Control method of electronic device and electronic device

Abstract

The application discloses a control method of an electronic device and the electronic device, and the method comprises the following steps: monitoring target feature data of a target application of the electronic device in a running process; in response to the target feature data satisfying a target trigger condition, controlling the electronic device to adjust from acquiring frame data of an application interface of the target application at a current frame frequency to acquiring the frame data at a target frame frequency, the target frame frequency being greater than or less than the current frame frequency; and inputting the frame data acquired at the target frame frequency into a target processing model to generate a target file.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a control method for an electronic device and an electronic device. Background Technology

[0002] During the operation of some applications on electronic devices, it is necessary to extract frame data from the application interface and process the frame data using a processing model (e.g., to identify whether there are highlight events in the frame data).

[0003] Currently, the application interface is typically captured at a fixed frequency and then sent to the processing model for processing. This method is prone to missing important frame data when the application interface content changes rapidly, and to wasting computing resources when the application interface content changes slowly. Summary of the Invention

[0004] This application provides a control method for an electronic device, comprising: monitoring target feature data of a target application of the electronic device during operation; responding to the target feature data satisfying a target triggering condition, controlling the electronic device to adjust from acquiring frame data of the application interface of the target application at the current frame acquisition frequency to acquiring frame data at a target frame acquisition frequency, wherein the target frame acquisition frequency is greater than or less than the current frame acquisition frequency; and inputting the frame data acquired at the target frame acquisition frequency into a target processing model to generate a target file.

[0005] In some embodiments, the target feature data of the target application of the monitoring electronic device during operation includes: when the electronic device acquires video frames from the target video stream at a default first frame capture frequency, performing at least one of the following: frame content change data of the acquired video frames, operation behavior data of the target user acting on the electronic device, and audio parameter change data in the acquired audio stream, wherein the target video stream is video data obtained by performing video capture operation on the application interface of the target application; or, when the electronic device does not perform video capture operation on the application interface of the target application, performing operation behavior data of the target user acting on the electronic device and / or the target peripheral and / or the emotional parameters of the target user.

[0006] In some embodiments, responding to the target feature data satisfying the target triggering condition includes: calculating a probability value of the target application occurring a target event during operation based on the target feature data; determining that the target triggering condition is satisfied if the probability value is greater than or less than the corresponding probability value; correspondingly, controlling the electronic device to adjust from acquiring frame data of the application interface of the target application at the current frame acquisition frequency to acquiring the frame data at the target frame acquisition frequency includes: determining the target frame acquisition frequency based on the probability value; adjusting the acquisition of image frames or video frames of the application interface at the current frame acquisition frequency to acquisition of image frames or video frames of the application interface at the target frame acquisition frequency.

[0007] In some embodiments, calculating the probability value of a target event occurring during the operation of the target application based on the target feature data includes: determining the screen change rate of the application interface during operation based on frame content change data of video frames of the target application's application interface; determining the operation intensity and / or emotional parameters of the target user during the operation of the target application based on operation behavior data of the target user on the electronic device; and calculating the probability value of the target event occurring based on at least one of the screen change rate, the operation intensity of the target user, the emotional parameters of the target user, and the audio parameter change data in the acquired audio stream.

[0008] In some embodiments, calculating the probability value of the target event based on at least one of the screen change rate, the target user's operation intensity, the target user's emotional parameters, and the audio parameter change data in the acquired audio stream includes: determining the prediction weights configured for each type of target feature data; and calculating the probability value of the target event based on the screen change rate, the target user's operation intensity, emotional parameters, the audio parameter change data in the acquired audio stream, and their respective corresponding prediction weights.

[0009] In some embodiments, the method further includes at least one of the following: if the probability value is a first probability value, determining that a first triggering condition is met, and controlling the electronic device to maintain the current acquisition of the image frame or video frame at a default first frame-fetching frequency; if the probability value is a second probability value, determining that a second triggering condition is met, and controlling the electronic device to increase the current default first frame-fetching frequency to a default second frame-fetching frequency to acquire the image frame or video frame; if the probability value is a first probability value, determining that the first triggering condition is met, and controlling the electronic device to decrease the current default second frame-fetching frequency to a default first frame-fetching frequency to acquire the image frame or video frame.

[0010] In some embodiments, determining the target frame rate based on the probability value includes: determining the target frame rate based on the probability value range in which the probability value is located; or, determining the target frame rate based on the probability value range in which the probability value is located and the application attribute information of the target application.

[0011] In some embodiments, determining the target frame rate based on the probability value range in which the probability value falls includes at least one of the following: when the probability value is in a first probability value range, determining a third frame rate corresponding to the first probability value range as the target frame rate, wherein the third frame rate is 0; when the probability value is in a second probability value range, determining a fourth frame rate corresponding to the second probability value range as the target frame rate, wherein the fourth frame rate is not greater than the first frame rate, which is the minimum default value of the electronic device; when the probability value is in a third probability value range, determining a fifth frame rate corresponding to the third probability value range as the target frame rate; when the probability value is in a fourth probability value range, determining a sixth frame rate corresponding to the fourth probability value range as the target frame rate, wherein the sixth frame rate is not less than the second frame rate, which is the maximum default value of the electronic device.

[0012] In some embodiments, inputting frame data acquired at the target frame acquisition frequency into a target processing model to generate a target file includes at least one of the following: inputting video frames or image frames acquired at the target frame acquisition frequency into a first processing model to generate a first highlight video file, wherein the first processing model is an artificial intelligence model capable of recognizing highlight events and generating highlight videos; inputting video frames or image frames acquired at the target frame acquisition frequency and first association information of target objects in the video frames or image frames into a second processing model to generate a second highlight video file, wherein the second processing model is an artificial intelligence model capable of recognizing highlight events and generating highlight videos; inputting video frames or image frames acquired at the target frame acquisition frequency and second association information of target objects in the video frames or image frames into a third processing model to generate a target summary file or a target record file; and inputting video frames or image frames acquired at the target frame acquisition frequency and second association information of target objects in the video frames or image frames into a fourth processing model to generate a target poster file.

