are only examples, and the scenarios and status information can be set according to the actual situation.

[0173] S302. The mobile phone inputs multiple training samples into the initial decision tree to train the initial decision tree to obtain a target decision tree. Among them, the target decision tree can predict the probability of enabling the super-resolution rendering function during the operation of the game application.

[0174] Among them, the target decision tree can predict the probability of enabling the super-resolution rendering function in different scenarios and different device states after the game application is started.

[0175] In some embodiments, the training process of the initial decision tree can be a process of adjusting the structure of the decision tree. As Figure 7 shown, this process may include: Step 1, feature selection and analysis. Exemplarily, Step 1 may include Steps a1 and b1. Among them, in Step a1, the mobile phone can determine the correlation degree corresponding to the features (including the scenarios included in the above scenario sample information and the status information included in the device status sample information).

[0176] Among them, the correlation degree corresponding to a feature represents the magnitude of the correlation between the feature and the classification result (here it can be whether to enable the super-resolution rendering function), that is, it affects the level of the classification result. Subsequently, the mobile phone can use the correlation degree corresponding to each feature to select target features from each feature. The target feature represents a feature with a relatively high correlation degree with the expected result (such as a feature higher than a certain correlation threshold). Optionally, the correlation degree is represented by information gain. For each feature, the mobile phone can calculate the information gain corresponding to the feature based on the training samples. Subsequently, the mobile phone can use the features with information gain greater than or equal to the preset gain as target features to achieve feature screening and avoid interference from irrelevant features to the classification result.

[0177] Step b1: The mobile phone can assign corresponding weights to the target features based on the correlation degree corresponding to the target features. Among them, the higher the correlation degree corresponding to the target feature, the higher the weight corresponding to the target feature. It should be understood that the mobile phone can preset rules to assign corresponding weights to the target features. The preset rules can be set according to the actual situation, as long as the sum of the weights corresponding to each target feature is equal to 1.

[0178] After determining the target features and the weights corresponding to the target features, the mobile phone can continue to execute Step 2: Use the target features to train the initial decision tree. Exemplarily, Step 2 can include Step a2 and Step b2. Among them, in Step a2, the mobile phone takes all the training samples as the root node of the initial decision tree, takes the preset classification conditions corresponding to each target feature as the child nodes of the initial decision tree, and takes the decision result as the leaf node of the initial decision tree.

[0179] Specifically, in the initial decision tree, the child nodes can be connected by branches. The branch connection means that a child node has different branches, that is, it corresponds to different child nodes. The mobile phone can execute the preset classification conditions corresponding to the corresponding branches according to the different judgment results corresponding to the preset classification conditions of the child node. For example, the target features can include load, temperature, and device form. The preset classification condition corresponding to the load is whether the load is less than the load value 1, the preset classification condition corresponding to the temperature is whether the temperature is less than the temperature 1, and the preset classification condition corresponding to the device form is whether the device form is in the unfolded state. Correspondingly, the connection relationship between the child nodes can be as Figure 8 shown. The branch corresponding to the child node 1 corresponding to the load can include the child node 2 corresponding to the device form and the child node 3 corresponding to the temperature.

[0180] Optionally, the distribution positions of the above child nodes, that is, the execution order of the preset classification conditions corresponding to the child nodes, can be determined according to the correlation degree corresponding to the target features corresponding to the child nodes. For example, the higher the correlation degree corresponding to the target feature, the earlier the execution order of the preset classification condition corresponding to the target feature, and the closer the distribution position of the child node is to the root node.

[0181] Step b2: For each child node, the mobile phone determines the judgment result corresponding to each training sample for the child node based on the preset classification condition corresponding to the child node and the value of the target feature in each training sample. Here, the judgment result is 0 or 1. The judgment result of 0 indicates that the super-resolution rendering function is turned off. The judgment result of 1 indicates that the super-resolution rendering function is turned on.

[0182] Continuing with the above example, when the judgment result corresponding to child node 1 is 1, the mobile phone continues to execute the preset classification condition corresponding to child node 2. When the judgment result corresponding to child node 1 is 0, the mobile phone continues to execute the preset classification condition corresponding to child node 3.

[0183] Step c: For each training sample, the mobile phone can perform a weighted calculation based on the judgment results corresponding to each child node of the training sample and the weights corresponding to each child node to obtain the decision result corresponding to the training sample. The decision result indicates whether to predict to turn on the super-resolution rendering function. Exemplarily, after the weighted calculation, the mobile phone can obtain a decision probability for using the decision probability to determine the decision result. For example, when the decision probability is greater than a certain threshold, it is determined that the decision result is to predict to turn on the super-resolution rendering function. When it is less than or equal to a certain threshold, it is determined that the decision result is to predict to turn off the super-resolution rendering function.

