Display method and system of intelligent wearable device

Abstract

The invention discloses a display method and system of an intelligent wearable device, and the method specifically comprises the steps: detecting the light intensity data and color temperature data of a use environment of the intelligent wearable device in real time, and carrying out the dynamic adjustment of a first display parameter of the intelligent wearable device according to the light intensity data and the color temperature data; acquiring historical operation information of a user on the interface elements of the intelligent wearable device, and performing personalized adjustment on the layout of the interface elements of the intelligent wearable device according to the historical operation information; according to the characteristics and importance of the display content of the intelligent wearable device, a self-adaptive display algorithm is adopted to dynamically adjust second display parameters of all display areas of the display content, and the second display parameters comprise the resolution ratio and the refresh rate. According to the invention, the matching degree of the intelligent wearable device and the visual perception of the user is obviously improved, the visual fatigue is reduced, the information transmission efficiency is optimized, and more natural and efficient visual experience is provided for the user.

Description

Technical Field

[0001] The present invention relates to the technical field of smart wearable devices, and in particular to a display method and system for smart wearable devices. Background Art

[0002] In the field of smart wearable devices, virtual reality (VR) and augmented reality (AR) devices, the way display content is presented is closely related to the user's visual experience. However, existing display methods face multiple technical challenges, which affect the overall user experience.

[0003] First, the matching degree between the displayed content and the user's line of sight is an urgent problem to be solved. When the user moves his head or eyes, if the displayed content cannot be adjusted in real time, it will cause visual incoherence and unnaturalness. Especially in fast-moving scenes, the delay or misalignment of the displayed content will significantly reduce the user's immersion and comfort. The root of this problem is that the existing display methods lack the ability to respond to environmental changes and user behavior in real time.

[0004] Secondly, the fixedness of the display area also limits the user experience. In some cases, users may need to focus on a fixed area for a long time, but the existing display area size and shape often cannot meet this demand, resulting in visual fatigue. In scenarios where a large amount of information needs to be quickly browsed, the fixed display area limits the display space of information and reduces the efficiency of information acquisition. This is mainly because the current display method fails to flexibly adjust according to the specific needs and usage scenarios of users.

[0005] In addition, changes in ambient light also have a significant impact on the display effect of VR / AR devices. In strong outdoor light or dark indoor light environments, if the brightness and contrast of the display screen cannot be adaptively adjusted, the content visibility will be reduced, the clarity will be impaired, and it may even cause damage to the user's eyesight. The root of this problem is that the existing display methods lack the ability to effectively perceive and dynamically adjust ambient light.

[0006] Finally, the personalized needs of different users are also a challenge faced by current display methods. Different users have different preferences for the color, size, shape, etc. of the display area. If it cannot be customized according to the personalized needs of users, the user satisfaction and usage experience will be reduced. This is mainly because the existing display methods lack in-depth understanding and flexible support for the personalized needs of users. Summary of the invention

[0007] The object of the present invention is to provide a display method and system for a smart wearable device, which significantly improves the matching degree between the smart wearable device and the user's visual perception, reduces visual fatigue, optimizes the efficiency of information transmission, and provides users with a more natural and efficient visual experience, so as to solve at least one of the above-mentioned prior art problems.

[0008] In a first aspect, the present invention provides a display method for a smart wearable device, the method specifically comprising:

[0009] Real-time detection of light intensity data and color temperature data of the use environment of the smart wearable device, and dynamic adjustment of first display parameters of the smart wearable device according to the light intensity data and the color temperature data, wherein the first display parameters include display brightness, display contrast, and display color;

[0010] Acquire historical operation information of the user on the interface elements of the smart wearable device, and perform personalized adjustment on the layout of the interface elements of the smart wearable device according to the historical operation information;

[0011] According to the characteristics and importance of the display content of the smart wearable device, an adaptive display algorithm is used to dynamically adjust the second display parameters of each display area of ​​the display content, where the second display parameters include resolution and refresh rate;

[0012] Determining whether to optimize the layout of the display content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface;

[0013] Obtain historical gaze information of a user when operating the smart wearable device, train an attention mechanism model according to the historical gaze information, and determine the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model.

[0014] In a second aspect, the present invention provides a display system for a smart wearable device, the system specifically comprising:

[0015] A first display module, used for real-time detection of light intensity data and color temperature data of the use environment of the smart wearable device, and dynamically adjusting first display parameters of the smart wearable device according to the light intensity data and the color temperature data, wherein the first display parameters include display brightness, display contrast and display color;

[0016] A second display module is used to obtain historical operation information of the user on the interface elements of the smart wearable device, and to personalize the layout of the interface elements of the smart wearable device according to the historical operation information;

[0017] A third display module, configured to dynamically adjust second display parameters of each display area of ​​the display content using an adaptive display algorithm according to the characteristics and importance of the display content of the smart wearable device, wherein the second display parameters include resolution and refresh rate;

[0018] A fourth display module, used to determine whether to optimize the layout of the display content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface;

[0019] The fifth display module is used to obtain historical gaze information of the user when operating the smart wearable device, train the attention mechanism model according to the historical gaze information, and determine the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model.

[0020] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor and a computer program stored in the memory, and when the computer program is executed on the processor, a display method of a smart wearable device as described in any one of the above methods is implemented.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the display method of a smart wearable device as described in any one of the above methods is implemented.

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

[0023] 1. The present invention significantly improves the matching degree between smart wearable devices and user visual perception, reduces visual fatigue, optimizes information transmission efficiency, and provides users with a more natural and efficient visual experience.

[0024] 2. The present invention can significantly improve the matching degree between the display content of the smart wearable device and the user's line of sight, enhance the flexibility of the display area of ​​the smart wearable device, improve the adaptability of the display effect of the smart wearable device, and meet the personalized needs of the user, thereby providing the user with a better quality and more comfortable visual experience.

[0025] 3. The present invention can automatically adjust the display brightness, contrast and color of the smart wearable device to adapt to different lighting conditions by real-time detection of the light intensity and color temperature of the use environment. This can not only improve the readability of the displayed content, but also reduce eye fatigue and protect the user's eyesight.

[0026] 4. By analyzing the user's historical operation information on interface elements, the present invention can learn and understand the user's personalized usage habits, thereby automatically adjusting the layout of interface elements, thereby improving the user experience and allowing the user to access required functions more conveniently.

[0027] 5. The present invention can identify the characteristics and importance of the displayed content and dynamically adjust the resolution and refresh rate of the display area based on this information, which can not only improve the clarity of the displayed content, but also ensure that important information is displayed first, thereby improving the user's information acquisition efficiency.

