A control method and system for an intelligent handheld device

Abstract

This invention discloses a method and system for controlling an intelligent handheld device. The method specifically includes: acquiring real-time power consumption and heat generation data of the intelligent handheld device; dynamically adjusting the processor frequency and display refresh rate of the intelligent handheld device based on a pre-built frequency adjustment table and the real-time power consumption and heat generation data; analyzing user interaction behavior data in real-time using a pre-built functional pattern recognition model to obtain the functional pattern recognition result of the intelligent handheld device; determining the optimal display parameter configuration based on the functional pattern recognition result; and dynamically calculating the optimal display brightness and optimal color parameters of the intelligent handheld device using an adaptive mapping algorithm based on ambient light intensity data, user viewing distance information, and user gaze area information. This invention can provide the best visual experience in different usage scenarios of the intelligent handheld device, while extending the device's battery life and improving user satisfaction.

Description

Technical Field

[0001] This invention relates to the field of intelligent handheld device technology, and in particular to a method and system for controlling an intelligent handheld device. Background Technology

[0002] With the increasing popularity of smart handheld consoles, users are demanding higher standards in terms of performance, power consumption, display quality, and user comfort. However, existing smart handheld consoles still have many unresolved issues regarding operation and display, which seriously affect the user experience.

[0003] First, most traditional handheld smart devices use fixed processor and display refresh rates. This design prevents the device from effectively adjusting power consumption and heat generation in different application scenarios, leading to problems such as shortened battery life and overheating. Especially when handling complex tasks, excessive power consumption and heat generation not only accelerate battery drain but may also damage the device hardware, reducing its stability and lifespan.

[0004] Secondly, existing smart handheld consoles have shortcomings in adjusting display parameters. Traditional handheld consoles typically cannot adjust display parameters in real time based on user interaction, resulting in unsatisfactory display effects in different functional modes. For example, in game mode, users may need a higher refresh rate and more vibrant colors, while in reading mode, users pay more attention to the brightness and color accuracy of the display. However, existing handheld consoles often cannot adjust to these needs in real time, thus affecting the user's visual experience.

[0005] Furthermore, traditional handheld smart devices suffer from another problem in display parameter adjustment: they cannot dynamically adjust based on ambient light intensity, user status, and other factors. This results in poor display quality and may even cause eye strain. Especially in dimly lit environments, excessively high screen brightness can irritate the user's eyes, while in bright light, insufficient screen brightness makes it difficult to see the screen content.

[0006] Furthermore, existing handheld game consoles are prone to issues such as screen stuttering and blurring during fast-paced action or scene transitions. These problems are mainly due to the limited response time of the display and the excessively long pixel illumination time. Traditional handheld consoles typically use simple image processing algorithms for smoothing, but the results are unsatisfactory and cannot effectively improve image quality. Summary of the Invention

[0007] The purpose of this invention is to provide a method and system for controlling an intelligent handheld device, which can provide the best visual experience in different usage scenarios of the intelligent handheld device, while extending the device's battery life and improving user satisfaction, thereby solving at least one of the aforementioned problems in the prior art.

[0008] In a first aspect, the present invention provides a method for controlling an intelligent handheld device, the method specifically comprising:

[0009] The system acquires real-time power consumption and heat generation data of the intelligent handheld device, and dynamically adjusts the processor frequency and display refresh rate of the intelligent handheld device based on a pre-built frequency adjustment table and the real-time power consumption and heat generation data.

[0010] The user interaction behavior data is analyzed in real time by a pre-built functional pattern recognition model to obtain the functional pattern recognition result of the intelligent handheld device, and the optimal display parameter configuration is determined based on the functional pattern recognition result.

[0011] Based on ambient light intensity data, user viewing distance information, and user gaze area information, an adaptive mapping algorithm is used to dynamically calculate the optimal display brightness and optimal color parameters of the intelligent handheld device.

[0012] Based on user grip posture data and user eye movement data, predictive user behavior data is obtained, and the display performance data of the intelligent handheld device is dynamically adjusted based on the predictive user behavior data.

[0013] When the intelligent handheld device is in a fast-moving state or when the screen is switching, the motion vectors of the preceding and following frames are analyzed, and a frame interpolation algorithm is used to smooth the preceding and following frames.

[0014] Secondly, the present invention provides a control system for an intelligent handheld device, the system specifically comprising:

[0015] The first control module is used to acquire real-time power consumption data and heat generation data of the intelligent handheld device, and dynamically adjust the processor frequency and display refresh rate of the intelligent handheld device according to the real-time power consumption data and the heat generation data based on a pre-built frequency adjustment table.

[0016] The second control module is used to analyze user interaction behavior data in real time through a pre-built functional pattern recognition model, obtain the functional pattern recognition result of the intelligent handheld device, and determine the optimal display parameter configuration based on the functional pattern recognition result.

[0017] The third control module is used to dynamically calculate the optimal display brightness and optimal color parameters of the intelligent handheld device based on ambient light intensity data, user viewing distance information, and user gaze area information using an adaptive mapping algorithm.

[0018] The fourth control module is used to obtain user prediction behavior data based on user grip posture data and user eye movement data, and to dynamically adjust the display performance data of the intelligent handheld device based on the user prediction behavior data;

[0019] The fifth control module is used to smooth the images of the preceding and following frames by analyzing the motion vectors of the images in the preceding and following frames and using a frame interpolation algorithm when the intelligent handheld device is in a fast motion or screen switching state.

[0020] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, and a computer program stored in the memory, wherein when the computer program is executed on the processor, it implements the control method of an intelligent handheld device as described in any of the above methods.

[0021] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the control method of an intelligent handheld device as described in any of the above methods.

[0022] Compared with the prior art, the present invention has at least one of the following technical effects:

[0023] 1. This invention can provide the best visual experience in different usage scenarios of intelligent handheld devices, while extending the device's battery life and improving user satisfaction.

[0024] 2. This invention can intelligently balance power consumption and performance based on current usage through dynamic adjustment, effectively reducing the real-time power consumption and heat generation of intelligent handheld devices, extending battery life, and ensuring stable operation of the device while avoiding overheating problems.

[0025] 3. The reinforcement learning algorithm of this invention can automatically learn and optimize the adjustment strategies of processor frequency and display refresh rate to adapt to different usage scenarios and needs, improve the accuracy and efficiency of adjustment, and thus enhance the user experience.

[0026] 4. This invention analyzes user interaction behavior in real time, intelligently identifies the handheld device's function mode, and automatically adjusts display parameters according to the needs of different modes to improve the display effect and meet the user's visual needs in different scenarios.

[0027] 5. This invention dynamically adjusts the brightness and color parameters of the display screen based on information such as ambient light intensity, user viewing distance, and user gaze area to achieve personalized display effects and improve visual comfort and user experience.

[0028] 6. This invention predicts user behavior and adjusts display performance data, such as brightness and contrast, in advance to meet the user's upcoming usage needs, thereby improving response speed and user experience.