[0184] Continuing with the above example, for training sample 1, the load in the training sample 1 is less than the load value 1, so the judgment result corresponding to child node 1 is 1. The mobile phone continues to execute the preset classification condition corresponding to child node 2. The device form in training sample 1 is a folded state, so the judgment result corresponding to child node 2 is 0. Correspondingly, the decision probability = the weight corresponding to 1 * child node 1 (i.e., load) + the weight corresponding to 0 * child node 2 (i.e., device form).

[0185] After obtaining the decision results corresponding to each training sample, the mobile phone can continue to adjust the initial decision tree based on the decision results corresponding to the training samples and in combination with the expected results corresponding to the training samples, such as adjusting the distribution position of the child nodes, the selection of the target feature, the preset classification conditions corresponding to the child nodes, etc., until the adjusted initial decision tree meets the preset stop condition, such as the matching rate between the expected result and the decision result corresponding to the training sample output by the adjusted initial decision tree exceeds the preset matching rate. Simply put, when the adjusted initial decision tree can accurately predict whether to turn on the super-resolution rendering function, the mobile phone can use the adjusted initial decision tree as the target decision result.

[0186] In some embodiments, after obtaining the target decision tree, as described above Figure 7As shown, the mobile phone can execute step 3 to prune and optimize the target decision tree to avoid overfitting problems. Optionally, the above pruning optimization can be pre-pruning or post-pruning.

[0187] It should be noted that the above training samples include training samples corresponding to game applications, such as scene sample information, device status sample information, and expected results corresponding to game applications, which are only examples. When it is necessary to predict whether the super-resolution rendering function needs to be enabled after other applications are launched, the training samples can also include training samples corresponding to other applications. For example, when it is necessary to predict the probability of whether to enable the super-resolution rendering function after the short video application is launched, the above training samples can include training samples corresponding to the short video application, and the training samples corresponding to the short video application can include scene sample information, device status sample information, and expected results corresponding to the short video application.

[0188] After obtaining the target decision tree, the mobile phone can apply the target decision tree to decide whether to enable the super-resolution rendering function after the game application is launched. The application process of the target decision tree can be further introduced below.

[0189] S303. The mobile phone receives a start operation on the game application.

[0190] Exemplarily, the above start operation can be a click operation by the user on the icon of the game application displayed on the mobile phone desktop (as shown above Figure 1A ). Of course, the start operation can also be other operations that can trigger the start of the game application. For example, the start operation is an operation where the user clicks on an application in the background applications displayed on the mobile phone, or the start operation is a jump operation. The mobile phone displays the interface of application A, and this interface includes the link information of the game application. The user clicks on this link information, and the mobile phone jumps into the game application in response to the user's click operation on this link information. The type of the start operation is not limited in this application, as long as it can trigger the mobile phone to start the game application.

[0191] S304. In response to the above start operation on the game application, the mobile phone starts the game application.

[0192] S305. After the game application is launched, the mobile phone obtains the current scene information and current device status information of the game application.

[0193] Exemplarily, after the game application is launched, the mobile phone can obtain the current scene information and current device status information in real time to realize the real-time judgment of the start and stop of the super-resolution rendering function, so as to realize the timely start and stop of the super-resolution rendering function. Or, the mobile phone can obtain the current scene information and current device status information of the game application every preset time, reduce the number of information acquisitions, and can ensure the timely start and stop of the super-resolution rendering function to a certain extent.

[0194] Alternatively, when the game scenario or device state changes, the mobile phone can obtain the current scenario information and current device state information of the game application, so as to use the current scenario information and current device state information to determine whether to enable the super-resolution rendering function, avoiding the acquisition of unnecessary information.

[0195] It can be understood that the information included in both the current scenario information and the current device state information is the value of the target feature. In other words, the number of features corresponding to both the current scenario information and the device state information is less than or equal to the number of features corresponding to the above-mentioned scenario sample information and device state sample information. For example, the current device state information includes at least one of device form, device window state, temperature, jitter rate, remaining battery power, charging state, network latency, load, screen refresh rate, screen resolution, and frame rate.

[0196] In some embodiments, after the application (such as the above-mentioned game application) is launched, the mobile phone can first determine whether the game application belongs to a preset application. The preset application refers to an application that can trigger the mobile phone to use the super-resolution rendering algorithm for rendering. In other words, the preset application refers to an application in which the super-resolution rendering function takes effect in the entire scene.