[0028] 6. By monitoring the user's eye fatigue and the time spent on the interactive interface, the present invention can determine whether it is necessary to optimize the layout of the display content of the current interactive interface, thereby reducing the user's visual burden and improving the user's comfort and satisfaction when using smart wearable devices.

[0029] 7. After determining that the layout of the display content of the current interactive interface needs to be optimized, the present invention can readjust the layout of the display content based on the user's historical interaction information on the interface to ensure that the display content is more in line with the user's usage habits and needs, thereby improving the user experience.

[0030] 8. By analyzing the user's historical gaze information, the present invention can train an attention mechanism model, and determine the loading priority of each display area of ​​the smart wearable device based on the model, ensuring that the information that the user is most concerned about is loaded and displayed first, thereby improving the efficiency and accuracy of information presentation.

[0031] 9. After determining the loading priority of each display area, the present invention can dynamically adjust the information loading progress of each display area according to the network status and device performance of the smart wearable device, ensuring that the information loading speed matches the user's needs and the capabilities of the device, thereby improving the overall user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 It is a flow chart of a display method of a smart wearable device provided by one embodiment of the present invention;

[0034] Figure 2 is a structural schematic diagram of a display system for a smart wearable device provided by an embodiment of the present invention;

[0035] Figure 3 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0037] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0038] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0039] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0040] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0041] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0042] In the embodiment of the present application, the execution subject of the process includes a terminal device, which includes but is not limited to: a server, a computer, a smart phone, a tablet computer, and other devices capable of executing the method disclosed in the present application. Figure 1 A flow chart of a display method for a smart wearable device disclosed in an embodiment of the present invention is shown, and the details are as follows:

[0043] S101, real-time detection of light intensity data and color temperature data of the use environment of the smart wearable device, and dynamic adjustment of first display parameters of the smart wearable device according to the light intensity data and the color temperature data, wherein the first display parameters include display brightness, display contrast and display color.

[0044] In this embodiment, the smart wearable device includes a light sensor, a color temperature sensor, a processor and a display screen. The light sensor is used to detect the light intensity data of the use environment in real time, and the color temperature sensor is used to detect the color temperature data of the use environment in real time. The processor receives data from the light sensor and the color temperature sensor, and dynamically adjusts the display brightness, display contrast and display color of the display screen according to these data. Specifically, the light sensor collects the light intensity data of the use environment regularly or in real time, and the color temperature sensor collects the color temperature data of the use environment regularly or in real time. The processor receives the data from the light sensor and the color temperature sensor, and determines the optimal display brightness, display contrast and display color of the display screen under different light intensity and color temperature conditions through machine learning or preset algorithms based on the historical light intensity data and color temperature data, and then maps the current light intensity data and color temperature data with the optimal display parameters to obtain the optimal display parameters in the current environment. The processor sends the calculated optimal display parameters to the display screen. The display screen adjusts the display brightness, display contrast and display color according to the received parameters.

[0045] In this embodiment, by real-time detection of the light intensity and color temperature of the use environment and dynamically adjusting the display parameters of the display screen, the system can ensure that the display screen can provide the best display effect in different environments. Users can obtain clear and comfortable display effects without manually adjusting the display parameters, which improves the user experience. In an environment where the light is too strong or too weak, the system can automatically adjust the display brightness to avoid damage to the user's eyes caused by the screen being too bright or too dark. By adjusting the display contrast and display color, the system can reduce screen flicker and reflection, and further protect the user's eyesight.

[0046] S102, obtaining historical operation information of the user on the interface elements of the smart wearable device, and performing personalized adjustment on the layout of the interface elements of the smart wearable device according to the historical operation information.

[0047] In this embodiment, the smart wearable device includes a data acquisition module, a data analysis module and a layout adjustment module. The data acquisition module is responsible for collecting the historical operation information of the user on the interface elements of the smart wearable device, and the data analysis module analyzes this information to understand the user's usage habits and preferences. Finally, the layout adjustment module makes personalized adjustments to the layout of the interface elements according to the analysis results. Specifically, through the data acquisition module of the smart wearable device, the user's historical operation information such as clicks, slides, and long presses on the interface elements (such as buttons, icons, text boxes, etc.) is collected, and the user's access frequency, residence time, operation sequence and other data for each interface element are recorded. The data analysis module pre-processes the collected historical operation information, such as deduplication and noise reduction, and uses data mining and machine learning technology to analyze the user's usage habits and preferences, such as which interface elements the user frequently visits and which layout method the user prefers. According to the analysis results, a probability density function of the user's personalized needs is generated to guide the layout adjustment. The layout adjustment module makes personalized adjustments to the layout of the interface elements of the smart wearable device according to the data analysis results. For example, if users frequently access a specific function, the interface elements corresponding to that function can be placed in a more prominent position; if users prefer a simple layout, unnecessary interface elements can be reduced or their arrangement can be optimized. The adjusted layout solution needs to be tested and verified to ensure that it conforms to the user's usage habits and preferences and improves the user experience.

[0048] In this embodiment, by personalizing the layout of interface elements, the interface of the smart wearable device is made more in line with the user's usage habits and preferences, thereby improving the user experience. Users can access the required functions more conveniently, reducing unnecessary operation steps and time costs. Personalized interface layout can increase users' preference and dependence on smart wearable devices, thereby enhancing user stickiness. The convenience and comfort felt by users during use will make them more willing to continue using and recommending the device.

[0049] S103: Adopting an adaptive display algorithm to dynamically adjust second display parameters of each display area of ​​the display content according to the characteristics and importance of the display content of the smart wearable device, where the second display parameters include resolution and refresh rate.

[0050] In this embodiment, the display content on the smart wearable device is first monitored in real time by sensors, including text, images, videos, etc. Then, the display content is feature extracted and evaluated for importance using technologies such as image processing and natural language processing. For example, key areas in the image (such as faces, text, etc.) can be identified and their importance to the user can be evaluated. According to the results of content monitoring and analysis, the system uses an adaptive display algorithm to dynamically adjust the resolution and refresh rate of each display area. The core of the algorithm is to allocate appropriate display resources to it according to the characteristics and importance of the display content. For example, for important display content (such as emergency notifications, key information prompts, etc.), its resolution and refresh rate can be increased to ensure that the user can see clearly and respond quickly; while for secondary display content (such as background images, non-critical information, etc.), its resolution and refresh rate can be reduced to save energy and extend the battery life of the device. When adjusting the resolution and refresh rate, the hardware limitations and energy management strategies of the device will also be considered to ensure that the adjusted parameters meet user needs without affecting the performance and battery life of the device. In addition, the adaptive display algorithm will be continuously optimized based on user feedback and usage habits to improve its accuracy and adaptability.