[0029] 7. When the intelligent handheld device is in rapid motion or during screen switching, this invention reduces screen stuttering and blurring through frame interpolation algorithm, improves screen smoothness and clarity, and enhances the visual experience.

[0030] 8. This invention collects and analyzes user experience data in different usage scenarios to establish a user experience evaluation model, and adjusts the display parameter combination based on the evaluation results to optimize the user experience. This method ensures that the display parameters of the smart handheld device always meet the user's needs and preferences, thereby improving user satisfaction. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is a flowchart illustrating a method for controlling an intelligent handheld device according to an embodiment of the present invention.

[0033] Figure 2 This is a schematic diagram of the control system of an intelligent handheld device provided in an embodiment of the present invention;

[0034] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0035] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0036] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0037] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0038] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0039] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0040] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0041] In this application embodiment, the entity executing the process includes a terminal device. This terminal device includes, but is not limited to, devices capable of executing the methods disclosed in this application, such as servers, computers, smartphones, and tablets. Figure 1 A flowchart illustrating a control method for an intelligent handheld device according to an embodiment of the present invention is shown below, in detail:

[0042] S101, acquire real-time power consumption data and heat generation data of the intelligent handheld device, and dynamically adjust the processor frequency and display refresh rate of the intelligent handheld device according to the pre-built frequency adjustment table and the real-time power consumption data and the heat generation data.

[0043] In this embodiment, a processor supporting Dynamic Voltage and Frequency Scaling (DVFS) is selected. This processor can adjust the frequency according to a preset frequency scaling table. It is equipped with high-precision power consumption and temperature sensors for real-time monitoring of the handheld device's power consumption and heat generation. The display screen uses a panel that supports multiple refresh rates for dynamic adjustment as needed. The handheld device's operating system or firmware is developed, integrating a power consumption and temperature monitoring module, a frequency scaling module, and a display refresh rate scaling module. The power consumption and temperature monitoring module reads sensor data and transmits it to the frequency scaling module. The frequency scaling module dynamically adjusts the processor's frequency based on a pre-built frequency scaling table, combined with real-time power consumption and heat generation data. The display refresh rate scaling module dynamically adjusts the display's refresh rate based on the processor's frequency, the currently running application, and user settings.

[0044] The frequency adjustment table is a preset two-dimensional array containing processor frequencies and display refresh rates corresponding to different power consumption and temperature ranges. For example, when power consumption is low and temperature is moderate, the processor frequency and display refresh rate can be set to lower values ​​to save energy; when power consumption is high and temperature is close to the critical value, the processor frequency and display refresh rate need to be reduced to prevent overheating.

[0045] Power and temperature sensors continuously monitor the handheld device's power consumption and temperature, transmitting the data to the operating system. Based on the received data, the operating system determines the current power consumption and temperature range of the handheld device. According to the determination, it looks up the corresponding processor frequency and display refresh rate in the frequency adjustment table. The operating system sends a frequency adjustment command to the processor, adjusting the processor frequency to the found value. Simultaneously, the operating system also adjusts the display refresh rate to match the processor frequency change.

[0046] In this embodiment, by dynamically adjusting the processor frequency and display refresh rate, the handheld device can minimize power consumption and extend battery life while maintaining performance. Adjusting the frequency based on real-time temperature data helps prevent overheating and improves system stability and reliability. Dynamically adjusting the display refresh rate based on the currently running application and user settings provides a smoother and more comfortable visual experience.

[0047] S102, the user interaction behavior data is analyzed in real time through a pre-built functional pattern recognition model to obtain the functional pattern recognition result of the intelligent handheld device, and the optimal display parameter configuration is determined based on the functional pattern recognition result.

[0048] In this embodiment, the intelligent handheld device is equipped with multiple sensors to capture user interaction data, such as the position, frequency, and pressure of touches on the screen, as well as the user's voice commands. Simultaneously, the system records display performance data of the handheld device in different functional modes, such as brightness, color saturation, and contrast. A functional pattern recognition model is constructed using machine learning algorithms, such as Support Vector Machines (SVM) or deep learning models. Historical user interaction data and corresponding display performance data are used as a training set to train the model, enabling it to accurately identify the handheld device's functional modes. During operation, the intelligent handheld device collects user interaction data in real time and inputs it into the functional pattern recognition model for analysis. Based on the input data, the model quickly identifies the current functional mode of the handheld device, such as game mode, reading mode, or video mode. According to the identified functional mode, the system selects the optimal configuration from a preset display parameter configuration library. For example, in game mode, the system may choose a higher refresh rate and brightness to provide a smoother gaming experience; while in reading mode, it may choose lower brightness and more comfortable color saturation to reduce eye fatigue.

[0049] In this embodiment, by analyzing user interaction data in real time, the intelligent handheld device can accurately identify the user's functional needs and provide personalized display parameter configurations, thereby improving the user experience. Depending on different functional modes, the system can automatically adjust parameters such as screen brightness and color saturation to provide a display effect that better meets the user's needs. In scenarios where high brightness or high refresh rate is not required, the system can automatically reduce these parameters, thereby saving energy and reducing carbon emissions.

[0050] S103, based on ambient light intensity data, user viewing distance information, and user gaze area information, an adaptive mapping algorithm is used to dynamically calculate the optimal display brightness and optimal color parameters of the intelligent handheld device.

[0051] In this embodiment, the intelligent handheld device is equipped with a light sensor, a distance sensor, and an eye-tracking sensor, used to acquire ambient light intensity data, user viewing distance information, and user gaze area information, respectively. The handheld device has a built-in adaptive mapping algorithm module for processing sensor data and calculating optimal display brightness and color parameters. The sensors collect data on ambient light intensity, user viewing distance, and user gaze area in real time. The adaptive mapping algorithm module receives the sensor data, performs preprocessing and feature extraction. Based on the preprocessed data, the algorithm module applies the adaptive mapping algorithm to calculate the optimal display brightness and color parameters. The handheld device's display dynamically adjusts the brightness and color parameters according to the calculation results to provide the most comfortable viewing experience.

[0052] The ambient light intensity data, user viewing distance information, and user gaze area information are preprocessed, including data cleaning, noise reduction, and normalization, to construct feature vectors describing the current environment and user state. An adaptive mapping algorithm is then applied to map these feature vectors to the optimal display brightness and color parameter space. The algorithm employs machine learning or deep learning techniques, optimizing the mapping relationship by training on historical data. The most comfortable display brightness is calculated based on the ambient light intensity and user viewing distance. Optimal color saturation, contrast, and hue parameters are calculated based on the user gaze area and the current display state.

[0053] In this embodiment, by adjusting the brightness and color parameters of the display screen in real time, the handheld device's display effect is made more suitable to the current environment and user status, improving the user's viewing comfort. When the ambient light intensity is low or the user's viewing distance is far, the display screen brightness is automatically reduced to decrease energy consumption. By optimizing color parameters, the display screen's stimulation to the eyes is reduced, minimizing the impact of prolonged handheld device use on vision.

[0054] S104. Based on the user's grip posture data and the user's eye movement data, obtain the user's predicted behavior data, and dynamically adjust the display performance data of the intelligent handheld device using the user's predicted behavior data.