[0197] Among them, the above-mentioned preset application can be set before the mobile phone leaves the factory, or can be set by the user during the use of the mobile phone.

[0198] If the game application does not belong to the preset application, it indicates that the game application cannot trigger the mobile phone to use the super-resolution rendering algorithm to render the interface, that is, it indicates that rendering the interface of the game application does not consume a lot of resources. Therefore, the mobile phone does not need to determine whether to enable the super-resolution rendering function, and thus does not need to obtain the current scenario information and current device state information of the game application.

[0199] If the game application belongs to the preset application, it indicates that the game application can trigger the mobile phone to use the super-resolution rendering algorithm to render the interface. Therefore, the mobile phone can continue to obtain the current scenario information and current device state information of the game application to determine whether to enable the super-resolution rendering function according to the overall situation of the mobile phone.

[0200] S306. The mobile phone inputs the current scenario information and current device state information of the game application into the target decision tree to obtain a prediction probability corresponding to the current scenario information and current device state information. Among them, the prediction probability represents the probability of predicting to enable the super-resolution rendering function.

[0201] S307. The mobile phone determines whether the prediction probability is greater than the preset probability threshold.

[0202] In the embodiments of the present application, when the predicted probability is greater than the preset probability threshold, it indicates that the scenario and device state of the mobile phone are suitable for enabling the super-resolution rendering function, and the mobile phone can execute S308. When it is less than or equal to, it indicates that the scenario or device state of the mobile phone is not suitable for enabling the super-resolution rendering function, and the mobile phone can execute S310.

[0203] S308. The mobile phone renders the image to be rendered of the game application based on Resolution 1 corresponding to the game application, using the super-resolution rendering technology, to obtain Target Image 1.

[0204] Among them, the resolution corresponding to Target Image 1 is less than Resolution 1 or greater than Resolution 1.

[0205] Resolution 1 corresponding to the game application represents the currently set resolution of the game application. Resolution 1 can be selected by the user or automatically set by the mobile phone according to the current situation of the mobile phone (such as load, etc.).

[0206] The following introduces, with an example, how to determine whether to enable the super-resolution rendering function according to the current device state information and current scenario information.

[0207] For example, the above-mentioned current scenario information represents a dungeon battle scenario (as Figure 9A shown), and the above-mentioned current device state information may include the current GPU load. As shown in Table 1, in the dungeon battle scenario, the current GPU load is 81.12. The mobile phone inputs the dungeon battle scenario and the current device state information (including this 81.12) into the target decision tree, and the corresponding predicted probability obtained is Probability a. Since Probability a is greater than the preset probability threshold, the mobile phone can enable the super-resolution rendering function to reduce the GPU load, thereby reducing the power consumption of the mobile phone.

[0208] After that, the above-mentioned game application switches to the world scenario (as Figure 9B shown), the current scenario information represents the world scenario. As shown in Table 1, in the world scenario, the current GPU load is 75.86. The mobile phone inputs the world scenario and the current device state information (including this 75.86) into the target decision tree, and the corresponding predicted probability obtained is Probability b. Since Probability b is less than the preset probability threshold, it indicates that in the world scenario and the current device state, the mobile phone does not need to enable the super-resolution rendering function, and the mobile phone can normally render the game images in the world scenario.

[0209] In addition, it can be seen from Table 1 that in the dungeon battle scenario, the GPU load is relatively high and the GPU frequency point is relatively high, resulting in relatively high power consumption of the mobile phone. To reduce the power consumption, the mobile phone enables the super-resolution rendering function. When switching to the world scenario, the CPU load of the mobile phone is relatively low and the frequency is also relatively low, and the mobile phone can turn off the super-resolution rendering function to avoid unnecessary loss of image quality.

[0210] After that, the above game application switches to the world battle scene. The current scene information indicates the world battle scene. As shown in Table 1, in the world battle scene, the current GPU load is 79. The mobile phone inputs the world battle scene and the current device status information (including this 79) into the target decision tree, and the corresponding predicted probability obtained is probability c. Since probability c is less than the preset probability threshold, it indicates that in the world battle scene and under the current device status, the mobile phone does not need to enable the super-resolution rendering function, and the mobile phone can normally render the game images in the world battle scene.