[0051] In this embodiment, through the adaptive display algorithm, the system can dynamically adjust the resolution and refresh rate of each display area according to the characteristics and importance of the displayed content, thereby improving the display effect, and users can get a clearer and smoother visual experience in different usage scenarios. By reducing the resolution and refresh rate of the secondary display content, the system can save energy and extend the battery life of the smart wearable device, which is especially important for smart wearable devices that need to be worn and used for a long time.

[0052] S104: Determine whether to perform layout optimization on display content of the current interactive interface according to the user's eye fatigue and the dwell time on the current interactive interface.

[0053] In this embodiment, the smart wearable device includes an eye tracking sensor, a user behavior analysis module, and a layout optimization module. The eye tracking sensor is used to monitor the user's eye movement trajectory, blinking frequency and other parameters in real time, so as to evaluate the user's eye fatigue. When the eye fatigue reaches a preset threshold, it is considered that the user may be in an eye fatigue state. Through the user behavior analysis module, the user's residence time on the current interactive interface is recorded. If the user's residence time on a certain interface exceeds the preset time threshold and no obvious interactive operation (such as clicking, sliding, etc.) is performed, the system believes that the user may be confused or dissatisfied with the layout or content of the interface. When it is detected that the user's eye fatigue is high or the residence time on the current interactive interface is too long, the built-in algorithm of the layout optimization module is triggered. The layout optimization module generates multiple possible layout optimization schemes based on factors such as the display content of the current interface, the user's usage habits, and the device hardware limitations. By comparing the expected effects of different schemes (such as user satisfaction, operation efficiency, etc.), the optimal layout optimization scheme is selected for implementation.

[0054] In this embodiment, by real-time monitoring of the user's eye fatigue and dwell time, the user's dissatisfaction and confusion with the current interactive interface can be discovered in time, and the layout can be automatically optimized, thereby improving the user experience. The interface after layout optimization is more in line with the user's visual habits and operation requirements, which helps to reduce the user's eye fatigue and visual burden.

[0055] S105, obtaining historical gaze information of the user when operating the smart wearable device, training an attention mechanism model according to the historical gaze information, and determining the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model.

[0056] In this embodiment, the eye tracking sensor built into the smart wearable device is used to record key information such as the user's gaze point position and gaze duration when operating the device in real time, and this information is summarized into a historical gaze information database to provide data support for subsequent analysis and model training. According to the characteristics of historical gaze information, a deep learning model based on the attention mechanism is designed. The model can receive the user's historical gaze information as input and output the loading priority of each display area. The input layer of the model includes features such as the position of the user's gaze point and the gaze duration, and the output layer is the loading priority score of the corresponding display area. The attention mechanism model is trained using data from the historical gaze information database. By adjusting the parameters and structure of the model, it can accurately predict the user's attention level to each display area in different situations. During the training process, the model is evaluated by cross-validation and other methods to ensure its generalization ability and accuracy. When the user uses the smart wearable device again, the loading priority of each display area will be calculated in real time through the trained attention mechanism model according to the current operation scenario and the user's historical gaze information. According to the calculated priority, the loading order and display content of each display area are intelligently adjusted to optimize the user's visual experience and device performance. Finally, we continuously collect user feedback data and new historical gaze information to continuously optimize and update the attention mechanism model. In this way, smart wearable devices can continuously adapt to user usage habits and demand changes, and provide more personalized loading priority optimization solutions.

[0057] In this embodiment, by intelligently determining the loading priority of each display area, it is possible to ensure that the information that the user is most concerned about is presented to the user first, thereby improving the user's visual experience and satisfaction. Intelligent adjustment of loading priority helps to reduce the resource consumption and response time of the device and improve the overall performance and operating efficiency of the device. The loading priority determination strategy can be continuously optimized and adjusted based on the user's historical gaze information and feedback data to achieve a more personalized user experience.

[0058] In some embodiments, in the above step S101, dynamically adjusting the first display parameter of the smart wearable device according to the light intensity data and the color temperature data specifically includes:

[0059] Acquire historical light intensity data and historical color temperature data, and determine optimal display brightness, display contrast, and optimal display color of the smart wearable device under different light intensity conditions and different color temperature conditions according to the historical light intensity data and the historical color temperature data to form a first training data set;

[0060] Taking the first training data set as input, using a support vector machine algorithm to perform modeling training to form a first display parameter mapping model;

[0061] The light intensity data and the color temperature data are input into the first display parameter mapping model for matching to obtain a matching result, and the first display parameter of the smart wearable device is dynamically adjusted according to the matching result.

[0062] In this embodiment, the ambient light intensity data and color temperature data of the smart wearable device over a period of time are obtained and stored as historical data. According to the user's display parameter adjustment under different light intensity and color temperature conditions in the historical data, the optimal display brightness, display contrast and display color parameters under various conditions are determined to generate a training data set. The training data set is input into the support vector machine algorithm for modeling training to obtain a display parameter mapping model, which can match the optimal display parameter combination according to the input light intensity and color temperature data. The light intensity data and color temperature data of the current environment are collected in real time by the sensor on the smart wearable device, and are input into the trained display parameter mapping model. The display brightness, display contrast and display color parameters that best match the current light intensity and color temperature are obtained from the output results of the display parameter mapping model. The optimal display parameters obtained in the previous step are applied to the screen display settings of the smart wearable device to dynamically adjust its display brightness, contrast and color. Monitor the changes in ambient light intensity and color temperature. Once the changes exceed a certain threshold, repeat the above steps to dynamically optimize the screen display effect of the smart wearable device in real time to adapt to different ambient lighting conditions.