[0055] In this embodiment, the intelligent handheld device incorporates a built-in sensor array, including posture sensors (such as gyroscopes and accelerometers) and eye-tracking sensors, to capture real-time data on the user's grip posture and eye movement. The device is also equipped with a high-performance processor and an advanced machine learning algorithm module to process sensor data, predict user behavior, and dynamically adjust display performance. Specifically, the sensors collect the user's grip posture and eye movement data in real time. The processor receives the sensor data, performs preprocessing and feature extraction, and the machine learning algorithm module predicts the user's future behavior (such as game operations, page turning, etc.) based on the preprocessed data. Based on the predicted behavior data, the processor dynamically adjusts the device's display performance data (such as brightness, contrast, color saturation, etc.) to provide a more user-friendly visual experience. The posture sensors capture the user's grip angle, direction, and other posture information. The eye-tracking sensors track the user's eye movement trajectory in real time, determining the area and focus of the user's current gaze. The machine learning algorithm module combines historical user behavior and current sensor data, using techniques such as pattern recognition and regression analysis to predict the user's future behavior. For example, if the user's gaze lingers on a game button for an extended period, the algorithm may predict that the user is about to click that button to initiate a game action. Based on predictive behavior data, the processor dynamically adjusts the handheld's display performance. For example, if it predicts that the user will engage in gaming, it increases the screen's refresh rate and color saturation to enhance the smoothness and visual effects of the game. If it predicts that the user will be reading, it reduces the screen's brightness and contrast to reduce eye strain.

[0056] In this embodiment, by capturing and analyzing user grip posture and eye movement data in real time, the intelligent handheld device can more accurately predict user behavior and adjust display performance accordingly, thereby providing a visual experience that better meets user needs. Based on the predicted user behavior data, the brightness, contrast, color saturation, and other parameters of the display screen are dynamically adjusted to make the display effect more suitable for the current scene and user needs.

[0057] S105, when the intelligent handheld device is in a fast motion or screen switching state, the motion vectors of the preceding and following frames are analyzed, and a frame interpolation algorithm is used to smooth the preceding and following frames.

[0058] In this embodiment, the intelligent handheld device incorporates a high-performance image processor and storage unit for real-time capture, storage, and processing of video frame images. The handheld device is also equipped with a motion vector analysis module and a frame interpolation algorithm module, used to analyze the motion vectors of consecutive frames and apply frame interpolation algorithms for smoothing. During rapid movement or screen transitions, the image processor captures video frame images in real-time and stores them in the storage unit. The motion vector analysis module reads consecutive frames from the storage unit, analyzes, and calculates the motion vectors between them. The frame interpolation algorithm module generates intermediate frame images based on the motion vector information, using a frame interpolation algorithm to smoothly transition between consecutive frames. The processed image is then presented to the user through the display screen, providing a smoother visual experience. Specifically, the motion vector analysis module calculates the motion vectors between identical objects in consecutive frames by comparing their positional changes. The motion vectors include two attributes: direction and magnitude, representing the object's direction of movement and distance, respectively. Based on motion vector information, the frame interpolation algorithm module generates intermediate frame images. The algorithm can employ linear interpolation, quadratic interpolation, or higher-order interpolation methods. It calculates the corresponding pixel values ​​in the intermediate frame image based on the pixel values ​​and motion vector information from the preceding and following frames. In particular, quadratic interpolation or higher-order interpolation methods can sense the acceleration of motion in the video, generating more accurate intermediate frame images and thus providing a smoother visual transition effect. By applying the frame interpolation algorithm, the smart handheld device can generate smoother video transitions during fast motion or scene changes. The insertion of intermediate frame images reduces the abruptness between preceding and following frames, making the video smoother and more natural.

[0059] In this embodiment, by applying a frame interpolation algorithm, the intelligent handheld device can generate smoother video transitions during fast-moving scenes or screen changes, improving visual fluency. The insertion of intermediate frame images reduces the abruptness between consecutive frames, making the video more coherent and natural. This smooth video transition enhances the user experience when watching videos or playing games on the handheld device.

[0060] In some embodiments, step S101 above, which involves dynamically adjusting the processor frequency and display refresh rate of the smart handheld device based on a pre-built frequency adjustment table, according to the real-time power consumption data and the heat generation data, further includes the following prior steps:

[0061] The real-time power consumption data, heat generation data, processor frequency, and display refresh rate of the intelligent handheld device are used as the state space, and the various adjustment operations of the processor frequency and display refresh rate are used as the action space, with the reduction of the real-time power consumption and heat generation of the intelligent handheld device as the reward function.

[0062] Based on the state space, the action space, and the reward function, a reinforcement learning algorithm is used for modeling and training to obtain a frequency adjustment model. The frequency adjustment model is used to output a frequency adjustment table, which includes the data correlation between real-time power consumption, heat generation, processor frequency, and display refresh rate.

[0063] In this embodiment, real-time power consumption data, heat generation data, processor frequency, and display refresh rate of the handheld device are acquired and used as the state space of the reinforcement learning algorithm. Various adjustment combinations of the processor frequency and display refresh rate are defined as the action space of the reinforcement learning algorithm. A reward function for the reinforcement learning algorithm is constructed with the optimization objective of reducing the real-time power consumption and heat generation of the handheld device. Based on the determined state space, action space, and reward function, a Q-learning reinforcement learning algorithm is used to model and train the frequency adjustment strategy. Through multiple rounds of iterative training, the Q-value table is continuously optimized and updated, ultimately obtaining the optimal frequency adjustment strategy that achieves reduced power consumption and heat generation. The trained optimal frequency adjustment strategy is transformed into a frequency adjustment model for subsequent online dynamic frequency adjustment. Based on the real-time detected power consumption and heat generation data, the frequency adjustment model outputs a frequency adjustment table containing processor frequency and display refresh rate adjustment values, guiding the handheld device to perform dynamic frequency adjustment and achieve continuous optimization of power consumption and heat generation.

[0064] For example, the frequency adjustment model is built using a reinforcement learning algorithm to optimize the device's power consumption and heat dissipation performance. The model's state space includes real-time power consumption data, heat generation data, processor frequency, and display refresh rate. These parameters collectively reflect the device's current operating state. For instance, a handheld console running a demanding game might consume up to 5W of power, generate 40°C of heat, have a processor frequency of 2.4GHz, and a screen refresh rate of 60Hz.

[0065] The operating space consists of combinations of adjustments to the processor frequency and the display refresh rate. Processor frequencies have multiple levels, such as 1.8GHz, 2.0GHz, and 2.2GHz; display refresh rates may have options like 30Hz, 60Hz, and 90Hz. Different combinations will produce different performance and power consumption effects.

[0066] The reward function aims to reduce real-time power consumption and heat generation. This is because excessive power consumption accelerates battery drain, while excessive heat generation can lead to performance degradation or safety hazards. By appropriately adjusting the frequency, energy consumption and heat dissipation can be optimized while maintaining performance.