[0013] This application also proposes an electronic device, including at least one processor and a display. The processor is configured to: monitor target feature data of a target application during operation; in response to the target feature data satisfying a target triggering condition, control the electronic device to acquire frame data of the application interface of the target application from the display at a current frame acquisition frequency, and adjust the acquisition frequency to a target frame acquisition frequency, wherein the target frame acquisition frequency is greater than or less than the current frame acquisition frequency; input the frame data acquired at the target frame acquisition frequency to a target processing model to generate a target file, wherein the target processing model may or may not belong to the electronic device. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A flowchart of a control method for an electronic device according to an embodiment of this application. Figure 1 ;

[0016] Figure 2 This is a flowchart illustrating the determination of whether the target triggering condition is met, as described in this application embodiment. Figure 3 This is a flowchart illustrating how the control electronic device in this application adjusts its frame data acquisition from the current frame rate to the target frame rate for acquiring frame data. Figure 4 This is a flowchart illustrating the calculation of the probability value of a target event occurring during the operation of a target application based on target feature data, according to an embodiment of this application. Figure 5 This is a flowchart illustrating how the probability of a target event occurring is calculated based on at least one of the following in an embodiment of this application: screen change rate, target user's operational intensity, target user's emotional parameters, and audio parameter change data in the acquired audio stream. Figure 6 A flowchart of a control method for an electronic device according to an embodiment of this application. Figure 2 ; Figure 7 A flowchart of a control method for an electronic device according to an embodiment of this application. Figure 3 ; Figure 8 A flowchart of a control method for an electronic device according to an embodiment of this application. Figure 4 ; Figure 9This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0017] Various embodiments and features of this application are described herein with reference to the accompanying drawings.

[0018] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this application will be apparent to those skilled in the art.

[0019] The accompanying drawings, which are included in and form part of this specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0020] These and other features of this application will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0021] It should also be understood that although this application has been described with reference to some specific examples, those skilled in the art can certainly implement many other equivalent forms of this application.

[0022] The above and other aspects, features and advantages of this application will become more apparent when taken in conjunction with the accompanying drawings and in view of the following detailed description.

[0023] Specific embodiments of this application are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of this application, which can be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that could obscure the application. Therefore, the specific structural and functional details claimed herein are not intended to be limiting, but merely serve as the basis and representative basis for the claims to teach those skilled in the art to use this application in a variety of substantially any suitable detailed structures.

[0024] This specification may use the phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments,” all of which may refer to one or more of the same or different embodiments according to this application.

[0025] An embodiment of this application provides a control method for an electronic device. By monitoring target feature data of a target application during its operation, and in response to the target feature data satisfying a target triggering condition, the electronic device is controlled to adjust from acquiring frame data at the current frame acquisition frequency to acquiring frame data at the target frame acquisition frequency. This achieves dynamic adjustment of the frame acquisition frequency based on the target feature data, thereby reducing computational overhead while avoiding the omission of important frame data.

[0026] like Figure 1 As shown, it includes the following steps: Step S101: Monitor the target feature data of the target application of the electronic device during operation.

[0027] In this embodiment, the electronic device can be any of the following: a mobile phone, a laptop computer, a tablet computer, a desktop computer, an all-in-one computer, a television, or a personal computer. The electronic device can run a target application, which can display changing screen content on its interface during operation. The target application can include, for example, any of the following: a game application, a video playback application, a video conferencing application, or a live streaming application. For example, if the target application is a game application, changing game footage can be displayed on the application interface during its operation. If the target application is a video conferencing application, changing meeting footage can be displayed on the application interface during its operation.

[0028] Target feature data can characterize changes in the content displayed on the application interface. This data can be data on changes in the content displayed on the screen (such as the appearance of a boss or a "powerful attack"); it can also be application runtime data obtained through the application memory interface or data on user actions on peripherals (such as the user's operation methods or frequency on peripherals like keyboards and mice, which can be used to determine the current running state or intensity of the target application); it can also be audio energy data, such as facial expressions captured by a camera, heart rate and breathing data detected by radar or millimeter-wave sensors, or voice parameters monitored through a microphone; it can also be parameter data characterizing the running state of the target application, such as the state of a powerful attack, low health, attack, obtaining special rewards (such as finding a treasure chest, rewarding weapons and skills), reaching the podium (or other specific locations), or defeating a boss; it can also be runtime parameters, such as the start of the game, the middle of the game, or a game point; and it can also be application display content data, such as the appearance of specific display content indicating the need to adjust the frame rate, such as the appearance of a boss, a PowerPoint presentation showcasing a new product in a video conference, or a new product appearing in a live streaming application.

[0029] Step S102: In response to the target feature data satisfying the target triggering condition, the electronic device is controlled to adjust from acquiring the frame data of the application interface of the target application at the current frame acquisition frequency to acquiring the frame data at the target frame acquisition frequency, wherein the target frame acquisition frequency is greater than or less than the current frame acquisition frequency.

[0030] In this embodiment, the target triggering condition may be, for example, the "highlight probability score" calculated based on the target feature data reaching a certain threshold, or decreasing from above the threshold to below the threshold; or a certain feature parameter in the target feature data meeting the corresponding threshold, such as the screen feature change rate being greater than or less than a certain threshold, the operation behavior change rate being greater than a specific value, the audio energy value being greater than a specific value; or the appearance of preset image element features in the application screen, the appearance of specific voice commands, etc.

[0031] The system determines whether the target feature data meets the target triggering condition. If it does, it controls the electronic device to adjust its frame acquisition frequency from the current frame acquisition frequency to the target frame acquisition frequency, which is greater than or less than the current frame acquisition frequency. The current frame acquisition frequency can be zero or non-zero. When the current frame acquisition frequency is zero, the target frame acquisition frequency is greater than zero; when the current frame acquisition frequency is non-zero, the target frame acquisition frequency can be greater than, less than, or zero. The frame data can be image frames or video frames.