[0063] Exemplarily, first obtain historical light intensity and color temperature data, which can come from the built-in light sensor of the smart wearable device. For example, in outdoor sunlight, the light intensity may reach 100,000 lux and the color temperature is about 5500K; while under indoor fluorescent lights, the light intensity may be 500 lux and the color temperature is about 4000K. By collecting this data over a long period of time, a comprehensive ambient light database can be established. Next, determine the optimal display parameters under different conditions based on these historical data. For example, in a strong light environment, it may be necessary to increase the display brightness to 400 nits, adjust the contrast to 1000:1, and increase the blue light component to improve readability; in a dark light environment, it may be necessary to reduce the brightness to 50 nits, reduce the contrast to 700:1, and reduce the blue light component to protect the eyes. These optimal parameters can be determined through user feedback and professional testing. These data are organized into a training data set, which contains input (light intensity and color temperature) and output (optimal display parameters). For example, a set of data may be: input (10,000 lux, 6,000K), output (300 nits, 900:1, color temperature 6,500K). By collecting a large number of such data pairs, a comprehensive training set can be formed. Then, the support vector machine (SVM) algorithm is used for modeling training. SVM is suitable for dealing with such multi-dimensional input and multi-dimensional output problems, and can effectively learn the nonlinear relationship between input and output. By adjusting the kernel function (such as RBF kernel) and other hyperparameters, an accurate mapping model can be obtained. This model can predict the optimal display parameters based on the input light conditions. Finally, the light data obtained in real time is input into the trained model. For example, when the user walks outdoors, the light sensor detects that the light intensity suddenly increases to 80,000 lux and the color temperature changes to 5,800K. The model may output recommendations to adjust the brightness to 350 nits, the contrast to 950:1, and the display color temperature to 6,300K. The device can automatically adjust the display parameters based on these suggestions to provide the user with the best visual experience. The advantage of this dynamic adjustment method is that it can adapt to various complex lighting environments. For example, outdoors on a cloudy day, although the light intensity is not high, the color temperature is high, and a special combination of display parameters may be required at this time. For another example, at sunset, the light intensity gradually decreases and the color temperature is also changing. The model can adjust the display parameters in real time to keep the display effect at its best. In addition, this method can also be customized. By recording the user's manual adjustment behavior, the model can be continuously optimized to make it more in line with personal preferences. For example, if the user often slightly reduces the brightness based on the model's recommendations, the system can learn this preference and appropriately reduce the brightness recommendations in future predictions. For smart glasses, the user's line of sight direction can also be considered as an additional input parameter, because different line of sight directions may face different light environments.In general, this dynamic display parameter adjustment method based on machine learning can provide users with the best visual experience in various complex and changing light environments, improving the comfort and practicality of smart wearable devices. With the continuous accumulation of data and continuous optimization of algorithms, the effect of this method will become better and better, bringing users a smarter and more humane experience.

[0064] In some embodiments, in the above step S102, the personalized adjustment of the interface element layout of the smart wearable device according to the historical operation information specifically includes:

[0065] Extracting a user's usage habit value from the historical operation information, and verifying whether the usage habit value conforms to a Gaussian distribution, the usage habit value including an area size, an area shape, and an area position of an interface element;

[0066] If the usage habit value conforms to the Gaussian distribution, the distribution law of the interface elements is determined according to the usage habit value, and a probability density function f(x, y, z) is generated to characterize the user's personalized needs, where x represents the size of the area, y represents the shape of the area, and z represents the position of the area;

[0067] Using the probability density function f(x, y, z) to generate a second training data set, and using the second training data set to train a decision tree model to form a user habit model;

[0068] Based on the user habit model, the layout of the interface elements of the smart wearable device is personalized and adjusted in real time.

[0069] In this embodiment, the historical operation information of the user in the application is obtained, and the usage habit values ​​such as the area size, area shape and area position of the interface elements are extracted. The extracted usage habit values ​​are statistically analyzed to determine whether they conform to the Gaussian distribution. If the usage habit values ​​conform to the Gaussian distribution, the distribution law of the interface elements in the area size, shape and position is determined according to parameters such as the mean and variance. The parameters of the probability density function f(x, y, z) that characterizes the personalized needs of the user are obtained by using the maximum likelihood estimation method. When generating a new interface layout, the area size, shape and position of the interface elements that conform to the user's usage habits are obtained by sampling the probability density function f(x, y, z). The sampled area size, shape and position of the interface elements are used as constraints, combined with other layout rules, to generate a personalized interface layout plan. The generated personalized interface layout is displayed in the actual application, and the user's operation feedback data is continuously collected to optimize and update the parameters of the probability density function, so as to achieve continuous personalized adaptation of the interface layout.

[0070] The Monte Carlo method is used to generate a second training data set based on the probability density function f(x, y, z). The second training data set contains a large number of interface element layout samples that conform to the user's usage habits. The second training data set is input into the decision tree model for training. By adjusting the parameters of the decision tree model, the decision tree model can accurately predict the user's preferred interface element layout, thereby forming a user habit model. The current interface element layout of the smart wearable device is obtained, and the current layout is input into the user habit model for prediction to obtain the user's preferred interface element layout. The predicted user preference layout is applied to the actual interface of the smart wearable device, and the interface element layout is personalized in real time to meet the user's personalized needs.

[0071] Exemplarily, firstly, the user usage habit values, including the area size, shape and position of the interface elements, are extracted from the historical operation information. To verify whether these values ​​conform to the Gaussian distribution, statistical methods such as the Shapiro-Wilk test can be used. If they conform to the Gaussian distribution, the distribution law of the interface elements can be determined. For example, it is found that users prefer to operate a circular button with a size of 200 pixels in the central area of ​​the screen. Based on these laws, a probability density function f(x, y, z) is generated, where x represents the area size, y represents the area shape, and z represents the area position. This function can quantify the user's preference for the layout of different interface elements. The second training data set is generated using the probability density function, and a large number of interface layout samples that conform to user habits can be simulated. For example, 1,000 different interface layout schemes are generated, each of which contains a combination of elements of different sizes, shapes and positions. These data are used to train a decision tree model to form a user habit model. The decision tree model can learn complex rules of user preferences, such as "if the button is located in the lower right corner and is circular, the size should be between 150 and 250 pixels." Based on the trained user habit model, the layout of interface elements of the smart wearable device can be adjusted in real time. When a user opens a new app, the model predicts the interface layout that best suits the user. For example, placing commonly used function buttons in a position that is easy for the user to reach, adjusting the font size to suit the user's vision, or adjusting the menu structure according to the user's operating habits. The advantage of this personalized adjustment method is that it can adapt to the dynamic changes in user habits. As users use the device more time, their operating habits may change. By continuously collecting new operating data and updating the model, the system can continuously optimize the interface layout and always maintain the best user experience. For example, if it is found that the user begins to use a certain function more frequently, the system will automatically adjust the entrance of the function to a more prominent position. In addition, this method can also dynamically adjust the interface according to different scenarios. For example, when it is detected that the user is moving, the button size can be increased and the interface can be simplified to facilitate the user's operation during movement. When the user is stationary, more detailed information can be displayed. This intelligent interface adjustment not only improves the user's operating efficiency, but also reduces the probability of misoperation, thereby significantly improving the user experience. In general, this intelligent interface adjustment method based on user habits realizes the personalization and dynamic optimization of the interface of smart wearable devices through data-driven and machine learning technologies, providing users with a more intuitive and convenient operating experience.