[0067] Reinforcement learning algorithms learn to select the optimal action in various states by continuously trying different frequency adjustment strategies. For example, when the device temperature is detected to be close to a critical value, the algorithm may reduce the processor frequency and screen refresh rate to reduce heat generation. Conversely, at lower temperatures, it may increase the frequency to improve performance. During training, the algorithm explores various possible state-action combinations and continuously adjusts its strategy based on feedback from the reward function. This process may require a large amount of simulated or real-world device test data. Ultimately, the algorithm converges to an optimal strategy that balances performance and power consumption. The output of the frequency adjustment model is a frequency adjustment table containing data relationships between real-time power consumption, heat generation, processor frequency, and display refresh rate. This table may be presented as a multi-dimensional matrix, with each dimension corresponding to a parameter. For example, when the power consumption is 3W and the heat generation is 35℃, the table may suggest setting the processor frequency to 2.0GHz and the display refresh rate to 60Hz. This reinforcement learning-based frequency adjustment method is more flexible and intelligent than traditional fixed threshold adjustment methods. It can dynamically adjust the frequency according to the device's real-time status, maximizing battery life while ensuring user experience. Furthermore, this method is adaptive, continuously optimizing its adjustment strategy as device usage changes. By implementing this intelligent frequency adjustment, the intelligent handheld device can maintain an optimal balance between performance and power consumption in different usage scenarios. For example, when playing casual games, the system may reduce the processor frequency and screen refresh rate to save power; while when running demanding 3D games, it will appropriately increase the frequency to ensure a smooth gaming experience. This dynamic adjustment not only enhances the user experience but also extends the device's lifespan.

[0068] In some embodiments, step S102 above, which involves analyzing user interaction behavior data in real time using a pre-built functional pattern recognition model to obtain the functional pattern recognition result of the intelligent handheld device, and determining the optimal display parameter configuration based on the functional pattern recognition result, further includes the following steps before:

[0069] Acquire display performance data, historical application scenario data, and historical user interaction behavior data of the intelligent handheld device under different functional modes;

[0070] The display performance data, historical application scenario data, and historical user interaction behavior data are correlated and analyzed to form a first training dataset;

[0071] Using the first training dataset as input, a support vector machine algorithm is used for modeling and training to construct a functional pattern recognition model.

[0072] In this embodiment, display performance data, historical application scenario data, and historical user interaction behavior data of the intelligent handheld device under different functional modes are acquired. Data preprocessing is performed on the acquired display performance data, historical application scenario data, and historical user interaction behavior data, including data cleaning and data normalization. Based on the preprocessed data, association rules and patterns between the data are mined using an association analysis algorithm to form a first training dataset. The first training dataset is randomly divided into a training set and a test set; the training set is used for model training, and the test set is used for model evaluation. A support vector machine algorithm is used to model and train the training set. By adjusting the algorithm parameters and iterative optimization, a functional pattern recognition model is obtained. The performance of the trained functional pattern recognition model is evaluated using the test set data. If the model performance meets a preset threshold, it is saved as the final model. When the intelligent handheld device is working, its display performance data and user interaction behavior data are acquired in real time and input into the functional pattern recognition model for prediction to determine the current functional mode.

[0073] For example, firstly, acquire display performance data of the handheld device in different functional modes, such as frame rate, resolution, and color depth. For instance, in game mode, the frame rate may reach 60fps, the resolution is 1920x1080, and the color depth is 32-bit; while in reading mode, the frame rate may drop to 30fps, the resolution remains unchanged, and the color depth is reduced to 16-bit to save power. Historical application scenario data includes the types of applications used by users, usage duration, and usage frequency. For example, users often use game applications for 2 hours on weekday evenings and tend to use reading applications for 1 hour on weekend days. This data reflects user habits and preferences. Historical user interaction behavior data involves the user's interaction methods with the device, such as touchscreen operation frequency, button usage, and voice command usage frequency. For example, in game mode, users may frequently use the touchscreen and physical buttons; while in video viewing mode, user interaction is less frequent, mainly focusing on volume adjustment and pause / play operations. Perform correlation analysis on this data to form the first training dataset. For example, it may be found that in gaming mode, high frame rates, high resolutions, and frequent touchscreen operations are strongly correlated; while in reading mode, low frame rates, lower color depths, and fewer screen interactions are correlated.

[0074] Support Vector Machine (SVM) is a powerful classification algorithm suitable for building functional pattern recognition models. SVM separates data points into different categories by finding the optimal hyperplane in a high-dimensional space. In this example, each functional pattern (such as gaming, reading, video watching, etc.) can be considered a category. The advantage of SVM lies in its ability to handle non-linear classification problems and its good generalization ability even with small sample sizes. During training, the SVM algorithm learns how to distinguish different functional patterns based on input features (display performance, application scenario, user interaction behavior). For example, it might learn that a combination of features such as high frame rate, high resolution, and frequent touchscreen operations typically corresponds to gaming mode; while low frame rate, low color depth, and less screen interaction might correspond to reading mode. Functional pattern recognition models built in this way can analyze the current device state and user behavior in real time to accurately identify the current functional pattern. This allows smart handheld devices to automatically adjust device parameters, such as processor frequency and display refresh rate, to optimize performance and power consumption, thereby improving user experience and device battery life. For example, when the model detects that a user is playing a high-performance game, it can automatically increase the processor frequency and display refresh rate; when it detects reading mode, it can reduce these parameters to save power.

[0075] In some embodiments, step S103 above, which involves dynamically calculating the optimal display brightness and optimal color parameters of the intelligent handheld device using an adaptive mapping algorithm based on ambient light intensity data, user viewing distance information, and user gaze area information, specifically includes:

[0076] Ambient light intensity data and user viewing distance information are acquired. Based on a pre-built mapping table between ambient light intensity, user viewing distance and display parameters, the first display parameters of the intelligent handheld device are determined according to the ambient light intensity data and the user viewing distance information. The first display parameters include the brightness of the first display screen and the first color parameters.

[0077] Based on the complexity of the different display content of the intelligent handheld device, the display screen of the intelligent handheld device is divided into several display areas;

[0078] Acquire user gaze area information, and determine second display parameters for each display area based on the user gaze area information. The second display parameters include the brightness of the second display screen and second color parameters.

[0079] The optimal display parameters of the intelligent handheld device are determined based on the first display parameters and the second display parameters. The optimal display parameters include the optimal screen brightness and the optimal color parameters.

[0080] In this embodiment, ambient light intensity data and user viewing distance information are acquired and used as input data for adjusting the display parameters of the intelligent handheld device. Based on a pre-established mapping table between ambient light intensity, user viewing distance, and display parameters, the brightness of the first display screen and the first color parameter corresponding to the current input data are determined. It is determined whether the brightness of the first display screen exceeds a preset display screen brightness threshold range. If it does, the brightness of the first display screen is adjusted to the threshold range. It is also determined whether the first color parameter exceeds a preset color parameter threshold range. If it does, the first color parameter is adjusted to the threshold range.