[0032] For example, if the highlight probability score of the target feature data reaches a threshold, the target triggering condition is determined to be met, and the current frame rate is increased to the target frame rate to accurately identify highlight events. Subsequently, if the highlight probability score falls below the threshold, the target triggering condition is determined to be met, and the current frame rate is decreased to the target frame rate to reduce computational overhead. Alternatively, if a preset image element feature appears in the application screen, the target triggering condition is determined to be met, and the current frame rate is increased from zero to a target frame rate greater than zero. Subsequently, if the preset image element feature disappears, the target triggering condition is determined to be met, and the current frame rate is decreased to zero to reduce computational overhead.

[0033] Step S103: Input the frame data obtained at the target frame rate into the target processing model to generate the target file.

[0034] In this embodiment, the target processing model can be set locally, in the cloud, or at the edge. The target processing model can be, for example, a highlight recognition model, a highlight video generation model, a video editing model, etc. The target file can include, for example, one or more of the following: highlight video file, highlight animation file, keyframe summary file, animated GIF file, and emoticon file.

[0035] In some embodiments of this application, while inputting frame data acquired at the target frame rate into the target processing model, the acquired image data, audio data, or video data of the target user can also be input into the target processing model, so that the target processing model adds the image data, audio data, or video data of the target user into the generation process of the highlight video; special effects selection data can also be input into the target processing model, so that the target processing model generates highlight video with added special effects; product information (such as shopping links) in the live broadcast scene, PPT files or important materials in the video conference, etc. can also be input into the target processing model, so that the target file generated by the target processing model can include the corresponding product information, PPT file content or important material content.

[0036] The control method for an electronic device according to embodiments of this application monitors target feature data of a target application during its operation. In response to the target feature data satisfying a target triggering condition, the method controls the electronic device to adjust its frame acquisition frequency from the current frame acquisition frequency to a target frame acquisition frequency, where the target frame acquisition frequency is greater than or less than the current frame acquisition frequency. The frame data acquired at the target frame acquisition frequency is then input into a target processing model to generate a target file. This dynamic adjustment of the frame acquisition frequency based on the target feature data reduces computational overhead while avoiding the omission of important frame data.

[0037] In some embodiments of this application, the target application of the monitoring electronic device uses target feature data during operation, including the following steps: When an electronic device acquires video frames from a target video stream at a default first frame capture frequency, it performs monitoring on at least one of the following: frame content change data of the acquired video frames, operation behavior data of the target user on the electronic device, and audio parameter change data in the acquired audio stream, wherein the target video stream is video data obtained by capturing video from the application interface of the target application; or, If the electronic device does not perform video capture operation on the application interface of the target application, the operation data of the target user's operation on the electronic device and / or the target peripheral device and / or the target user's emotional parameters are monitored.

[0038] In this embodiment, the electronic device can perform a video capture operation on the target application's interface, acquiring video frames from the target video stream at a default first frame capture frequency, or it can choose not to perform the video capture operation on the target application's interface. The video capture operation can be, for example, video recording, video trimming request operations, etc. The first frame capture frequency can be a low frame capture frequency (e.g., 5fps) to reduce computational overhead.

[0039] If the electronic device acquires video frames from the target video stream at a default first frame rate, the target feature data is determined by monitoring at least one of the following: frame content change data of the acquired video frames, user action data on the electronic device, and audio parameter change data in the acquired audio stream. Frame content change data can be the rate of change of image content, which can be determined by calculating pixel-level or feature-level differences between consecutive frames (such as histogram differences or SSIM (Structural Similarity Index Measure)). A high rate of change of image content indicates drastic changes in the image (such as explosions, powerful attacks, intense attacks, scene transitions, etc.). User action data can include the intensity of player actions, which can be monitored through the game memory interface or peripherals. Player action intensity includes, for example, mouse click / movement speed and keyboard keystroke frequency per unit time. A sudden increase in player action intensity usually indicates the possibility of a highlight event. In other embodiments, the action data can also include the user's facial expressions, voice command data, voice input data, etc. Audio streams can be generated simultaneously with video streams, capturing both application visuals and audio, or they can be independently collected internal audio data and external environmental sound data during application operation. Audio parameter change data can be audio energy analysis data; for example, analyzing game audio streams, sudden volume spikes or specific sound effects (such as the "First Blood" sound effect) are strong trigger signals.

[0040] If the electronic device does not perform video capture of the target application's interface, target characteristic data is determined by monitoring operational behavior data and / or the target user's emotional parameters. Operational behavior data may include the intensity of player actions, which can be monitored via the game memory interface or peripherals. Player action intensity includes, for example, mouse click / movement speed and keyboard keystroke frequency per unit time. A sudden increase in player action intensity usually indicates a potential highlight event. In other embodiments, operational behavior data may also include voice command data, voice input data, etc. Emotional parameters may include the target user's heart rate, respiratory rate, blink rate, voice volume, speech rate, etc.

[0041] By performing video capture operations via electronic devices and acquiring video frames from the target video stream at a first frame-fetching frequency, target feature data can be determined, enabling accurate monitoring of the application interface and improving the accuracy of the target file. Alternatively, by not performing video capture operations via electronic devices but determining target feature data through monitoring operational behavior data and / or emotion parameters, computational overhead can be reduced.

[0042] In some embodiments of this application, the response is that the target feature data satisfies the target triggering condition, such as... Figure 2As shown, it includes the following steps: Step S1021: Calculate the probability value of the target event occurring during the operation of the target application based on the target feature data.

[0043] In this embodiment, the target event can be a highlight event in a game (such as unleashing a powerful attack, being low on health, attacking, receiving a special reward, reaching the podium, or defeating a boss), a highlight event in a competition (such as scoring a goal, making a tackle, or making a save in a football match), an exciting plot segment in a movie or TV show, content that the user is particularly interested in in a video, or key content appearing in a video conference, etc. The probability value can include a "highlight probability score," which can be a comprehensive evaluation parameter or an evaluation parameter on a single dimension, such as the rate of change in the visuals or the intensity of the player's actions.

[0044] Step S1022: If the probability value is greater than or less than the corresponding probability value, determine that the target triggering condition is met.