[0072] In some embodiments, in the above step S103, dynamically adjusting the second display parameters of each display area of ​​the display content using an adaptive display algorithm according to the characteristics and importance of the display content of the smart wearable device specifically includes:

[0073] Acquire texture feature information of display content of the smart wearable device, and perform data clustering processing on the texture feature information using a K-means clustering algorithm to obtain feature clustering data;

[0074] Comparing the feature clustering data with a preset information category mapping table to determine a business classification probability distribution vector corresponding to all features of the display content;

[0075] Inputting the business classification probability distribution vector into a pre-built logistic regression model, and calculating the importance value of each display area of ​​the display content through a sigmoid function;

[0076] Based on the importance value, second display parameters of each display area are dynamically calculated, where the second display parameters include resolution and refresh rate.

[0077] In this embodiment, the image information of the content currently displayed by the smart wearable device is obtained, and the texture features of the image information are extracted to obtain the texture feature information. The K-means clustering algorithm is used to perform clustering processing on the texture feature information to obtain multiple cluster centers reflecting different texture features, and obtain feature clustering data. A preset information category mapping table is obtained, and the mapping table records the correspondence between various texture features and business information categories. Each cluster center in the feature clustering data is compared with the information category mapping table to determine the business information category corresponding to each cluster center. According to the business information category corresponding to each cluster center and the number of samples contained in each cluster center, the probability of each business classification of the displayed content is calculated to generate a business classification probability distribution vector. The probability distribution vector is input into the pre-built logistic regression model, and the importance value of each display area of ​​the display content is calculated through the sigmoid function; the importance of each display area is judged according to the importance value, and if the importance value is greater than the preset threshold, the area is marked as an important area; different display strategies are adopted for different important areas, and the resolution and refresh rate of important areas are improved; the second display parameters of each display area, including resolution and refresh rate, are determined by dynamic calculation; the calculated second display parameters are applied to the content display of each display area, and the content of important areas is displayed emphatically; during the display process, the changes in the importance values ​​of each area are continuously monitored, and the display parameters are dynamically adjusted according to the changes to ensure real-time optimization of the display effect.

[0078] Exemplarily, first, the system needs to deeply understand the nature of the displayed content, which requires extracting the texture feature information of the displayed content. Texture feature information refers to the characteristics of the color, brightness, spatial distribution, etc. of pixels in the image or displayed content, which can reflect the details and structure of the image. For example, the texture features of a face image may include the texture of the skin, the shape of the eyes, the outline of the mouth, etc. Next, in order to effectively process these texture feature information, the system uses the K-means clustering algorithm. This is a commonly used unsupervised machine learning algorithm that can automatically divide data into several categories. In the K-means algorithm, first, K data points need to be randomly selected as the initial clustering centers, and then the distance from each data point to these centers is calculated, and the data points are assigned to the category where the nearest center is located. Then, the center point of each category is recalculated, and the above assignment process is repeated until the category no longer changes or the preset number of iterations is reached. For example, when processing multiple application icons displayed by a smart wearable device, the K-means algorithm can classify similar icons into one category based on the texture features such as the color and shape of the icons, such as clustering all social application icons into one category and clustering all health application icons into another category. After obtaining the feature clustering data, the system compares it with the preset information category mapping table. This mapping table defines the correspondence between different texture features and business categories. For example, delicate textures and bright colors may correspond to the "game" category, while simple lines and a single tone may correspond to the "tool" category. By comparison, the business classification probability distribution vector corresponding to all features of the display content can be determined. For example, after texture feature extraction and clustering of a certain display content, it is found that 70% of its features match the "health monitoring" category, 20% of its features match the "message notification" category, and 10% of its features match the "entertainment" category. The corresponding business classification probability distribution vector is (0.7, 0.2, 0.1). In order to further quantify the importance of different areas in the display content, the system inputs the business classification probability distribution vector into a pre-built logistic regression model. The logistic regression model is a generalized linear model that is often used for binary classification problems, but can also be extended to multi-classification scenarios. It maps the output of the linear function to between 0 and 1 through the sigmoid function, indicating the probability of belonging to a certain category. Here, the logistic regression model is trained to predict the importance values ​​of each area of ​​the display content based on the business classification probability distribution vector. For example, the model may predict that the importance value of the area where the health monitoring data is located is 0.8, the importance value of the message notification area is 0.6, and the importance value of the entertainment content area is 0.3. Finally, based on these importance values, the system dynamically calculates the second display parameters of each display area, including resolution and refresh rate.For example, for health monitoring areas with higher importance values, their resolution can be improved to make data such as heart rate and blood oxygen clearer; at the same time, in order to ensure the real-time nature of the data, the refresh rate of the area can be increased. For entertainment content areas with lower importance values, the resolution and refresh rate can be appropriately reduced to save power. For example, when a user is viewing stock information, the importance value of the stock chart area may be very high, so the system will give priority to ensuring the resolution and refresh rate of this area, while other areas, such as the time display area, may have relatively low importance values, so their display parameters can be appropriately reduced. This method of dynamically adjusting display parameters has significant advantages. First, it can intelligently allocate display resources according to the user's current focus, and improve the readability and real-time nature of key information. Second, by reducing the display parameters of non-important areas, the power consumption of the device can be effectively reduced and the battery life can be extended. For example, when a user is doing outdoor sports for a long time, the device can continue to display sports data at high resolution and high refresh rate, while when the user is resting, the overall display parameters can be reduced to save power. This intelligent display content optimization method, through data-driven and machine learning technology, realizes the personalization and dynamic adjustment of the display effects of smart wearable devices, providing users with a clearer, smoother and more energy-efficient visual experience.

[0079] In some embodiments, in the above step S104, determining whether to optimize the layout of the display content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface specifically includes:

[0080] Collecting pupil image information of the user, and processing the pupil image information using a Hough circle transform algorithm to obtain a pupil diameter sequence;

[0081] Based on the pupil diameter sequence, calculating the average pupil diameter of the user's pupil diameters in each preset time period;

[0082] Determine a pupil diameter change rate according to a difference between average pupil diameters in two adjacent preset time periods in the pupil diameter sequence, and determine the user's eye fatigue degree through the pupil diameter change rate;

[0083] The dwell time of the user on the current interactive interface of the smart wearable device is obtained, and it is determined whether to perform layout optimization on the display content of the current interactive interface according to the eye fatigue and the dwell time.