[0211] Table 1

[0212] World scene World battle scene Instance battle scene GPU frequency point 364.94 361.93 429.20 GPU load 75.89 79 81.12

[0213] In some embodiments, based on the above description, the super-resolution rendering function may include a high-resolution rendering function and a low-resolution rendering function. Among them, the high-resolution rendering function is used to render game images with a resolution higher than Resolution 1. The low-resolution rendering function is used to render game images with a resolution lower than Resolution 1. After the mobile phone determines that it needs to enable the super-resolution rendering function, it can continue to combine the current scene information of the game application to determine whether the mobile phone enables the high-resolution rendering function to improve the image quality of the game and ensure the user's immersive gaming experience, or enables the low-resolution rendering function to reduce the image quality of the game, thereby reducing the resources required for the mobile phone to render the game images and reducing the power consumption of the mobile phone.

[0214] Two possible implementation methods for determining whether the mobile phone enables the high-resolution rendering function or the low-resolution rendering function will be introduced below.

[0215] In one implementation method, the above target decision tree may include a first target decision tree, which is used to output a predicted probability 1 (or referred to as the first predicted probability), and this predicted probability 1 represents the probability of enabling the high-resolution rendering function in the super-resolution rendering function. That is to say, the above predicted probability may include the predicted probability 1. Correspondingly, the mobile phone can determine whether this predicted probability 1 is greater than the first preset probability threshold. When the predicted probability 1 is greater than the first preset probability threshold, it indicates that in the current scene and the current device status, it is suitable to render high-resolution game images. Therefore, the mobile phone can enable the high-resolution rendering function.

[0216] The above-mentioned target decision tree may include a second target decision tree, which is used to output a prediction probability 2. This prediction probability 2 (or referred to as the second prediction probability) represents the probability of enabling the high-resolution rendering function in the super-resolution rendering function. That is to say, the above-mentioned prediction probability may include the prediction probability 2. Correspondingly, the mobile phone can determine whether the prediction probability 2 is greater than a second preset probability threshold. When the prediction probability 2 is greater than the first preset probability threshold, it indicates that in the current scenario and current device state, it is suitable to render low-resolution game images. Therefore, the mobile phone can enable the low-resolution rendering function to reduce the power consumption of the mobile phone on the basis of less loss of image quality.

[0217] Optionally, in one case, the above-mentioned prediction probability may only include the prediction probability 1. In other words, the above-mentioned determination of whether to enable the super-resolution rendering function is actually a determination of whether to enable the high-resolution rendering function. That is to say, the target decision tree is used to predict whether to enable the high-resolution rendering function. Correspondingly, when the prediction probability 1 is less than or equal to the first preset probability threshold, the mobile phone can determine to turn off the high-resolution rendering function, that is, turn off the super-resolution rendering function.

[0218] Or, the above-mentioned prediction probability may only include the prediction probability 2. In other words, the above-mentioned determination of whether to enable the super-resolution rendering function is actually a determination of whether to enable the low-resolution rendering function. That is to say, the target decision tree is used to predict whether to enable the low-resolution rendering function. Correspondingly, when the prediction probability 2 is less than or equal to the first preset probability threshold, the mobile phone can determine to turn off the low-resolution rendering function, that is, turn off the super-resolution rendering function.

[0219] In another case, the prediction probability may include the prediction probability 1 and the prediction probability 2. When the prediction probability 1 is less than or equal to the first preset probability threshold and the prediction probability 2 is less than or equal to the second preset probability threshold, the mobile phone can determine to turn off the super-resolution rendering function. When the prediction probability 1 is less than or equal to the first preset probability threshold and the prediction probability 2 is greater than the second preset probability threshold, the mobile phone can determine to enable the low-resolution rendering function. When the prediction probability 1 is greater than the first preset probability threshold and the prediction probability 2 is less than or equal to the second preset probability threshold, the mobile phone can determine to enable the high-resolution rendering function. It should be understood that generally, in this other case, the predicted prediction probability 1 and prediction probability 2 will not be greater than the corresponding preset probability thresholds at the same time.

[0220] It should be noted that the above-mentioned first target decision tree and second target decision tree may be the same decision tree or different decision trees, and the present application does not limit them.

[0221] In another implementation, after determining that the prediction probability is greater than the preset probability threshold, the mobile phone can continue to determine whether to enable the high-resolution rendering function or the low-resolution rendering function in combination with the current scene information. Exemplarily, the mobile phone can determine to enable the high-resolution rendering function when the current scene information belongs to the first preset scene. When the current scene information does not belong to the first preset scene, it is determined to enable the low-resolution rendering function. The first preset scene represents a scene with relatively high requirements for image quality in the game scene of the game application. For example, the first preset scene includes a telescopic sight scene or other game scenes. The scenes included in the first preset scene can be set according to actual needs, and the present application does not limit it.