[0045] In this embodiment, if the probability value is greater than the target high probability value (e.g., 0.95), the target triggering condition is determined to be met, indicating that the target event will definitely occur. The frame rate can be increased to improve accuracy. If the probability value is less than the target low probability value (e.g., 0.25), the triggering condition is determined to be met, indicating that the target event will definitely not occur. The frame rate can be decreased to reduce computational overhead.

[0046] Correspondingly, the electronic device is controlled to adjust its acquisition of frame data from the application interface of the target application from the current frame acquisition frequency to the target frame acquisition frequency, such as... Figure 3 As shown, it includes the following steps: Step S1023: Determine the target frame rate based on the probability value.

[0047] In this embodiment, the target frame rate can be determined based on the type of the probability value. For example, if the probability value is "certain to occur," a high frame rate is used as the target frame rate; if the probability value is "certain not to occur," a low frame rate is used as the target frame rate. Alternatively, multiple intervals can be pre-set, with different intervals corresponding to different frame rates, and the target frame rate can be determined based on the interval in which the probability value falls.

[0048] Step S1024: Adjust the acquisition of image frames or video frames of the application interface at the current frame acquisition frequency to the acquisition of image frames or video frames of the application interface at the target frame acquisition frequency.

[0049] In this embodiment, the frame data can be image frames or video frames from the application interface. If the current probability value is less than the corresponding probability value (e.g., 0.25), the current frame rate (e.g., 5fps) is too low. When the target triggering condition is met, the current frame rate is increased to the target frame rate (e.g., 30fps) to improve accuracy. If the probability value is greater than the corresponding probability value (e.g., 0.95), the current frame rate (e.g., 30fps) is too high. When the target triggering condition is met, the current frame rate is decreased to the target frame rate (e.g., 5fps) to reduce computational overhead.

[0050] This allows for the determination of whether the target triggering condition is met by measuring the probability value, and the determination of the corresponding frame rate, enabling efficient and accurate dynamic adjustment of the frame rate based on target feature data.

[0051] In some embodiments of this application, the step of calculating the probability value of the target event occurring during the operation of the target application based on the target feature data is as follows: Figure 4 As shown, it includes the following steps: Step S10211: Determine the screen change rate of the application interface of the target application during operation based on the obtained frame content change data of the video frames of the application interface of the target application.

[0052] In this embodiment, the frame content change data of video frames can be calculated using a pre-trained model, or the frame content change data of video frames can be determined by statistically analyzing the proportion of changed area in each frame, the number of changes in image elements (such as histogram differences, SSIM), etc.

[0053] Step S10212: Determine the intensity of the target user's operation and / or emotional parameters during the operation of the target application based on the target user's operational behavior data on the electronic device.

[0054] In this embodiment, the operational behavior data can be direct operational speed, operational frequency, etc., or physiological parameters (such as voice characteristics, blood pressure, brain waves, etc.) that characterize the user's tension, excitement, or agitation.

[0055] Step S10213: Calculate the probability value of the target event based on at least one of the following: the screen change rate, the target user's operation intensity, the target user's emotional parameters, and the audio parameter change data in the acquired audio stream.

[0056] In this embodiment, the audio stream can be generated simultaneously with the video stream, capturing both the application's visuals and audio. Alternatively, it can be independently collected internal audio data and external environmental sound data during application operation, such as the user's voice data. Audio parameter changes can be determined by performing audio energy analysis on the audio stream. For example, analyzing game audio streams reveals sudden volume spikes or specific sound effects as strong trigger signals. The probability of the target event occurring is calculated based on at least one of the following: the rate of change in the visuals, the intensity of the target user's actions, the target user's emotional parameters, and the audio parameter changes in the acquired audio stream.

[0057] It should be noted that if the probability value can be determined solely based on the screen change rate, the step of determining the target user's action intensity and / or emotional parameters can be omitted; if the probability value can be determined solely based on the target user's action intensity and / or emotional parameters, the step of determining the screen change rate can be omitted.

[0058] By utilizing feature data from different perspectives during the operation of the target application, the probability of the target event occurring can be determined more flexibly.

[0059] In some embodiments of this application, the probability value of the target event is calculated based on at least one of the following: the screen change rate, the target user's operational intensity, the target user's emotional parameters, and audio parameter change data in the acquired audio stream. Figure 5 As shown, it includes the following steps: Step S201: Determine the prediction weights configured for each type of target feature data.

[0060] In this embodiment, different weight coefficients are assigned in advance according to the contribution of different types of target feature data to the probability value. For example, different prediction weights are configured for the change rate of the screen, the intensity of the target user's operation, the emotion parameters, and the audio parameter change data in the acquired audio stream. For example, a higher weight coefficient can be configured for the change rate of the screen and a lower weight coefficient for the change data of the audio parameters; or the weight coefficients of each type of target feature data can be configured to be the same.

[0061] Step S202: Based on the screen change rate, the target user's operation intensity, emotional parameters, the audio parameter change data in the acquired audio stream and their corresponding prediction weights, calculate the probability value of the target event occurring.

[0062] In this embodiment, the rate of change of the screen, the intensity of the target user's operation, the emotional parameters, and the sub-scores corresponding to the audio parameter change data in the acquired audio stream can be determined. The sub-scores are weighted and summed based on each prediction weight to determine the comprehensive score. The comprehensive score is then determined as the probability value, thereby determining the probability of the target event occurring from multiple dimensions and improving the accuracy of the probability value.

[0063] In some embodiments of this application, at least one of the following is also included: If the probability value is a first probability value, and the first triggering condition is determined to be met, the electronic device is controlled to maintain the current acquisition of the image frame or video frame at the default first frame acquisition frequency. If the probability value is the second probability value, and the second triggering condition is determined to be met, the electronic device is controlled to increase from the current default first frame acquisition frequency to the default second frame acquisition frequency to acquire the image frame or video frame. If the probability value is the first probability value, and the first triggering condition is met, the electronic device is controlled to reduce the current default second frame-taking frequency to the default first frame-taking frequency to acquire the image frame or video frame.