[0084] In this embodiment, the pupil image information of the user is obtained, and the pupil image information is processed by the Hough circle transform algorithm to obtain pupil diameter sequence data. According to the pupil diameter sequence data, a subset of pupil diameter data in each preset time period is determined. For each subset of pupil diameter data, the average pupil diameter is calculated to obtain the average pupil diameter data in the preset time period. According to the difference between the average pupil diameters in two adjacent preset time periods, the pupil diameter change rate is determined. The pupil diameter change rate is compared with the preset eye fatigue threshold. If the change rate is greater than the threshold, it is determined that the user's eyes are in a fatigue state, otherwise it is determined that the user's eyes are in a non-fatigue state. The user's residence time on the current interactive interface of the smart wearable device is obtained, and the residence time is compared with the preset time threshold. If the residence time is greater than the time threshold and the user's eyes are in a fatigue state, it is determined that the layout optimization of the display content of the current interactive interface needs to be performed, otherwise it is determined that the layout optimization does not need to be performed. If layout optimization is required, the layout of the display content of the current interactive interface is adjusted according to the pre-established layout optimization rules to obtain an optimized interface layout. Apply the optimized interface layout to the current interactive interface of the smart wearable device and update the displayed content to relieve the user's eye fatigue.

[0085] Furthermore, the embodiment also includes: determining whether the average pupil diameter data is greater than a preset pupil diameter threshold, and if so, determining that the user is in an excited state within the preset time period, otherwise determining that the user is in a calm state. Obtaining user state data within a historical preset time period, training the user state data using a support vector machine algorithm, and obtaining a user state prediction model. Using the user state prediction model, predict the state of the user within the next preset time period, and output and display the predicted user state result. Based on the predicted user state result, a reinforcement learning algorithm is used to optimize and update the user state prediction model to improve the accuracy of subsequent user state predictions.

[0086] For example, changes in pupil diameter can reflect the physiological and psychological state of the human body, and therefore become an important indicator for assessing fatigue. First, the device collects the user's pupil image. This can be achieved through a built-in micro camera, such as the camera on smart glasses. The frequency of acquisition can be set to multiple times per second to capture subtle changes in pupil size. Next, the system processes the pupil image using the Hough circle transform algorithm. The Hough circle transform is an image processing technique for detecting circular objects. In pupil detection, it can effectively identify the boundaries of the pupil and calculate the diameter of the pupil. For example, if the image resolution is 640x480 pixels, the algorithm may identify a circle with a radius of 20 pixels, corresponding to an actual pupil diameter of about 4 mm. The system calculates the average pupil diameter within a preset time period (such as every 5 minutes). Suppose that in a certain 5-minute period, the system collects 300 pupil diameter data with an average value of 3.8 mm. In the next 5 minutes, the average diameter becomes 3.5 mm. The system calculates the rate of change of pupil diameter between these two time periods, which is a key indicator for judging eye fatigue. Generally speaking, as the degree of fatigue increases, the pupil will gradually shrink and the rate of change will be negative. For example, if the rate of change for three consecutive time periods is -5%, -8% and -10% respectively, the system may determine that the user is in a state of moderate fatigue. In addition to pupil data, the system also records the time the user stays on the current interactive interface. For example, if the user stays on the reading interface for 30 minutes and the pupil data shows moderate fatigue, the system may decide to optimize the layout of the interface. This optimization may include increasing the font, adjusting the contrast, or inserting a break reminder. This interface optimization method based on physiological data has significant advantages. It can respond to the user's physical state in real time and provide a personalized user experience. For example, when user fatigue is detected, the system can automatically adjust the display brightness or simplify complex infographics to reduce visual burden. In addition, this method can also help prevent health problems caused by excessive eye use, such as dry eyes and decreased vision. In actual applications, the system may combine multiple data to improve accuracy. For example, in addition to pupil diameter, indicators such as blinking frequency and gaze point distribution can also be monitored. Through these comprehensive data, the system can more accurately assess the user's fatigue state, thereby providing a smarter and more humane interface optimization solution.

[0087] Further, the determining whether to optimize the layout of the display content of the current interactive interface according to the eye fatigue degree and the dwell time further includes:

[0088] If it is determined to optimize the layout of the display content of the current interactive interface, determining the priority parameters of each display area of ​​the display content of the current interactive interface according to the historical interaction information of the user on the current interactive interface;

[0089] According to the priority parameter, the layout of the displayed content of the current interactive interface is readjusted.

[0090] In this embodiment, the historical interaction information of the user in the current interactive interface is obtained, including data such as clicks, browsing, and dwell time. The user's historical interaction data is analyzed to explore the user's interactive behavior patterns and preference habits. According to the results of the interaction data analysis, the priority parameters of each display area of ​​the current interactive interface are determined. The priority parameters are combined with the preset interface design rules, and the dynamic layout algorithm is used to adjust the layout of the display content of the current interactive interface. During the layout adjustment process, the display area with high priority is placed in a prominent position on the interface to increase its exposure. At the same time, according to the user's interaction preferences, the content in the display area is personalized and recommended. Finally, an optimized interactive interface layout plan is generated, and the user behavior is continuously tracked during the user's subsequent interaction process, and the interface layout is dynamically adjusted in real time to adapt to the user's changing interaction needs.

[0091] Exemplarily, first, the system analyzes the historical interaction information of the user in the current interactive interface, which may include the user's click heat map, dwell time distribution, sliding trajectory, etc. For example, on the main interface of a health monitoring application, the system may find that the user often pays attention to the heart rate data area, but rarely views the sleep quality report. Based on these historical data, the system assigns priority parameters to each display area of ​​the interface. The priority parameter can be a value between 0 and 1, and the higher the value, the more important the area is. For example, the heart rate data area may be assigned a priority of 0.9, while the sleep quality report area may only have a priority of 0.3. After determining the priority parameters, the system will readjust the interface layout according to these parameters. High-priority areas may be enlarged or moved to a more prominent position, while low-priority areas may be reduced or moved to a secondary position. For example, the heart rate data area may be enlarged and moved to the top of the screen, while the sleep quality report may be reduced and moved to the bottom. This dynamic adjustment is not limited to the size and position of the area, but may also involve the presentation of the content. For high-priority information, the system may use more eye-catching colors, larger fonts, or add animation effects to attract user attention. For example, heart rate data may be presented as a beating heart icon instead of a static number. In addition, the system may also adjust the arrangement of function buttons based on the user's usage habits. If it is found that the user frequently uses a certain function, the corresponding button may be moved to a more accessible position. For example, if the user often uses the sports mode, the shortcut button of the function may be moved to the quick access bar at the bottom of the interface. This priority-based layout optimization method has many advantages. First, it can improve the user's operation efficiency and allow users to find the required information faster. Second, it can reduce the user's visual burden, especially on small-screen devices, by highlighting important information to reduce the risk of information overload. Finally, this method can adapt to changes in user needs and dynamically adjust as the user's usage habits change, providing a continuously optimized user experience. In actual applications, the system may combine multiple factors to determine the priority parameters. In addition to historical interaction information, contextual information such as time and location may also be considered. For example, when waking up in the morning, the priority of the sleep quality report may be temporarily increased. For example, when the user is in the gym, the priority of sports-related functions may be automatically increased. Through this intelligent interface optimization method, smart wearable devices can provide each user with a customized user experience, which not only improves the practicality of the device, but also enhances user stickiness and satisfaction.

