Electronic whiteboard large-screen intelligent screen splitting method and system based on AI algorithm

By automatically recognizing and dynamically adjusting the split-screen layout using AI algorithms, the problem of complex manual split-screen recognition in existing technologies has been solved, enabling intelligent split-screen management of electronic whiteboard screens and improving user experience and operational efficiency.

CN119002851APending Publication Date: 2024-11-22GUANGZHOU LANGO ELECTRONICS TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411022724.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Existing electronic whiteboard large-screen split-screen technology requires users to manually identify applications that support split-screen functionality and lacks dynamic adjustment capabilities, resulting in complex operation and a poor user experience.

Method used

It uses AI-based image recognition and reinforcement learning algorithms to automatically identify applications that support split-screen functionality, dynamically generates the optimal split-screen layout, and adjusts the split-screen layout in real time through deep learning algorithms, while also optimizing event response by combining edge computing.

Benefits of technology

It realizes intelligent split-screen management of electronic whiteboard large screen, improves user operation efficiency and experience, and ensures that the split-screen layout meets user needs and is optimized in real time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002851A_ABST
    Figure CN119002851A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of electronic whiteboard screen splitting, in particular to an electronic whiteboard large-screen intelligent screen splitting method and system based on an AI algorithm. The method comprises the following steps: automatically identifying a current running application by utilizing an image identification algorithm and an application identifier library, and judging whether the current running application supports a screen splitting function or not by inquiring a preset database; dynamically generating an optimal split-screen layout by adopting an AI algorithm based on the split-screen requirement of the user and the split-screen judgment result of the current application; the interactive operation of the user is monitored through a deep learning algorithm, and the split-screen layout is automatically adjusted; when the user selects to quit the split screen, the split screen state is evaluated through event monitoring and a state management algorithm, and a quit strategy is determined. By integrating various intelligent algorithms, intelligent split-screen management of the electronic whiteboard large screen is realized, the operation efficiency of the user is improved, the user experience is optimized, the diversified requirements of the user in the aspects of multi-task processing and information display are met, and the overall working efficiency and the user satisfaction degree are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electronic whiteboard split-screen technology, and in particular to an AI algorithm-based large-screen intelligent split-screen method and system for an electronic whiteboard. Background Art

[0002] The application split-screen function is a basic and important function in large-screen electronic whiteboard devices. Especially for large-screen devices, users expect to be able to view and operate multiple applications at the same time. Some customers use this function frequently and clearly express their demand for this function. For example, in an educational scenario, teachers may need to display teaching courseware and student homework feedback at the same time; in a business meeting, users may need to view reports and meeting minutes at the same time. Therefore, the application split-screen function can not only improve the efficiency of work and study, but also meet the specific needs of customers, and even become a must-have item for some users to meet bidding needs. At present, there are still the following problems: users need to manually identify and judge whether the currently running application supports the split-screen function, which not only increases the operation steps, but also easily leads to misjudgment, resulting in the inability to use the split-screen function normally; existing split-screen technology usually relies on a fixed layout scheme and lacks the ability to dynamically adjust according to user needs and application characteristics, resulting in the split-screen layout being unable to meet the personalized needs of users; in the process of user interaction with traditional split-screen technology, the split-screen layout often cannot be adjusted in real time according to user operations, resulting in poor user experience. Summary of the invention

[0003] To solve the above problems, the present invention provides an intelligent split-screen method and system for a large-screen electronic whiteboard based on an AI algorithm, which solves the problem of realizing an intelligent application split-screen function in a large-screen electronic whiteboard device, so that it can automatically identify and determine the split-screen support of the application, dynamically adjust the split-screen layout to meet the personalized needs of users, and optimize the split-screen experience in real time during user interaction, thereby realizing intelligent split-screen management of the large-screen electronic whiteboard, improving the user's operating efficiency, and optimizing the user experience.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] On the one hand, a method for intelligently splitting a large-screen electronic whiteboard based on an AI algorithm comprises the following steps:

[0006] S1: Automatically identify the currently running application using an image recognition algorithm and an application identifier library, and determine whether it supports the split-screen function by querying a preset database;

[0007] S2: Based on the user's split-screen requirements and the split-screen judgment results of the current application, an AI algorithm is used to dynamically generate the optimal split-screen layout;

[0008] S3: Monitor user interactions through deep learning algorithms and automatically adjust split-screen layouts;

[0009] S4: When the user chooses to exit the split screen, the split screen status is evaluated through event monitoring and state management algorithm to determine the exit strategy.

[0010] Furthermore, the operation method of the split-screen function includes long pressing the sidebar application list, clicking the free window operation bar and the multi-tasking application list.

[0011] Furthermore, the application identifier library includes a unique identifier of the application, split-screen support information of the application, and application attribute data related to split-screen.

[0012] Furthermore, the step S1 specifically includes the following steps:

[0013] Get the window information of the application currently running on the electronic whiteboard, including window size, position and application name;

[0014] The acquired window information is processed using an image recognition algorithm to extract the interface features of the application program, and the interface features of the application program in the application identifier library are matched to determine the currently running application program;

[0015] Querying a preset database to obtain split-screen support information corresponding to the currently running application in the application identifier library;

[0016] Determine whether the currently running application supports the split-screen function.

[0017] Furthermore, the determination condition for determining whether the currently running application supports the split-screen function is as follows:

[0018] If split screen is supported, the split screen support status and related attribute data of the current application are recorded;

[0019] If split screen is not supported, skip the current application.