[0064] In this embodiment, the first probability value can be a value representing the probability that the target event will not occur, such as 0. The default first frame rate can be the default minimum frame rate, such as 5fps. If the probability value is the first probability value, then it is determined that the first triggering condition is met, and the electronic device is controlled to maintain the acquisition of image frames or video frames at the first frame rate to reduce computational overhead.

[0065] The second probability value can be a value representing the probability of the target event occurring, such as 1. The default second frame frequency can be the default maximum frame rate, such as 30fps or 60fps. If the probability value is the second probability value, it is determined that the second triggering condition is met, and the electronic device is controlled to increase the current first frame rate to the second frame rate to avoid missing important image frames or video frames and improve the accuracy of the target file.

[0066] If the probability value changes to the first probability value when the current frame fetching frequency is the second frame fetching frequency, then the first triggering condition is determined to be met. The electronic device is then controlled to reduce the current second frame fetching frequency to the first frame fetching frequency in order to reduce unnecessary frame fetching operations and reduce computational overhead.

[0067] For example, such as Figure 6 As shown, the method for controlling an electronic device may include the following steps: Step S301: The target game application is launched.

[0068] Step S302: Acquire video frames at a frame rate of 5fps.

[0069] After the target game application starts, it acquires video frames at a frame rate of 5fps and executes step S307, thereby acquiring video frames at a lower frame rate, reducing unnecessary frame acquisition operations and lowering computational overhead.

[0070] Step S303: Check if the probability value becomes 1. If yes, proceed to step S304; otherwise, proceed to step S302.

[0071] Step S304: Increase the frame rate from the current 5fps to 30fps to acquire video frames.

[0072] If the probability value becomes 1, it means that a highlight event is currently occurring in the target game application. The frame rate is increased from the current 5fps to 30fps to obtain video frames, and step S307 is executed to avoid missing important video frames and improve the accuracy of the target file.

[0073] Step S305: Check if the probability value becomes 0. If yes, proceed to step S306; otherwise, proceed to step S304.

[0074] Step S306: Reduce the frame rate from 30fps to 5fps to acquire video frames.

[0075] If the probability value becomes 0, it means that the highlight event has ended. The frame rate is reduced from the current 30fps to 5fps to obtain video frames, and step S307 is executed, thereby reducing unnecessary frame-taking operations and reducing computational overhead.

[0076] Step S307: Input into the target processing model.

[0077] The target processing model is a highlight recognition model, which can identify highlight events in the acquired video frames and generate highlight videos as target files.

[0078] In some embodiments of this application, determining the target frame rate based on the probability value includes: The target frame rate is determined based on the probability value range within which the probability value falls; or... The target frame rate is determined based on the probability value range of the probability value and the application attribute information of the target application.

[0079] In this embodiment, multiple probability value ranges can be preset, each probability value range corresponds to a frame rate, and the frame rate corresponding to the probability value range in which the probability value is located is determined and used as the target frame rate, thereby achieving more precise dynamic adjustment of the frame rate.

[0080] Considering that different types of applications may have different output frame rates or different frame rate ranges, the frame rate frequency can be adjusted by referring to the application's frame rate range. Application attribute information can include application type, application name, version, etc., such as game applications, video conferencing applications, live streaming applications, video playback applications, teaching and training applications, etc. The frame rate corresponding to the probability value range where the probability value falls can be determined first, and this can be used as the initial frame rate frequency. Then, the initial frame rate frequency can be compensated based on the application attribute information to determine the target frame rate frequency. This allows for more precise dynamic adjustment of the frame rate frequency while making the target frame rate frequency more suitable for the target application, improving accuracy.

[0081] In some embodiments of this application, determining the target frame rate based on the probability value range in which the probability value falls includes at least one of the following: When the probability value is within the range of the first probability value, the third frame rate corresponding to the range of the first probability value is determined as the target frame rate, and the third frame rate is 0. When the probability value is within the range of the second probability value, the fourth frame rate corresponding to the range of the second probability value is determined as the target frame rate, wherein the fourth frame rate is not greater than the first frame rate, which is the minimum default frame rate of the electronic device. If the probability value is within the range of the third probability value, the fifth frame rate corresponding to the range of the third probability value is determined as the target frame rate. When the probability value is within the range of the fourth probability value, the sixth frame-taking frequency corresponding to the range of the fourth probability value is determined as the target frame-taking frequency, wherein the sixth frame-taking frequency is not less than the second frame-taking frequency, which is the maximum default value of the electronic device.

[0082] In this embodiment, if the probability value is within the range of the first probability value, it is determined that the target event will not occur at present, and the third frame fetching frequency of 0 is determined as the target frame fetching frequency, that is, no frame fetching is performed on the target application.

[0083] If the probability value is within the range of the second probability value, then the fourth frame rate is determined as the target frame rate. This fourth frame rate is not greater than the default minimum first frame rate of the electronic device. In this case, it can be considered as low-intensity monitoring of the target application.

[0084] If the probability value is within the range of the third probability value, then the fifth frame rate is determined as the target frame rate. The fifth frame rate can be greater than the fourth frame rate. In this case, it can be considered as general intensity monitoring of the target application.

[0085] If the probability value is within the range of the fourth probability value, then the sixth frame rate is determined as the target frame rate. This sixth frame rate is not less than the default maximum second frame rate. In this case, the target event is very likely to occur, which can be considered as high-intensity monitoring of the target application.

[0086] By determining the probability range of the probability value, the corresponding frame rate is used as the target frame rate, enabling more precise dynamic adjustment of the frame rate.

[0087] For example, if the probability value is S, then the range of the first probability value can be S<0.2, the range of the second probability value can be 0.2≤S<0.5, the range of the third probability value can be 0.5≤S<0.8, and the range of the fourth probability value can be S≥0.8.

[0088] If S < 0.2, then the third frame rate is 0. In this case, it is in sleep mode and frame fetching stops, such as when the game application is in the lobby interface.