[0081] The system acquires the display content of the smart handheld device, analyzes its complexity, and divides the screen into several display areas based on this complexity. Eye-tracking technology is used to acquire the user's gaze area information to determine the area the user is currently focusing on. Based on this gaze area information, secondary display parameters for each area are determined, including secondary display brightness and secondary color parameters. For the area the user is focusing on, the secondary display brightness is set to a higher value, while the brightness of the secondary display in other areas is set to a lower value, guiding the user's gaze to focus on key areas through differentiated screen brightness. Similarly, for the area the user is focusing on, the secondary color parameters are set to values ​​with high saturation and high contrast, while the secondary color parameters for other areas are set to values ​​with low saturation and low contrast, highlighting key display content through differentiated color effects. The system continuously tracks changes in the user's gaze area and dynamically adjusts the secondary display parameters of each area in real time, providing personalized display effects, reducing eye strain, and improving the user experience.

[0082] For example, firstly, information on ambient light intensity and user viewing distance is obtained, as these two factors directly affect display performance. For instance, in a bright outdoor environment, screen brightness needs to be increased to ensure clarity; while in a dimly lit indoor environment, excessive brightness can lead to eye strain. Similarly, the distance between the user and the device also affects optimal display performance. A pre-established mapping table can quickly determine the most suitable display parameters for the current environment. Specifically, assuming a sunny outdoor environment with an illuminance of 50,000 lux and a user viewing distance of approximately 30 cm, the system might adjust the screen brightness to its maximum value (e.g., 500 nits) and increase color saturation and contrast to ensure visibility in strong light, based on the mapping table. Conversely, in an indoor environment with an illuminance of only 100 lux and a user viewing distance of 50 cm, the system might reduce the brightness to 100 nits and adjust the color temperature to a warmer 3000K to reduce blue light stimulation to the eyes.

[0083] Next, dividing the display area based on the complexity of the displayed content is an intelligent optimization method. For example, in a game interface, the complexity of the character action area and the status bar differs significantly. The system might divide the screen into high, medium, and low complexity areas. High-complexity areas (such as the character action area) might occupy 60% of the central screen area, medium-complexity areas (such as background elements) 20%, and low-complexity areas (such as the status bar) the remaining 20%. Obtaining information about the user's gaze area is a key step in optimizing the display effect. Through the front-facing camera or eye-tracking technology, the system can detect the user's gaze focus in real time. For example, in a reading application, if the system detects that the user is looking at the text area in the upper left corner of the screen, it will prioritize improving the display parameters of that area. Specifically, it might increase the brightness of that area by 10%, increase the contrast, and fine-tune the color temperature to improve text clarity. For areas that the user is not currently looking at, the display parameters can be appropriately reduced to save energy.

[0084] Finally, the system needs to comprehensively consider both the primary and secondary display parameters to determine the optimal display effect. This process involves balancing multiple factors. For example, if the primary display parameter suggests an overall brightness of 300 nits, while the secondary display parameter for the user's viewing area suggests 350 nits, the system might adopt a compromise, setting the brightness of the viewing area to 325 nits and the non-viewing area to 275 nits. This ensures clarity in the viewing area while avoiding visual discomfort caused by excessive brightness differences between different areas of the screen. Optimization of color parameters is equally important. If the primary display parameter suggests a color temperature of 6500K (a cool tone), while the content in the user's viewing area (such as a warm indoor scene) is more suitable for warm colors, the system might adjust the color temperature of the viewing area to 5500K while slightly increasing the saturation to present a more comfortable and immersive visual effect. Through this dynamic and intelligent adjustment of display parameters, the intelligent handheld device can provide users with the best visual experience in different environments and usage scenarios, while optimizing energy consumption and extending device usage time. This technology not only improves user satisfaction but also reflects the intelligence level of the device, laying the foundation for more personalized and scenario-based human-computer interaction in the future.

[0085] In some embodiments, step S104 above, which involves obtaining user predicted behavior data based on user grip posture data and user eye movement data, and dynamically adjusting the display performance data of the intelligent handheld device using the user predicted behavior data, specifically includes:

[0086] Acquire user grip posture data and user eye movement data, as well as the corresponding user behavior results;

[0087] Preprocessing and feature extraction are performed on the user's grip posture data and the user's eye movement data to obtain key behavioral features related to the user's behavioral results;

[0088] The key behavioral features are input into a pre-trained user behavior recognition model to obtain user predicted behavior data, which includes user intent and user predicted usage status.

[0089] Based on a preset mapping table of user behavior and display performance requirements, the display performance requirements of users for intelligent handheld devices within a preset future time period are determined according to the predicted user behavior data.

[0090] Based on the display performance requirements, the display performance data of the intelligent handheld device is dynamically adjusted.

[0091] In this embodiment, user grip posture data, gaze movement data, and corresponding user behavior result data are acquired to construct a user behavior dataset. The user behavior dataset undergoes data cleaning and preprocessing to remove outlier and noisy data, and the data is normalized. Key behavioral features, including grip posture features, gaze movement features, and behavior result features, are extracted from the preprocessed user behavior data to construct a key behavioral feature vector. Based on the key behavioral feature vector, an unsupervised learning algorithm is used to perform user behavior clustering analysis to obtain different types of user behavior patterns. For each user behavior pattern, a supervised learning algorithm is used to train a user behavior recognition model to obtain a recognition model that predicts user intent and usage status. The real-time acquired user grip posture data and gaze movement data are input into the corresponding user behavior recognition model to predict the user's current usage intent and usage status in real time.

[0092] Based on user behavior prediction data, a pre-defined mapping table of user behavior and display performance requirements is consulted to determine the user's display performance needs for the smartphone within the predicted time period. These needs include parameters such as display brightness, frame rate, and resolution. Based on these determined user display performance needs, the system checks whether the current smartphone display performance settings meet the requirements. If not, a dynamic adjustment process for the display performance parameters is triggered. During this dynamic adjustment, the system retrieves the display's performance parameter range from the phone's hardware configuration information, determines the target performance parameter value based on the needs, and uses an intelligent algorithm to calculate the adjustment step size and time interval from the current parameters to the target parameters. The calculated adjustment step size and time interval are used to dynamically and progressively adjust parameters such as display brightness, frame rate, and resolution of the smartphone until the target required value is reached, thereby achieving dynamic optimization of display performance. During the adjustment of display performance parameters, the usage of hardware resources such as the phone's CPU, GPU, memory, and battery is continuously monitored. If excessive resource usage or insufficient battery power is detected, dynamic degradation adjustment of performance parameters is triggered to ensure smooth operation and battery life of the phone. The system continuously tracks changes in user behavior at different times and in different scenarios, and regularly updates the user behavior prediction model and behavior-performance mapping table to adapt to dynamic changes in user needs, thereby achieving continuous optimization of smartphone display performance.