[0222] Based on this, after determining that the super-resolution rendering function needs to be enabled, it indicates that if the game scene currently running on the mobile phone belongs to a specific scene, it means that the current game scene has relatively high requirements for image quality. Therefore, the mobile phone can enable the high-resolution rendering function, use the super-resolution rendering algorithm to render high-resolution game images, which are not limited to the resolution set by the user, and consume less power. On the basis of ensuring the image quality of the game images, it avoids high power consumption of the mobile phone and improves the user's immersive game experience, thereby improving the user's satisfaction.

[0223] If the game scene running on the mobile phone does not belong to the specific scene, it indicates that the current game scene has relatively low requirements for image quality or the mobile phone currently needs to reduce power consumption. Therefore, the mobile phone can enable the low-resolution rendering function and use the super-resolution rendering algorithm to render low-resolution game images to reduce the power consumption of the mobile phone.

[0224] S309. The mobile phone displays the target image 1.

[0225] The above S308 - S309 introduce the process of the mobile phone enabling the super-resolution rendering function when the prediction probability is greater than the preset probability threshold. Of course, there is also a case where the prediction probability is less than the preset probability threshold. In this case, the mobile phone turns off the super-resolution rendering function. The following will introduce this case in combination with S310 - S311.

[0226] S310. The mobile phone renders the image to be rendered of the game application based on the resolution 1 corresponding to the game application, and obtains the target image 2.

[0227] Among them, the resolution corresponding to the target image 2 is equal to the resolution 1.

[0228] S311. The mobile phone displays the target image 2.

[0229] In the embodiments of the present application, when the prediction probability is less than the preset probability threshold, it indicates that the current performance of the mobile phone can meet the requirement of rendering an image with the original resolution, and there is no need to turn on the super-resolution rendering function. The mobile phone can turn off the super-resolution rendering function and normally render the image to be rendered of the game application based on Resolution 1 to obtain the corresponding target image 2, avoiding unnecessary loss of image quality and ensuring the user's gaming experience.

[0230] It should be understood that the content included in the above target image 1 and target image 2 is the same, except for the different resolutions.

[0231] In the embodiments of the present application, after the game application is started, the mobile phone integrates the active scene information and the passive scene information, and uses the target decision tree to evaluate whether to turn on the super-resolution rendering function currently, realizing the automatic and flexible start and stop of the super-resolution rendering function in different scenarios, avoiding the judgment deviation caused by determining whether to turn on or off the super-resolution rendering function based on a single factor (such as the name of the application), ensuring the accuracy of the start and stop of the super-resolution rendering function, ensuring that the image quality of the game application meets the user's requirements, and being able to avoid the heating problem caused by the high power consumption of the mobile phone.

[0232] It should be noted that the process of decision tree training introduced in the above S301 - S302 can be executed by the mobile phone, or it can be executed by other devices instead of the mobile phone. Only the target decision tree determined on other devices needs to be pre - set on this mobile phone, that is to say, the mobile phone can directly apply the target decision tree.

[0233] In some embodiments, rendering the image to be rendered by using the super - resolution rendering algorithm may be inputting the image to be rendered into the super - resolution rendering model for the super - resolution rendering model to render the image to be rendered.

[0234] In some embodiments, the decision tree introduced above is only an example of the model, that is, the above initial decision tree is only an example of the initial model, and the above target decision tree is only an example of the target model. The mobile phone can also train other models (such as the convolutional model) to obtain the corresponding target model.

[0235] In addition, the mobile phone can not only determine the prediction probability matching the current scenario and the current device state through the target model, but also determine the prediction probability in other ways. Exemplarily, for each target feature, the mobile phone can calculate the product of the classification value corresponding to the target feature and the weight corresponding to the target feature to obtain the weighted value corresponding to the target feature. Among them, the classification value corresponding to the target feature can include 1 or 0, and the classification value corresponding to the target feature is determined according to whether the value of the target feature meets the preset classification condition corresponding to the target feature. The value of the target feature includes the information in the current scenario information and the current device state information. That is to say, the information included in the current scenario information and the current device state can be the value of the target feature. After that, the electronic device can calculate the sum of the weighted values corresponding to each target feature to obtain the prediction probability, realizing the determination of the prediction probability.

[0236] For example, the current device state information includes GPU load (60) and temperature (45 degrees). The target features include GPU load and temperature. Correspondingly, the values of the target features include 60 and 45 degrees. For the GPU load, the mobile phone can determine whether 60 meets the preset classification condition for the GPU load (such as whether it is greater than 55). If it is greater, the prediction value corresponding to the GPU load is 1. If it is less than or equal, the prediction value corresponding to the GPU load is 0. Here, the GPU load is 60, so the prediction value corresponding to the GPU load is 1. After that, the mobile phone can use the product of 1 and the weight corresponding to the GPU load as the weighted value corresponding to the GPU load.