[0089] If 0.2 ≤ S < 0.5, then the fourth frame rate is 5 fps. In this case, it is a patrol mode for low-intensity monitoring. The default minimum first frame rate is 5 fps.

[0090] If 0.5≤S<0.8, then the fifth frame rate is 10fps. This is the active frame rate, for example, when the game application is in normal gameplay.

[0091] If S≥0.8, the sixth frame rate is 30fps. This is the combat setting, such as during a highlight moment in the game application, like a pentakill. The default maximum second frame rate is 30fps.

[0092] It should be noted that the range of multiple probability value intervals in the embodiments of this application can be increased or decreased, and the frame rate corresponding to each probability value interval can also be other frame rates. Other different probability value intervals and corresponding frame rate settings are all within the protection scope of this application.

[0093] In some embodiments of this application, the step of inputting frame data acquired at the target frame rate into the target processing model to generate a target file includes at least one of the following: The video frames or image frames acquired at the target frame rate are input into the first processing model to generate the first highlight video file. The first processing model is an artificial intelligence model that can identify highlight events and generate highlight videos. The video frames or image frames acquired at the target frame rate and the first association information of the target object in the video frames or image frames are input into the second processing model to generate a second highlight video file. The second processing model is an artificial intelligence model that can identify highlight events and generate highlight videos. The video frames or image frames acquired at the target frame rate and the second association information of the target object in the video frames or image frames are input into the third processing model to generate a target summary file or a target record file. The video frames or image frames acquired at the target frame rate and the second associated information of the target object in the video frames or image frames are input into the fourth processing model to generate the target poster file.

[0094] In this embodiment, the target processing model can be a first processing model, which is an artificial intelligence model capable of recognizing highlight events and generating highlight videos. By inputting video frames or image frames acquired at the target frame rate into the first processing model, the first processing model identifies the highlight events and generates a first highlight video file.

[0095] The target processing model can also be a second processing model, which is an artificial intelligence model capable of recognizing highlight events and generating highlight videos. Video frames or image frames acquired at the target frame rate, along with the first association information of the target object within those frames, are input into the second processing model. The second processing model then identifies the highlight events and generates a second highlight video file. The first association information of the target object can be image data, audio data, or video data of the target user, which is added to the highlight video generation process by the second processing model. Alternatively, the first association information can also be some special effects selection data, enabling the second processing model to generate highlight videos with added special effects.

[0096] The target processing model can also be a third processing model, which can generate a target summary file or a target record file. Video frames or image frames acquired at the target frame rate, along with the second association information of the target object within those frames, are input into the third processing model, which then generates the target summary file or target record file. The second association information of the target object may include purchase links for specific goods or products, product description links, links or hyperlinks to other related accessible information, such as video demos or manufacturer material data introducing an electronic product or component.

[0097] The target processing model can also be a fourth processing model, which can generate the target poster file. Video frames or image frames acquired at the target frame rate and the second associated information are input into the fourth processing model, which then generates the target poster file. The target poster file can be, for example, a product promotional poster or a merchandise advertisement poster, etc.

[0098] By using different target processing models, different target files can be generated, enabling more flexible target file generation and expanding the scope of applicable scenarios.

[0099] To further illustrate the technical concept of this application, the technical solution will now be explained in conjunction with specific application scenarios.

[0100] This application provides a control method for an electronic device, applied to a dynamic frame rate decision-making system. The core of this system lies in introducing a game rhythm and scene perception intermediary layer between the original video stream and the highlight recognition model. This intermediary layer analyzes the game state in real time using lightweight technology and dynamically decides whether to send the current frame to the backend highlight recognition model for in-depth analysis.

[0101] The frame rate dynamic decision system includes a raw video stream capture module, a game rhythm and scene perception intermediate layer, and a highlight recognition model. The game rhythm and scene perception intermediate layer includes a lightweight feature extraction unit and a dynamic decision unit.

[0102] The raw video stream capture module is responsible for capturing the game's video stream in real time and sending it to the lightweight feature extraction unit. This module takes frames at a base frequency (e.g., 5fps) as the raw material for analysis.

[0103] The lightweight feature extraction unit extracts one or more lightweight feature metrics (i.e., target feature data) for each captured image frame. The computational cost of these metrics is far less than that of a full specular recognition model. The metrics include at least one of the following: Frame change rate: Calculates pixel-level or feature-level differences (such as histogram differences, structural similarity (SSIM)) between consecutive frames. A high change rate indicates dramatic changes in the scene (such as explosions or scene transitions).

[0104] Player activity intensity: Data is obtained through the game's memory interface or external monitoring devices, such as mouse click / movement speed and keyboard keystroke frequency per unit time. A sudden increase in activity usually indicates the possibility of highlight plays.

[0105] Audio energy analysis: Analyze the game audio stream; sudden volume spikes or specific sound effects (such as "First Blood") are strong trigger signals.

[0106] The dynamic decision-making unit calculates a highlight probability score in real time based on one or more of the aforementioned lightweight feature indicators. This score is associated with a dynamic value used to adjust the frame rate. When the score exceeds a threshold, it is classified as a "highlight suspected state," and a frame inspection is immediately triggered. In a "highlight suspected state" with a high score, the system enters a "high-frequency mode," potentially increasing the frame rate to 30fps or even higher to ensure the capture of critical details. When the score falls below the threshold, the system enters a "low-frequency / standby mode," significantly reducing the frame rate (e.g., to 5fps) or suspending frame inspection altogether.

[0107] The highlight recognition model is the original highlight recognition model, used for the final highlight event recognition of the submitted frame sequence. Because the input is a high-value frame, both its recognition efficiency and accuracy are improved.

[0108] like Figure 7 As shown, the control method for this electronic device includes the following steps: Step S401: Capture the raw video stream.

[0109] The raw video stream capture module captures the raw video stream from the game screen and sends it to the lightweight feature extraction unit.

[0110] Step S402: Extract lightweight features.

[0111] The lightweight feature extraction unit extracts lightweight features from the original video stream and sends them to the dynamic decision unit. The lightweight features include screen transition rate, player operation intensity, audio energy analysis, etc.