[0093] For example, firstly, the system acquires user grip posture and gaze movement data using sensors and cameras. For instance, when a user holds the device with both hands and frequently moves their gaze, it may indicate that they are engaged in intense gaming. This raw data is preprocessed and feature extracted to transform it into meaningful key behavioral features. For example, grip posture can be transformed into finger position and pressure distribution, while gaze movement can be transformed into fixation trajectory and dwell time. These key behavioral features are then input into a pre-trained user behavior recognition model. This model may employ deep learning algorithms, such as Long Short-Term Memory (LSTM) networks, which can effectively capture the temporal features of user behavior. The model outputs user predicted behavior data, including usage intent and predicted usage state. For example, the model may predict that the user is about to start a long gaming session or is preparing to switch to reading mode. Based on a pre-defined mapping table, the system transforms the user predicted behavior data into display performance requirement information. This mapping table may be optimized through extensive user testing and feedback. For example, for a predicted gaming session, the system may increase the refresh rate and color saturation; while for reading mode, it may reduce brightness and adjust the color temperature to a warmer tone. Finally, the system dynamically adjusts the handheld device's display parameters based on the display performance requirement information. This adjustment is real-time and gradual to avoid abrupt changes that could negatively impact the user experience. For example, if it predicts a user will be gaming for the next 30 minutes, the system might gradually increase the refresh rate from 60Hz to 120Hz over 5 minutes, while simultaneously increasing color saturation by 10%. This intelligent display performance adjustment not only enhances the user experience but also optimizes energy consumption. For instance, when it predicts a user is about to end a session, the system can proactively reduce unnecessary high-performance display settings, thereby extending battery life. Furthermore, by analyzing user behavior patterns, the system can learn personalized display preferences. For example, for users who frequently use their devices at night, the system might be more inclined to automatically enable a low blue light mode at night. The implementation of this technology requires consideration of privacy protection. The collection and processing of user behavior data should be performed locally on the device to avoid the leakage of sensitive information. Simultaneously, the system should also provide manual adjustment options, allowing users to override automatic settings when needed to meet personalized needs in specific scenarios. Through this intelligent display performance optimization, smart handheld devices can better adapt to different users' habits and environmental changes, providing a more personalized and efficient user experience.

[0094] In some embodiments, step S105 above, which involves analyzing the motion vectors of the preceding and following frames and using a frame interpolation algorithm to smooth the preceding and following frames, specifically includes:

[0095] Acquire every two adjacent frames of the intelligent handheld device, and divide each two adjacent frames into a first frame and a second frame.

[0096] A block-matching-based motion estimation algorithm is used to estimate the motion of the first frame image and the second frame image to obtain the motion vector field between the first frame image and the second frame image;

[0097] Based on the motion vector field, a motion compensation frame interpolation algorithm is used to insert at least one intermediate frame image between the first frame image and the second frame image.

[0098] The intermediate frame image is weighted and fused with the first frame image and the second frame image to obtain an image sequence.

[0099] In this embodiment, a video sequence captured by the intelligent handheld device is acquired, and two adjacent frames are selected as the first and second frames to be processed. The first frame is divided into several non-overlapping image blocks of the same size. For each image block, a search window is determined in the second frame. The similarity between the image block and each candidate block in the search window is calculated, and the candidate block with the highest similarity is selected as the best matching block for that image block in the second frame. Based on the position of the image block in the first frame and the position of the best matching block in the second frame, the motion vector of the image block is calculated. The above steps are repeated for all image blocks to obtain the motion vector field between the first and second frames. The motion vector field is smoothed using a median filtering algorithm to remove isolated erroneous vectors and obtain a smooth motion vector field. Based on the motion vector field, a motion compensation frame interpolation algorithm is used to insert at least one intermediate frame between the first and second frames. The pixel positions in the intermediate frame are obtained by interpolation calculation based on the motion vectors between corresponding pixels in the first and second frames. For each pixel in the intermediate frame image, a weight coefficient is calculated based on its positional distance from the first and second frames, relating it to the corresponding pixels in the first and second frames. Based on this weight coefficient, a weighted average is taken of the pixel values ​​of each pixel in the intermediate frame image and its corresponding pixels in the first and second frames to obtain the final pixel value for each pixel in the intermediate frame image. All the interpolated intermediate frame images are then concatenated with the first and second frames in chronological order to obtain the interpolated image sequence. Motion edge detection is performed on each frame of the image sequence to extract the contour information of the moving target. The contour information is used to determine whether the motion trajectory of the moving target is continuous and smooth. If the motion trajectory shows abrupt changes or is discontinuous, the process returns to adjust the motion vector field and re-interpolates the frames; otherwise, the final generated image sequence is output.

[0100] For example, firstly, the system acquires two adjacent image frames, dividing them into a first frame and a second frame. Next, a block-matching-based motion estimation algorithm is used to analyze these two frames. This algorithm divides the image into multiple small blocks and estimates motion by comparing the positional differences of corresponding blocks in adjacent frames. For instance, in a racing game, the background might remain relatively stationary while the race car moves rapidly. The algorithm will identify blocks in the race car's area that have undergone significant displacement, while blocks in the background area have experienced smaller displacements. This method effectively captures local motion features in complex scenes. The result of motion estimation is a motion vector field, describing the direction and magnitude of motion in different parts of the image. In the racing game example, the motion vector field might show a small backward motion at the edge of the track, while the race car area has a larger forward motion vector. Based on the obtained motion vector field, the system uses a motion-compensated frame interpolation algorithm to insert an intermediate frame between the original two frames. For example, if the original frame rate is 30 frames per second, inserting an intermediate frame can increase the frame rate to 60 frames per second. The interpolation algorithm calculates the position and color of each pixel in the intermediate frame based on the information from the motion vector field. In racing games, this means the car's position is precisely interpolated to a point between two original frames, creating smoother motion. The final step is to weighted-fuse the interpolated intermediate frame with the two original frames. This process aims to further improve image quality and reduce potential interpolation artifacts. The weights for fusion can be determined based on the temporal distance between the intermediate frame and the original frames. For example, if the intermediate frame is exactly midway between two original frames, then all three frames can be assigned equal weights. This fusion technique enables smooth transitions and reduces screen tearing or jumpiness. The benefits of this frame rate enhancement technique are multifaceted. First, it significantly improves the smoothness of animation, reduces motion blur, and makes the outlines of fast-moving objects (such as race cars) clearer. Second, it can improve the visual quality of games or videos without increasing the production cost of the original content. Furthermore, this technique can, to some extent, compensate for insufficient hardware performance, allowing even less powerful devices to display higher-quality images.

[0101] In some embodiments, in steps S101 to S105 above, the method further includes:

[0102] Collect user experience data in different usage scenarios of intelligent handheld devices, including eye fatigue, hand comfort, and operation smoothness;

[0103] Acquire historical display data of intelligent handheld devices under different usage scenarios, and perform correlation analysis on the historical display data and the experience data to form a second training dataset;

[0104] Based on the second training dataset, a user experience evaluation model is established by using the support vector machine algorithm for modeling and training.

[0105] The user experience evaluation model is used to obtain the user experience score in any usage scenario of the smart handheld device. By comparing the experience score with a preset experience score threshold, it is determined whether to adjust the display parameter combination of the smart handheld device.