[0092] In some embodiments, in the above step S105, the training of the attention mechanism model according to the historical gaze information and the determination of the loading priority of each display area of ​​the smart wearable device by the trained attention mechanism model specifically include:

[0093] Preprocessing the historical gaze information to extract gaze feature data;

[0094] Based on the gaze feature data, a recurrent neural network is used to train the attention mechanism model to obtain a display area loading priority allocation model;

[0095] Based on the display area loading priority allocation model, the attention weight of each display area of ​​the smart wearable device is calculated, and the loading priority of each display area is sorted according to the attention weight to form a loading priority list;

[0096] Based on the loading priority list, the information loading progress of each display area is dynamically adjusted according to the network status and device performance of the smart wearable device.

[0097] In this embodiment, the user's historical gaze information is obtained, and the historical gaze information is denoised and normalized to obtain the preprocessed gaze information. Gaze features are extracted from the preprocessed gaze information, including gaze point coordinates, gaze duration, gaze trajectory, etc., to construct gaze feature data. According to the constructed gaze feature data, the attention mechanism model is trained using a long short-term memory network to obtain a preliminary attention model. For the preliminary attention model obtained through training, the gaze heat weight is introduced, the gaze feature data is weighted, and the weight parameters of the attention model are updated. Based on the updated attention model, combined with the layout information of the display area, the loading priority probability distribution of each display area is calculated by the softmax function. According to the calculated loading priority probability distribution, a display area loading priority allocation model is constructed to realize the priority sorting of the display areas.

[0098] The layout information and content information of multiple display areas of the smart wearable device are obtained, and the feature vectors of each display area are extracted according to the display area loading priority allocation model. According to the feature vectors of each display area, the attention weight of each display area is calculated by using the attention mechanism to obtain the weight distribution reflecting the importance of the display area. The loading priority of each display area is sorted according to the attention weight, and a display area loading priority list is generated, and the display area with high priority is loaded first. The current network status parameters and device performance parameters of the smart wearable device are obtained to determine whether the current network status and device performance meet the loading requirements of the display area content. If the network status and device performance meet the requirements, the information content of each display area is loaded in parallel according to the order of the display areas in the loading priority list. If the network status and device performance do not meet the requirements, the loading progress of each display area is adjusted according to the loading priority list, and the loading quality of the high-priority display area is prioritized. Dynamically track the changes in the network status and device performance of the smart wearable device, and adjust the information loading progress of the display area in real time according to the changes to ensure the smoothness and timeliness of information loading.

[0099] Exemplarily, in the interface optimization process of smart wearable devices, the historical gaze information is first preprocessed. This step involves cleaning the original data, removing outliers, and extracting meaningful features. For example, the user's gaze duration and gaze frequency on each interface element can be calculated. These processed data constitute the gaze feature data, which provides a basis for subsequent model training. Based on the gaze feature data, a recurrent neural network (RNN) is used to train the attention mechanism model. RNN is chosen because it can effectively process sequence data and capture the time dependency of user gaze behavior. In this process, variants such as long short-term memory network (LSTM) or gated recurrent unit (GRU) can be used to better handle long-term dependencies. During the training process, the model learns to map the gaze sequence to the importance weights of each display area, thereby forming a display area loading priority allocation model. Using the trained model, attention weights can be calculated for each display area of ​​the smart wearable device. For example, in a health monitoring application, the heart rate monitoring area may obtain a weight of 0.8, while the weather information area may only have a weight of 0.3. These weights reflect the user's attention to different information and provide a quantitative basis for interface optimization. According to the calculated attention weight, the system sorts the loading priorities of the display areas to form a loading priority list. This list determines which information should be loaded and displayed first when resources are limited. For example, high-priority heart rate data may be placed at the top of the list to ensure the fastest loading and updating. Finally, the system dynamically adjusts the information loading progress of each display area based on the loading priority list and the current network status and performance of the device. This dynamic adjustment mechanism can prioritize the timely update of important information when network conditions are poor. For example, when network bandwidth is limited, the system may reduce the refresh frequency of low-priority areas or reduce their display quality to ensure smooth loading of high-priority areas. This dynamic loading strategy based on the attention mechanism not only improves the user experience, but also optimizes the efficiency of device resource use. By prioritizing the loading of information that users care about most, unnecessary data transmission and processing are reduced, thereby extending battery life and improving the overall performance of the device. At the same time, the adaptability of this method enables the device to continuously adjust according to changes in user habits and provide a continuously optimized personalized experience.

[0100] Reference Figure 2 An embodiment of the present invention provides a display system 2 for a smart wearable device, and the system 2 specifically includes:

[0101] The first display module 201 is used to detect the light intensity data and color temperature data of the use environment of the smart wearable device in real time, and dynamically adjust the first display parameter of the smart wearable device according to the light intensity data and the color temperature data, wherein the first display parameter includes display brightness, display contrast and display color;

[0102] The second display module 202 is used to obtain historical operation information of the user on the interface elements of the smart wearable device, and to personalize the layout of the interface elements of the smart wearable device according to the historical operation information;

[0103] The third display module 203 is used to dynamically adjust the second display parameters of each display area of ​​the display content by using an adaptive display algorithm according to the characteristics and importance of the display content of the smart wearable device, where the second display parameters include resolution and refresh rate;

[0104] The fourth display module 204 is used to determine whether to optimize the layout of the display content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface;

[0105] The fifth display module 205 is used to obtain historical gaze information of the user when operating the smart wearable device, train the attention mechanism model according to the historical gaze information, and determine the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model.

[0106] It is understandable that if Figure 1 The contents of the display method embodiment of the smart wearable device shown in the figure are applicable to the display system embodiment of the smart wearable device. The functions specifically implemented by the display system embodiment of the smart wearable device are similar to those of the embodiment shown in the figure. Figure 1 The display method embodiment of the smart wearable device shown in the figure is the same as that of the embodiment of the smart wearable device shown in the figure, and the beneficial effects achieved are the same as those of the embodiment of the smart wearable device shown in the figure. Figure 1 The beneficial effects achieved by the display method embodiment of the smart wearable device shown are also the same.