[0112] Step S403: Calculate whether the highlight probability score exceeds the threshold. If yes, proceed to step S404; otherwise, proceed to step S405.

[0113] The dynamic decision unit calculates the highlight probability score based on the extracted lightweight features and determines whether the highlight probability score exceeds the threshold.

[0114] The highlight probability score (S) can be a normalized value, for example, ranging from [0, 1.0]. S=0 indicates that a highlight event is almost impossible at the current moment. S=1.0 indicates that a highlight event is very likely to be happening at the current moment.

[0115] Step S404: Increase the frequency of sample submission.

[0116] If the highlight probability score exceeds the threshold, the frequency of testing will be increased to avoid missing important video frames and improve the accuracy of highlight recognition.

[0117] Step S405: Reduce the frequency of sample submission or suspend sample submission.

[0118] If the highlight probability score does not exceed the threshold, the submission frequency is reduced or submission is suspended to reduce computational overhead.

[0119] Step S406: The highlight recognition model performs recognition.

[0120] Step S407: Output the highlight recognition result.

[0121] In some embodiments of this application, the dynamic decision unit may also have a built-in multi-level threshold mapping function to define the conversion relationship from "score" to "submission frequency".

[0122] Multiple score thresholds are set to create different response levels: S<0.2, hibernation mode: inspection frequency = 0 fps (completely stop inspection, such as in the lobby interface).

[0123] 0.2 ≤S<0.5, patrol file: inspection frequency = 5 fps (low-intensity monitoring).

[0124] 0.5 ≤S<0.8, active range: sampling frequency = 10 fps (normal game process).

[0125] 0.8≤S<0.95, combat mode: inspection frequency = 15 fps (intense team battle).

[0126] S ≥ 0.95, Extreme setting: Testing frequency = 30 fps (ultimate highlight moment, such as a pentakill).

[0127] In some embodiments of this application, such as Figure 8 As shown, the control method for an electronic device may include the following process.

[0128] After the user launches the game application, the frame rate dynamic decision-making system is activated. Initially, a low-power monitoring mode is used, with a frame rate of F_low. Multiple signals are continuously monitored: visuals, actions, audio, and game events. If the signal is stable, indicating a low-value phase, the low-power mode continues, with a frame rate of F_low. If the signal changes abruptly, detecting a potential highlight event, the highlight probability score is calculated in real time, and it is determined whether the score exceeds a threshold. If not, the low-power mode continues, with a frame rate of F_low; if so, it immediately switches to high-speed capture mode, with a frame rate of F_high. Signal strength is continuously monitored. If the signal attenuates to a calm state, indicating the highlight event has ended, the system switches back to low-power mode and generates and saves the complete highlight video clip. Simultaneously, the low-power monitoring mode continues, with a frame rate of F_low.

[0129] The following explanation will be based on both scenario one and scenario two.

[0130] Scenario 1: Fast-paced, high-intensity combat game scenario.

[0131] In a crucial ranked match, a user used a sniper rifle to eliminate four enemies in a narrow alley within just 3 seconds, achieving a spectacular "quad kill." Under the scheme of this embodiment, the system continuously monitors the underlying game data. When it detects a significant increase in the user's mouse operation frequency, drastic changes in the captured image (significantly reduced SSIM index in key areas of consecutive frames, large differences between frames), and the appearance of a knockdown sound, it determines that the "high probability score of highlight" is extremely high, and instantly increases the frame rate from "patrol mode" (e.g., 0.5 frames per second) to "combat mode" (e.g., 60 frames per second). Every micro-operation, every shot, and every knockdown by the user in the next 3 seconds is clearly recorded. When the battle ends and the game data returns to normal, the system intelligently reduces the frame rate. Ultimately, a complete, smooth "quad kill" highlight video containing all keyframes is automatically generated, perfectly recreating the user's peak performance.

[0132] Scenario 2: Game scenarios with large changes in pace and many quiet periods.

[0133] After the laning phase ends, players have several minutes of "garbage time"—their controlled heroes merely move around in the jungle, recall to base to buy equipment, and set up wards. In the solution of this application, the decision-making system comprehensively assesses the game state. When it detects that the game screen is in a low-movement state for an extended period (high SSIM index, small inter-frame variation) and the frequency of user keyboard and mouse operations is very low, the system determines the current state as a "low-value phase" and automatically reduces the frame rate to an extremely low level (e.g., 0.1 frames per second), only used for basic monitoring, significantly reducing GPU computing load and keeping the computer cool and quiet. Suddenly, when the system senses a team fight signal through game data, it immediately wakes up and instantly maximizes frame rate and recognition computing power, ensuring that every skill release and every brilliant combination in the team fight is accurately captured. After the team fight ends, the system returns to a low-power monitoring state. In this way, computing resources are used effectively throughout the game, ensuring complete recording of highlight moments while greatly reducing idle power consumption and improving the user experience.

[0134] This application also proposes an electronic device, such as... Figure 9As shown, the device includes at least one processor and a display. The processor is configured to: monitor target feature data of a target application of an electronic device during operation; in response to the target feature data satisfying a target triggering condition, control the electronic device to acquire frame data of the application interface of the target application from the display at a current frame acquisition frequency, and adjust the acquisition frequency to a target frame acquisition frequency, wherein the target frame acquisition frequency is greater than or less than the current frame acquisition frequency; input the frame data acquired at the target frame acquisition frequency to a target processing model to generate a target file, wherein the target processing model belongs to or does not belong to the electronic device.

[0135] In this embodiment, the target processing model can be deployed in an electronic device, or it can be deployed in a cloud or network device outside of the electronic device.

[0136] The electronic device in this embodiment monitors the target feature data of the target application during its operation. In response to the target feature data meeting the target triggering conditions, the electronic device controls the electronic device to adjust the frame data acquisition frequency from the current frame acquisition frequency to the target frame acquisition frequency. In this way, the frame acquisition frequency is dynamically adjusted according to the target feature data, thereby reducing the computational overhead while avoiding the omission of important frame data.