[0106] In this embodiment, historical display data of the intelligent handheld device under different usage scenarios is acquired. Parameters such as brightness, contrast, and color temperature in the historical display data are assessed to determine if they exceed preset threshold ranges. If they do, they are marked as abnormal data that may cause eye fatigue. User eye fatigue data under different usage scenarios is collected, and the marked abnormal historical display data is obtained. Correlation analysis is performed between the two to obtain the display parameter thresholds that cause eye fatigue. User hand operation data under different usage scenarios is acquired, including button size, key layout, and grip method. Comfort is assessed based on ergonomic parameters to obtain comfort values ​​under different hand operation parameters. User operation fluency data under different usage scenarios is collected, and corresponding handheld device hardware configuration parameters and software performance parameters are obtained. Through multivariate regression analysis, a relationship model between hardware configuration, software performance, and operation fluency is established. The eye fatigue threshold, hand comfort values, and operation fluency relationship model are used as training features. Combined with user subjective ratings, a support vector machine classification model is constructed to achieve a comprehensive evaluation of user experience. In new smart handheld device usage scenarios, hardware configuration, software performance, display parameters, and user operation parameters are collected in real time and input into an evaluation model to predict the user experience in that scenario. For each usage scenario, the user experience evaluation model calculates the user's experience score and compares the score with a preset experience score threshold. If the user experience score is lower than the preset threshold, it is determined that the smartphone's display parameter combination needs to be adjusted and optimized; if the user experience score is higher than or equal to the preset threshold, the current display parameter combination remains unchanged. For usage scenarios requiring adjustment, relevant display parameters such as screen brightness, color temperature, contrast ratio, and resolution are determined, forming a candidate set for parameter adjustment. Intelligent optimization algorithms, such as genetic algorithms or particle swarm optimization algorithms, search for the optimal parameter combination in the candidate parameter set, maximizing the user experience score under this combination. The optimized display parameter combination is applied to the smartphone's display settings, displaying with the new parameter combination in the corresponding usage scenario. The user experience score under the new parameter combination is continuously monitored, and the user experience evaluation model dynamically judges the optimization effect of the parameter combination. If necessary, the parameter adjustment process is triggered again to achieve closed-loop control of display optimization.

[0107] For example, firstly, user experience data is collected in different scenarios, including eye fatigue, hand comfort, and operational smoothness. For instance, playing action games for extended periods in bright environments may exacerbate eye fatigue, while watching videos in dim environments may reduce eye strain. Hand comfort may be affected by game type; strategy games may require prolonged device holding, while casual games allow for intermittent relaxation. Operational smoothness is closely related to game frame rate and touch response. Historical display data is acquired and correlated with experience data to form a training dataset. For example, a high refresh rate may improve operational smoothness in fast-paced games, but its effect may be less noticeable when watching movies; color temperature adjustment may affect eye comfort under different lighting conditions. A user experience evaluation model is built using the Support Vector Machine (SVM) algorithm. SVM can effectively handle high-dimensional feature spaces and is suitable for processing complex user experience data. During model training, it may be discovered that certain combinations of display parameters can significantly improve the user experience in specific scenarios. For example, increasing screen brightness and contrast may be more effective in strong outdoor light, while reducing blue light output may be more beneficial for protecting eyesight in low-light indoor environments. Based on a trained model, a user experience score can be predicted for any usage scenario. Assuming a preset experience score threshold of 85 points (out of 100), the system automatically adjusts display parameters when the predicted score falls below this threshold. For example, if the system detects that a user has been using the device for an extended period in a dark environment, the predicted eye fatigue score might drop to 80 points. In this case, the system might automatically reduce screen brightness, activate eye protection mode, and remind the user to take a break. This dynamic adjustment mechanism not only improves the user experience but also extends the device's lifespan. By responding to user needs in real time, the intelligent handheld device can maintain optimal performance in different scenarios, protecting user health while ensuring an enjoyable entertainment experience. This data-driven intelligent optimization method reflects the trend of modern consumer electronics products moving towards personalization and intelligence, providing users with a more considerate and intelligent user experience.

[0108] Reference Figure 2 An embodiment of the present invention provides a control system 2 for an intelligent handheld device, the system 2 specifically comprising:

[0109] The first control module 201 is used to acquire real-time power consumption data and heat generation data of the intelligent handheld device, and dynamically adjust the processor frequency and display refresh rate of the intelligent handheld device according to the real-time power consumption data and the heat generation data based on a pre-built frequency adjustment table.

[0110] The second control module 202 is used to analyze user interaction behavior data in real time through a pre-built functional pattern recognition model, obtain the functional pattern recognition result of the intelligent handheld device, and determine the optimal display parameter configuration based on the functional pattern recognition result.

[0111] The third control module 203 is used to dynamically calculate the optimal display screen brightness and optimal color parameters of the intelligent handheld device based on ambient light intensity data, user viewing distance information and user gaze area information, using an adaptive mapping algorithm.

[0112] The fourth control module 204 is used to obtain user prediction behavior data based on user grip posture data and user eye movement data, and to dynamically adjust the display performance data of the intelligent handheld device based on the user prediction behavior data;

[0113] The fifth control module 205 is used to smooth the images of the preceding and following frames by analyzing the motion vectors of the images in the preceding and following frames and using a frame interpolation algorithm when the intelligent handheld device is in a fast motion or screen switching state.

[0114] It is understandable that, such as Figure 1 The content of the control method embodiments of the intelligent handheld device shown herein is applicable to the control system embodiments of this intelligent handheld device. The specific functions implemented by the control system embodiments of this intelligent handheld device are as follows: Figure 1 The control method of the intelligent handheld device shown is the same as that of the embodiment, and the beneficial effects achieved are the same as those described above. Figure 1 The beneficial effects achieved by the control method embodiment of the intelligent handheld device shown are also the same.

[0115] It should be noted that the information interaction and execution process between the above systems are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0116] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0117] Reference Figure 3The present invention also provides a computer device 3, including: a memory 302 and a processor 301, and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, it implements the control method of the intelligent handheld device as described in any of the above methods.

[0118] The computer device 3 may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will understand that... Figure 3 The computer device 3 is merely an example and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0119] The processor 301 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0120] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Furthermore, the memory 302 may include both internal and external storage units of the computer device 3. The memory 302 is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0121] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the control method of an intelligent handheld device as described in any of the above methods.