[0237] Among them, the weight corresponding to the above target feature can be set manually or trained through training samples.

[0238] In some embodiments, the mobile phone can use the GUE service in the mobile phone to control the switch of the super-resolution rendering function to determine whether to use the super-resolution algorithm to render the images of the game application. The following will be combined with the above Figure 4 shown structure, taking the above current device state information including GPU load, CPU load, screen resolution, screen refresh rate, frame rate, temperature as an example, to introduce the process of determining whether to use the super-resolution rendering function to render images. This process may include S1-S10 as Figure 10 shown.

[0239] S1. After the game application is started, the temperature rise module in the mobile phone sends the temperature of the mobile phone to the GUE service in the mobile phone.

[0240] Exemplarily, the temperature rise module can identify whether the game application is started. After determining that the game application is started, the temperature rise module can notify the GUE service of the current temperature of the mobile phone in real time, periodically or when the temperature changes.

[0241] S2. The screen information determination module in the mobile phone sends the screen resolution and screen refresh rate to the GUE service.

[0242] S3. The AGP module in the mobile phone sends the frame rate to the GUE service.

[0243] S4. The load calculation module in the mobile phone sends the GPU load and CPU load to the GUE service.

[0244] S5. The game toolkit module in the mobile phone sends the current scene information to the GUE service.

[0245] Among them, the current scene information represents the game scene where the game application is currently located.

[0246] Optionally, the game scenes recognized by the game toolkit module are limited. When the game application enters certain scenes, the game toolkit module cannot recognize the scene, and the GUE service can recognize it to obtain the current scene information.

[0247] The above S1 - S5 introduce the process by which the GUE service obtains the current device status information and the current scene information. After obtaining the current device status information and the current scene information, the GUE can continue to determine whether to enable the super - resolution rendering function using the current device status information and the current scene information.

[0248] S6. The GUE service inputs the above - mentioned screen resolution, screen refresh rate, frame rate, GPU load, CPU load, temperature, and current scene information into the target decision tree to obtain a prediction probability.

[0249] S7. The GUE service determines the start - stop result according to the prediction probability.

[0250] Among them, the start - stop result indicates whether to enable the super - resolution rendering function.

[0251] Exemplarily, when the prediction probability is greater than the preset probability threshold, the GUE service determines that the start - stop result indicates enabling the super - resolution rendering function. When the prediction probability is less than or equal to the preset probability threshold, the GUE service determines that the start - stop indication is to disable the super - resolution rendering function.

[0252] The above S6 - S7 introduce the process by which the GUE determines the start - stop result regarding the super - resolution rendering function using the current device status information and the current scene information. Next, the process of rendering the image to be rendered of the game application according to the start - stop result will be continued.

[0253] S8. The GUE service sends the start - stop result to the rendering service.

[0254] S9. When the start / stop result indicates that the super-resolution rendering function is enabled, the rendering service renders the image to be rendered of the game application based on the resolution 1 corresponding to the game application, and obtains the target image 1. The resolution of the target image 1 is greater than or less than the resolution 1.

[0255] Among them, the resolution 1 can be automatically set by the mobile phone or set by the user after the game application is started. Exemplarily, as described above Figure 10 shown, S20. The game toolkit module sends the resolution 1 to the GUE service. S21. The GUE service sends the resolution 1 to the rendering service.

[0256] Among them, optionally, the above-mentioned enabling of the super-resolution rendering function includes enabling the high-resolution rendering function or the low-resolution rendering function. When the start / stop result indicates that the high-resolution rendering function is enabled, the resolution of the rendered target image 1 is greater than the resolution 1. For example, the resolution 1 is 1080P, and the rendering service renders the image to be rendered to obtain a 1080P image. Then, the mobile phone uses the super-resolution rendering technology to continue rendering the 1080P image to obtain a target image 1 close to 2K. Compared with directly rendering a 2K image, the super-resolution rendering technology can reduce the resources occupied by rendering on the basis of ensuring the image quality, thereby reducing the power consumption of the mobile phone.

[0257] When the start / stop result indicates that the low-resolution rendering function is enabled, the resolution of the rendered target image 1 is less than the resolution 1. For example, the resolution 1 is 1080P, and the rendering service renders the image to be rendered to obtain a 720P image. Then, the mobile phone uses the super-resolution rendering technology to continue rendering the 720P image to obtain a target image 1 close to 1080P, avoiding unnecessary power consumption losses.