[0137] The electronic device in this application embodiment can be a terminal, or it can be any other device besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. The embodiments disclosed in this disclosure do not impose specific limitations.

[0138] The processors mentioned above can be general-purpose processors, including CPUs, NPs (Network Processors), etc.; they can also be DSPs (Digital Signal Processors), ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0139] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0140] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.

Claims

1. A control method for an electronic device, comprising: The target application of monitoring electronic equipment uses target characteristic data during operation; In response to the target feature data satisfying the target triggering condition, the electronic device is controlled to adjust from acquiring the frame data of the application interface of the target application at the current frame acquisition frequency to acquiring the frame data at the target frame acquisition frequency, wherein the target frame acquisition frequency is greater than or less than the current frame acquisition frequency. The frame data acquired at the target frame rate is input into the target processing model to generate the target file.

2. The method according to claim 1, wherein the target feature data of the target application of the monitoring electronic device during operation includes: When an electronic device acquires video frames from a target video stream at a default first frame capture frequency, it performs monitoring on at least one of the following: frame content change data of the acquired video frames, operation behavior data of the target user on the electronic device, and audio parameter change data in the acquired audio stream. The target video stream is video data obtained by performing video capture operation on the application interface of the target application. or, If the electronic device does not perform video capture operation on the application interface of the target application, the operation data of the target user's operation on the electronic device and / or the target peripheral device and / or the target user's emotional parameters are monitored.

3. The method according to claim 1 or 2, wherein the response to the target feature data satisfying the target triggering condition includes: Calculate the probability value of the target event occurring during the operation of the target application based on the target feature data; If the probability value is greater than or less than the corresponding probability value, it is determined that the target triggering condition is met; Correspondingly, controlling the electronic device to adjust from acquiring frame data of the application interface of the target application at the current frame acquisition frequency to acquiring frame data at the target frame acquisition frequency includes: The target frame rate is determined based on the probability value; The image or video frames of the application interface are acquired at the current frame rate, and then acquired at the target frame rate.

4. The method according to claim 3, wherein calculating the probability value of the target application occurring during operation based on the target feature data includes: The rate of change of the application interface during operation of the target application is determined based on the frame content change data of the video frames of the application interface of the target application obtained. Based on the target user's operational behavior data on the electronic device, determine the target user's operational intensity and / or emotional parameters during the operation of the target application; The probability value of the target event is calculated based on at least one of the following: the rate of change of the screen, the intensity of the target user's operation, the target user's emotional parameters, and the audio parameter change data in the acquired audio stream.

5. The method according to claim 4, wherein calculating the probability value of the target event based on at least one of the image change rate, the target user's operational intensity, the target user's emotional parameters, and the audio parameter change data in the acquired audio stream includes: Determine the prediction weights assigned to different types of target feature data; Based on the screen change rate, the target user's operational intensity and emotional parameters, the audio parameter change data in the acquired audio stream, and their respective prediction weights, the probability value of the target event occurring is calculated.

6. The method of claim 3, further comprising at least one of the following: If the probability value is a first probability value, and the first triggering condition is determined to be met, the electronic device is controlled to maintain the current acquisition of the image frame or video frame at the default first frame acquisition frequency. If the probability value is the second probability value, and the second triggering condition is determined to be met, the electronic device is controlled to increase from the current default first frame acquisition frequency to the default second frame acquisition frequency to acquire the image frame or video frame. If the probability value is the first probability value, and the first triggering condition is met, the electronic device is controlled to reduce the current default second frame-taking frequency to the default first frame-taking frequency to acquire the image frame or video frame.

7. The method according to claim 3, wherein, Determining the target frame rate based on the probability value includes: The target frame rate is determined based on the probability value range within which the probability value falls; or... The target frame rate is determined based on the probability value range of the probability value and the application attribute information of the target application.

8. The method according to claim 7, wherein, Determining the target frame rate based on the probability value range in which the probability value falls includes at least one of the following: When the probability value is within the range of the first probability value, the third frame rate corresponding to the range of the first probability value is determined as the target frame rate, and the third frame rate is 0. When the probability value is within the range of the second probability value, the fourth frame rate corresponding to the range of the second probability value is determined as the target frame rate, wherein the fourth frame rate is not greater than the first frame rate, which is the minimum default frame rate of the electronic device. If the probability value is within the range of the third probability value, the fifth frame rate corresponding to the range of the third probability value is determined as the target frame rate. When the probability value is within the range of the fourth probability value, the sixth frame-taking frequency corresponding to the range of the fourth probability value is determined as the target frame-taking frequency, wherein the sixth frame-taking frequency is not less than the second frame-taking frequency, which is the maximum default value of the electronic device.

9. The method according to claim 1, wherein inputting the frame data acquired at the target frame acquisition frequency into the target processing model to generate the target file includes at least one of the following: The video frames or image frames acquired at the target frame rate are input into the first processing model to generate the first highlight video file. The first processing model is an artificial intelligence model that can identify highlight events and generate highlight videos. The video frames or image frames acquired at the target frame rate and the first association information of the target object in the video frames or image frames are input into the second processing model to generate a second highlight video file. The second processing model is an artificial intelligence model that can identify highlight events and generate highlight videos. The video frames or image frames acquired at the target frame rate and the second association information of the target object in the video frames or image frames are input into the third processing model to generate a target summary file or a target record file. The video frames or image frames acquired at the target frame rate and the second associated information of the target object in the video frames or image frames are input into the fourth processing model to generate the target poster file.

10. An electronic device comprising at least one processor and a display, the processor being configured to: The target application of monitoring electronic equipment uses target characteristic data during operation; In response to the target feature data satisfying the target triggering condition, the electronic device is controlled to obtain frame data of the application interface of the target application from the display at the current frame rate, and then adjusted to obtain the frame data at the target frame rate, wherein the target frame rate is greater than or less than the current frame rate. The frame data acquired at the target frame rate is input into the target processing model to generate a target file, wherein the target processing model may or may not belong to the electronic device.

Images