[0122] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0123] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0124] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] In the embodiments disclosed in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. A method for controlling an intelligent handheld device, characterized in that, The method specifically includes: The system acquires real-time power consumption and heat generation data of the intelligent handheld device, and dynamically adjusts the processor frequency and display refresh rate of the intelligent handheld device based on a pre-built frequency adjustment table and the real-time power consumption and heat generation data. The user interaction behavior data is analyzed in real time by a pre-built functional pattern recognition model to obtain the functional pattern recognition result of the intelligent handheld device, and the optimal display parameter configuration is determined based on the functional pattern recognition result. Based on ambient light intensity data, user viewing distance information, and user gaze area information, an adaptive mapping algorithm is used to dynamically calculate the optimal display brightness and optimal color parameters of the intelligent handheld device. Based on user grip posture data and user eye movement data, predictive user behavior data is obtained, and the display performance data of the intelligent handheld device is dynamically adjusted based on the predictive user behavior data. When the intelligent handheld device is in a fast-moving state or when the screen is switching, the motion vectors of the preceding and following frames are analyzed, and a frame interpolation algorithm is used to smooth the preceding and following frames. The frequency adjustment table is a preset two-dimensional array containing processor frequencies and display refresh rates corresponding to different power consumption and temperature ranges. The step of obtaining user prediction behavior data based on user grip posture data and user eye movement data, and dynamically adjusting the display performance data of the intelligent handheld device based on the user prediction behavior data, specifically includes: Acquire user grip posture data and user eye movement data, as well as the corresponding user behavior results; Preprocessing and feature extraction are performed on the user's grip posture data and the user's eye movement data to obtain key behavioral features related to the user's behavioral results; The key behavioral features are input into a pre-trained user behavior recognition model to obtain user predicted behavior data, which includes user intent and user predicted usage status. Based on a preset mapping table of user behavior and display performance requirements, the display performance requirements of users for intelligent handheld devices within a preset future time period are determined according to the predicted user behavior data. Based on the display performance requirements, the display performance data of the intelligent handheld device is dynamically adjusted.

2. The method according to claim 1, characterized in that, The method of dynamically adjusting the processor frequency and display refresh rate of the smart handheld device based on the pre-built frequency adjustment table and the real-time power consumption data and heat generation data also includes: The real-time power consumption data, heat generation data, processor frequency, and display refresh rate of the intelligent handheld device are used as the state space, and the various adjustment operations of the processor frequency and display refresh rate are used as the action space, with the reduction of the real-time power consumption and heat generation of the intelligent handheld device as the reward function. Based on the state space, the action space, and the reward function, a reinforcement learning algorithm is used for modeling and training to obtain a frequency adjustment model. The frequency adjustment model is used to output a frequency adjustment table, which includes the data correlation between real-time power consumption, heat generation, processor frequency, and display refresh rate.

3. The method according to claim 1, characterized in that, The process of analyzing user interaction behavior data in real time through a pre-built functional pattern recognition model to obtain the functional pattern recognition result of the intelligent handheld device, and determining the optimal display parameter configuration based on the functional pattern recognition result, further includes: Acquire display performance data, historical application scenario data, and historical user interaction behavior data of the intelligent handheld device under different functional modes; The display performance data, historical application scenario data, and historical user interaction behavior data are correlated and analyzed to form a first training dataset; Using the first training dataset as input, a support vector machine algorithm is used for modeling and training to construct a functional pattern recognition model.

4. The method according to claim 1, characterized in that, The process of dynamically calculating the optimal display brightness and optimal color parameters of the intelligent handheld device using an adaptive mapping algorithm based on ambient light intensity data, user viewing distance information, and user gaze area information specifically includes: Ambient light intensity data and user viewing distance information are acquired. Based on a pre-built mapping table between ambient light intensity, user viewing distance and display parameters, the first display parameters of the intelligent handheld device are determined according to the ambient light intensity data and the user viewing distance information. The first display parameters include the brightness of the first display screen and the first color parameters. Based on the complexity of the different display content of the intelligent handheld device, the display screen of the intelligent handheld device is divided into several display areas; Acquire user gaze area information, and determine second display parameters for each display area based on the user gaze area information. The second display parameters include the brightness of the second display screen and second color parameters. The optimal display parameters of the intelligent handheld device are determined based on the first display parameters and the second display parameters. The optimal display parameters include the optimal screen brightness and the optimal color parameters.

5. The method according to claim 1, characterized in that, The process of smoothing the images by analyzing the motion vectors of consecutive frames and using a frame interpolation algorithm specifically includes: Acquire every two adjacent frames of the intelligent handheld device, and divide each two adjacent frames into a first frame and a second frame. A block-matching-based motion estimation algorithm is used to estimate the motion of the first frame image and the second frame image to obtain the motion vector field between the first frame image and the second frame image; Based on the motion vector field, a motion compensation frame interpolation algorithm is used to insert at least one intermediate frame image between the first frame image and the second frame image. The intermediate frame image is weighted and fused with the first frame image and the second frame image to obtain an image sequence.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Collect user experience data in different usage scenarios of intelligent handheld devices, including eye fatigue, hand comfort, and operation smoothness; Acquire historical display data of intelligent handheld devices under different usage scenarios, and perform correlation analysis on the historical display data and the experience data to form a second training dataset; Based on the second training dataset, a user experience evaluation model is established by using the support vector machine algorithm for modeling and training. The user experience evaluation model is used to obtain the user experience score in any usage scenario of the smart handheld device. By comparing the experience score with a preset experience score threshold, it is determined whether to adjust the display parameter combination of the smart handheld device.

7. A control system for an intelligent handheld device, characterized in that, The system specifically includes: The first control module is used to acquire real-time power consumption data and heat generation data of the intelligent handheld device, and dynamically adjust the processor frequency and display refresh rate of the intelligent handheld device according to the real-time power consumption data and the heat generation data based on a pre-built frequency adjustment table. The second control module is used to analyze user interaction behavior data in real time through a pre-built functional pattern recognition model, obtain the functional pattern recognition result of the intelligent handheld device, and determine the optimal display parameter configuration based on the functional pattern recognition result. The third control module is used to dynamically calculate the optimal display brightness and optimal color parameters of the intelligent handheld device based on ambient light intensity data, user viewing distance information, and user gaze area information using an adaptive mapping algorithm. The fourth control module is used to obtain user prediction behavior data based on user grip posture data and user eye movement data, and to dynamically adjust the display performance data of the intelligent handheld device based on the user prediction behavior data; The fifth control module is used to smooth the images of the preceding and following frames by analyzing the motion vectors of the images in the preceding and following frames and using a frame interpolation algorithm when the intelligent handheld device is in a fast motion or screen switching state. The frequency adjustment table is a preset two-dimensional array containing processor frequencies and display refresh rates corresponding to different power consumption and temperature ranges. The step of obtaining user prediction behavior data based on user grip posture data and user eye movement data, and dynamically adjusting the display performance data of the intelligent handheld device based on the user prediction behavior data, specifically includes: Acquire user grip posture data and user eye movement data, as well as the corresponding user behavior results; Preprocessing and feature extraction are performed on the user's grip posture data and the user's eye movement data to obtain key behavioral features related to the user's behavioral results; The key behavioral features are input into a pre-trained user behavior recognition model to obtain user predicted behavior data, which includes user intent and user predicted usage status. Based on a preset mapping table of user behavior and display performance requirements, the display performance requirements of users for intelligent handheld devices within a preset future time period are determined according to the predicted user behavior data. Based on the display performance requirements, the display performance data of the intelligent handheld device is dynamically adjusted.

8. A computer device, characterized in that, include: The memory and processor, and the computer program stored in the memory, when the computer program is executed on the processor, implement the control method of the intelligent handheld device as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the control method of the intelligent handheld device as described in any one of claims 1 to 6.

Images