[0258] S10. When the start / stop result indicates that the super-resolution rendering function is disabled, the rendering service renders the image to be rendered of the game application based on the resolution 1 corresponding to the game application, and obtains the target image 2. The resolution of the target image 2 is equal to the resolution 1.

[0259] For example, the resolution 1 is 1080P, and the rendering service renders the image to be rendered to obtain a 1080P image, thereby avoiding unnecessary loss of image quality.

[0260] In some embodiments, the GUE service can communicate externally, such as Figure 11As shown, the AGP plugin in the GUE service can obtain the information (such as frame rate) collected by the AGP service by calling the AGPserviceclient class. The PG plugin in the GUE service can obtain the information collected by the PG service (PGservice) by calling the PGserviceclient class. The PGservice can include modules / services other than the AGP service, such as the APS module, temperature rise module, game toolkit module, load calculation module, etc., to achieve the acquisition of current scenario information and current device status information.

[0261] Optionally, the above GUE service can obtain information through the gameservicehandler class. In addition, the operations performed by the GUE service are actually performed by the messagelooper thread.

[0262] Optionally, the above AGP service can manage the collected frame rate through the gasmanager class.

[0263] After that, after the AGP plugin obtains the information collected by the AGP service, it sends it to the state module in the GUE service. Similarly, after the PG plugin obtains the information collected by the PG service, it sends it to the state module.

[0264] After that, the plugin component (pluginhandler) in the GUE service can obtain the current scenario information and current device status information from the state module.

[0265] Optionally, the above AGP plugin and PG plugin can send a notification message to the pluginhandler. The notification message is used to trigger the pluginhandler to obtain the current scenario information and current device status information from the state module. Or, the AGP plugin and PG plugin can also send the collected information to the pluginhandler, and the pluginhandler does not need to obtain information from the state module.

[0266] After that, the pluginhandler sends the current scenario information and current device status information to the listenermanager module. The AI model decision-making module can obtain the current scenario information and current device status information from the listenermanager module through the state callback function (statecallback). The AI model decision-making module inputs the current scenario information and current device status information into the target decision tree to obtain the corresponding prediction probability, and determines the above start / stop result according to the prediction probability, so as to determine whether to enable the super-resolution rendering function.

[0267] Among them, the above-mentioned AGP plugin, PG plugin, pluginhandler, and monitoring management module belong to the GUE State Management (GUEStateManager) module, and this GUEStateManager module is responsible for maintaining all target features (or called game metrics), that is, maintaining the current device status information and the current scenario information.

[0268] In some embodiments, the above-mentioned AGP plugin function can also be implemented through the baseplugin class. The baseplugin class is a general class and is usually used as the base class or abstract class for plugin development. It provides some general functions and interfaces for specific plugin classes to inherit and implement. Similarly, the plugin function of the PG plugin can also be implemented through the baseplugin class.

[0269] In some embodiments, the operations performed by the above-mentioned software module or service can also be performed by other modules / services in the software layer, and this application does not limit the software module / service that performs the above operations. Additionally, it can be understood that the operations actually performed by the software module / service are all performed by the mobile phone.

[0270] In the technical solution disclosed in this application, the information involved (such as scenario information and device status information) is all information obtained with the individual consent of the user, including but not limited to notifying and reminding the user to read the relevant user agreement (notification) before the user uses this function, and signing the agreement (authorization) including authorizing the relevant user information.

[0271] This application embodiment also provides a computer-readable storage medium, and this computer-readable storage medium includes computer instructions. When the computer instructions run on an electronic device (such as the above-mentioned mobile phone), the electronic device is caused to execute the interface display method as described above.

[0272] This application embodiment also provides a computer program product. When the computer program product runs on a computer, the computer is caused to execute the method as described above.

[0273] This application embodiment also provides a data protection device. The data protection device can be divided into different logical units or modules according to functions, and each unit or module performs different functions, so that the data protection device executes the method as described above.

[0274] Through the description of the above embodiments, those skilled in the art can clearly understand that the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0275] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0276] The units described as separate components may or may not be physically separated. The components displayed as units can be one physical unit or multiple physical units, that is, they can be located in one place, or they can be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0277] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0278] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical discs that can store program codes.

[0279] The above content is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An interface display method, characterized in that, Applied to an electronic device, the method includes: Receiving a first operation on a first application of the electronic device; In response to the first operation, starting the first application; Based on the current scene information and current device state information of the first application, rendering a to-be-rendered interface of the first application to obtain a target interface; wherein, when the prediction probability corresponding to the current scene information and current device state information is greater than a preset probability threshold, the target interface is rendered based on the set resolution of the first application, combined with a super-resolution rendering algorithm, and the resolution of the target interface is not equal to the set resolution; the prediction probability represents the probability of predicting to turn on the super-resolution rendering function; the current scene information of the first application represents the scene where the first application is currently located; Displaying the target interface.