[0107] It should be noted that the information interaction, execution process and other contents between the above-mentioned systems are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0108] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by 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 embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0109] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: 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, a display method of a smart wearable device as described in any one of the above methods is implemented.

[0110] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0111] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) 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, etc.

[0112] 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 also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0113] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the display method of the smart wearable device as described in any one of the above methods is implemented.

[0114] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0115] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0117] In the embodiments disclosed in the present 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 only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A display method for a smart wearable device, characterized in that: The method specifically comprises: Real-time detection of light intensity data and color temperature data of the use environment of the smart wearable device, and dynamic adjustment of first display parameters of the smart wearable device according to the light intensity data and the color temperature data, wherein the first display parameters include display brightness, display contrast, and display color; Acquire historical operation information of the user on the interface elements of the smart wearable device, and perform personalized adjustment on the layout of the interface elements of the smart wearable device according to the historical operation information; According to the characteristics and importance of the display content of the smart wearable device, an adaptive display algorithm is used to dynamically adjust the second display parameters of each display area of ​​the display content, where the second display parameters include resolution and refresh rate; Determining whether to optimize the layout of the display content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface; Obtain historical gaze information of a user when operating the smart wearable device, train an attention mechanism model according to the historical gaze information, and determine the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model.

2. The method according to claim 1, characterized in that The dynamically adjusting the first display parameter of the smart wearable device according to the light intensity data and the color temperature data specifically includes: Acquire historical light intensity data and historical color temperature data, and determine optimal display brightness, display contrast, and optimal display color of the smart wearable device under different light intensity conditions and different color temperature conditions according to the historical light intensity data and the historical color temperature data to form a first training data set; Taking the first training data set as input, using a support vector machine algorithm to perform modeling training to form a first display parameter mapping model; The light intensity data and the color temperature data are input into the first display parameter mapping model for matching to obtain a matching result, and the first display parameter of the smart wearable device is dynamically adjusted according to the matching result.

3. The method according to claim 1, characterized in that The personalized adjustment of the layout of the interface elements of the smart wearable device according to the historical operation information specifically includes: Extracting a user's usage habit value from the historical operation information, and verifying whether the usage habit value conforms to a Gaussian distribution, the usage habit value including an area size, an area shape, and an area position of an interface element; If the usage habit value conforms to the Gaussian distribution, the distribution law of the interface elements is determined according to the usage habit value, and a probability density function f(x, y, z) is generated to characterize the user's personalized needs, where x represents the size of the area, y represents the shape of the area, and z represents the position of the area; Using the probability density function f(x, y, z) to generate a second training data set, and using the second training data set to train a decision tree model to form a user habit model; Based on the user habit model, the layout of the interface elements of the smart wearable device is personalized and adjusted in real time.

4. The method according to claim 1, characterized in that: The method of dynamically adjusting the second display parameters of each display area of ​​the display content by using an adaptive display algorithm according to the characteristics and importance of the display content of the smart wearable device specifically includes: Acquire texture feature information of display content of the smart wearable device, and perform data clustering processing on the texture feature information using a K-means clustering algorithm to obtain feature clustering data; Comparing the feature clustering data with a preset information category mapping table to determine a business classification probability distribution vector corresponding to all features of the display content; Inputting the business classification probability distribution vector into a pre-built logistic regression model, and calculating the importance value of each display area of ​​the display content through a sigmoid function; Based on the importance value, second display parameters of each display area are dynamically calculated, where the second display parameters include resolution and refresh rate.

5. The method according to claim 1, characterized in that: The determining whether to optimize the layout of the displayed content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface specifically includes: Collecting pupil image information of the user, and processing the pupil image information using a Hough circle transform algorithm to obtain a pupil diameter sequence; Based on the pupil diameter sequence, calculating the average pupil diameter of the user's pupil diameters in each preset time period; Determine a pupil diameter change rate according to a difference between average pupil diameters in two adjacent preset time periods in the pupil diameter sequence, and determine the user's eye fatigue degree through the pupil diameter change rate; The dwell time of the user on the current interactive interface of the smart wearable device is obtained, and it is determined whether to perform layout optimization on the display content of the current interactive interface according to the eye fatigue and the dwell time.

6. The method according to claim 5, characterized in that The step of determining whether to optimize the layout of the display content of the current interactive interface according to the eye fatigue degree and the dwell time further includes: If it is determined to optimize the layout of the display content of the current interactive interface, determining the priority parameters of each display area of ​​the display content of the current interactive interface according to the historical interaction information of the user on the current interactive interface; According to the priority parameter, the layout of the displayed content of the current interactive interface is readjusted.

7. The method according to claim 1, characterized in that The training of the attention mechanism model according to the historical gaze information and determining the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model specifically includes: Preprocessing the historical gaze information to extract gaze feature data; Based on the gaze feature data, a recurrent neural network is used to train the attention mechanism model to obtain a display area loading priority allocation model; Based on the display area loading priority allocation model, the attention weight of each display area of ​​the smart wearable device is calculated, and the loading priority of each display area is sorted according to the attention weight to form a loading priority list; Based on the loading priority list, the information loading progress of each display area is dynamically adjusted according to the network status and device performance of the smart wearable device.

8. A display system for a smart wearable device, characterized in that: The system specifically comprises: A first display module, used for real-time detection of light intensity data and color temperature data of the use environment of the smart wearable device, and dynamically adjusting first display parameters of the smart wearable device according to the light intensity data and the color temperature data, wherein the first display parameters include display brightness, display contrast and display color; A second display module is used to obtain historical operation information of the user on the interface elements of the smart wearable device, and to personalize the layout of the interface elements of the smart wearable device according to the historical operation information; A third display module, configured to dynamically adjust second display parameters of each display area of ​​the display content using an adaptive display algorithm according to the characteristics and importance of the display content of the smart wearable device, wherein the second display parameters include resolution and refresh rate; A fourth display module, used to determine whether to optimize the layout of the display content of the current interactive interface according to the user's eye fatigue and the dwell time of the current interactive interface; The fifth display module is used to obtain historical gaze information of the user when operating the smart wearable device, train the attention mechanism model according to the historical gaze information, and determine the loading priority of each display area of ​​the smart wearable device through the trained attention mechanism model.

9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory. When the computer program is executed on the processor, the display method of the smart wearable device according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the display method of the smart wearable device as described in any one of claims 1 to 7 is implemented.

Images