2. The method according to claim 1, characterized in that, When the prediction probability is less than or equal to the preset probability threshold, the target interface is rendered based on the set resolution, and the resolution of the target interface is equal to the set resolution.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Using the current scene information and current device state information as input parameters of a target model, running the target model to obtain a prediction probability corresponding to the current scene information and current device state information; wherein, the target model is obtained by training an initial model based on a plurality of training samples, and each training sample in the plurality of training samples includes scene sample information, device state sample information, and an expected result corresponding to the scene sample information and the device state sample information; the expected result represents whether to turn on the super-resolution rendering function.

4. The method according to claim 3, characterized in that, The target model includes a first target model, the prediction probability includes a first prediction probability, and the preset probability threshold includes a first preset probability threshold; The step of using the current scene information and current device state information as input parameters of a target model, running the target model to obtain a prediction probability corresponding to the current scene information and current device state information includes: Using the current scene information and current device state information as input parameters of the first target model, running the first target model to obtain a first prediction probability corresponding to the current scene information and current device state information; the first prediction probability represents the probability of predicting to turn on a first rendering function in the super-resolution rendering function, and the first rendering function represents the function of rendering an interface with a resolution higher than the set resolution; The step of rendering the to-be-rendered interface of the first application to obtain a target interface includes: When the first prediction probability is greater than the first preset probability threshold, rendering the to-be-rendered interface based on the set resolution, combined with the super-resolution rendering algorithm, to obtain the target interface, and the resolution of the target interface is greater than the set resolution.

5. The method according to claim 3, characterized in that, The target model includes a second target model, the prediction probability includes a second prediction probability, and the preset probability threshold includes a second preset probability threshold; Taking the current scene information and the current device status information as input parameters of a target model, running the target model, and obtaining a prediction probability corresponding to the current scene information and the current device status information, includes: Taking the current scene information and the current device status information as input parameters of a second target model, running the second target model, and obtaining a second prediction probability corresponding to the current scene information and the current device status information; the second prediction probability represents the probability of predicting to enable a second rendering function in the super-resolution rendering function, and the second rendering function represents a function of rendering an interface with a resolution lower than a set resolution; Rendering a to-be-rendered interface of the first application to obtain a target interface, includes: When the second prediction probability is greater than a second preset probability threshold, based on the set resolution, combining with the super-resolution rendering algorithm, rendering the to-be-rendered interface to obtain the target interface, and the resolution of the target interface is less than the set resolution.

6. The method according to claim 1 or 2, characterized in that, The method further includes: For each target feature, calculating the product of the classification value corresponding to the target feature and the weight corresponding to the target feature to obtain a weighted value corresponding to the target feature; wherein, the classification value corresponding to the target feature is determined according to whether the value of the target feature meets a preset classification condition corresponding to the target feature; the value of the target feature includes information in the current scene information and the current device status information; Calculating the sum of the weighted values corresponding to each of the target features to obtain the prediction probability.

7. The method according to any one of claims 1, 3 or 6, characterized in that, If the prediction probability is greater than the preset probability threshold, when the current scene information belongs to first preset scene information, the resolution of the target interface is greater than the set resolution; When the current scene information does not belong to the first preset scene information, the resolution of the target interface is less than the set resolution.

8. The method according to any one of claims 1 to 7, characterized in that, The current device status information includes at least one of device form, device window status, temperature, jitter rate, remaining battery power, charging status, network latency, screen refresh rate, screen resolution, frame rate, and load; the device form refers to a folded state, an unfolded state, and a non-folded device state; the device window status refers to a multi-window state or a single-window state, and the charging status indicates whether the electronic device is in a charging state.

9. The method according to any one of claims 1 to 8, characterized in that, The first application includes a game application, and the current scene information includes at least one of a scope scene, an airplane scene, a shooting scene, a battle scene, and a game lobby scene.

10. An electronic device, characterized in that, The electronic device includes a display screen, a memory, and one or more processors; the display screen, the memory, and the processor are coupled; the display screen is used to display an image generated by the processor, the memory is used to store computer program code, and the computer program code includes computer instructions; the memory includes a shared cache, and when the processor executes the computer instructions, the electronic device executes the method according to any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that, including computer instructions that, when executed on an electronic device, cause the electronic device to perform the method according to any one of claims 1 to 9.

Images