[0020] Furthermore, the step S2 specifically includes the following steps:

[0021] S21: receiving the user's split-screen requirement, and analyzing the number of applications that the user expects to split the screen and the specific layout requirements;

[0022] S22: Based on the user's split-screen requirements, the reinforcement learning algorithm is used to analyze the available screen space of the current electronic whiteboard and calculate the optimal size and position of each application window;

[0023] S23: Referring to the split-screen support information in the application identifier library and combining with the historical split-screen layout data in the preset database, a preliminary split-screen layout plan is generated;

[0024] S24: using a reinforcement learning algorithm to iteratively optimize the preliminary split-screen layout solution to generate an optimal split-screen layout;

[0025] S25: Apply the optimal split-screen layout to the large electronic whiteboard screen to ensure that each application window can run and display normally in split-screen mode.

[0026] Furthermore, the construction of the reinforcement learning algorithm in step S22 includes the following steps:

[0027] Define a state space, an action space and a reward function, wherein the state space includes the available screen space information of the current electronic whiteboard, the size and position of the application window, the action space includes the operation of adjusting the size and position of the application window, and the reward function is set according to the user satisfaction and system resource utilization of the split-screen layout;

[0028] Initialize the reinforcement learning model and perform initial strategy evaluation by randomly sampling initial states and actions;

[0029] During the operation of the electronic whiteboard, user interaction data and system status data are collected in real time to update the parameters of the reinforcement learning model;

[0030] Use the updated reinforcement learning model to optimize the split-screen layout and iterate until the optimal strategy is reached.

[0031] The final optimal split-screen layout solution is applied to the large electronic whiteboard screen.

[0032] Furthermore, the interactive operation includes dragging a separator line to adjust the window size, switching the window position, and converting the application to a small window mode.

[0033] Furthermore, the step S3 includes the following steps:

[0034] S31: Using a deep learning algorithm to collect and analyze user interaction operation data in real time to generate a user interaction model;

[0035] S32: Based on the user interaction model, predict the user's split-screen operation trends and habits, and generate an analysis report;

[0036] S33: dynamically adjusting the current split-screen layout based on the analysis report;

[0037] S34: When it is detected that the user frequently adjusts the split-screen layout, an optimized split-screen solution is generated and recommended.

[0038] Furthermore, the formula of the user interaction model is as follows:

[0039]

[0040] Among them, UIM(t) represents the output of the user interaction model, the split-screen operation trend and habits at time t; N represents the number of user interaction features; w i represents the importance of each user interaction feature in the model; f i represents the user interaction feature function, which is used to process specific interaction data; X i represents the input data of the i-th user interaction feature, including the user's specific interaction operations on the electronic whiteboard; Δt represents the time interval, which is used to capture the dynamic changes of user interaction operations; b represents the output of the adjustment model.

[0041] Furthermore, the event monitoring and state management algorithm is implemented through an edge computing architecture, utilizing local computing resources to improve event response speed.

[0042] Furthermore, the split-screen layout includes horizontal split-screen, vertical split-screen and custom split-screen layout, and also supports intelligent content-aware split-screen, automatically adjusting the split-screen ratio and position according to the application content and user operation.

[0043] On the other hand, an intelligent split-screen system for a large electronic whiteboard screen based on an AI algorithm includes an application identification module, a split-screen layout generation module, a user interaction monitoring module, a state management module, and a display control module that are sequentially connected in communication;

[0044] The application identification module is used to automatically identify the currently running application through an image recognition algorithm and an application identifier library, and query a preset database to determine whether it supports the split-screen function;

[0045] The split-screen layout generation module is used to dynamically generate the optimal split-screen layout using an AI algorithm based on the user's split-screen requirements and the split-screen judgment result of the current application;

[0046] The user interaction monitoring module is used to monitor the user's interactive operations through a deep learning algorithm and automatically adjust the split-screen layout;

[0047] The state management module is used to evaluate the split-screen state through event monitoring and state management algorithm and determine the exit strategy when the user chooses to exit the split-screen;

[0048] The display control module is used to apply the generated optimal split-screen layout to the large electronic whiteboard screen, so that each application window can run and display normally in the split-screen mode.

[0049] The beneficial effects of the present invention are:

[0050] The present invention can automatically identify the currently running application through an image recognition algorithm and an application identifier library, and determine whether it supports the split-screen function by querying a preset database. This enables the system to intelligently adapt to different types of applications and improve the applicability and flexibility of the split-screen function. The AI ​​algorithm is used to dynamically generate the optimal split-screen layout based on user needs and application compatibility, ensuring that users can obtain the best operating experience and visual effects while maximizing the use of screen space. The deep learning algorithm monitors the user's interactive operations in real time, and automatically adjusts the split-screen layout according to user behavior, so that the split-screen layout can flexibly respond to various user operation needs and provide a more intelligent and personalized user experience. Through event monitoring and state management algorithms, when the user chooses to exit the split screen, the split-screen state can be intelligently evaluated and the optimal exit strategy can be determined to avoid operational confusion and inconvenience caused by exiting the split screen, and to ensure the continuity and fluency of user operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of an intelligent split-screen method for a large-screen electronic whiteboard based on an AI algorithm in the present invention.

[0052] Figure 2 It is a flowchart of step S2 provided in an embodiment of the present invention.

[0053] Figure 3 It is a module schematic diagram of an electronic whiteboard large-screen intelligent split-screen system based on AI algorithm in the present invention. DETAILED DESCRIPTION

[0054] See also Figure 1-3 As shown, the present invention relates to an intelligent screen splitting method and system for a large-screen electronic whiteboard based on an AI algorithm.

[0055] Example 1

[0056] An intelligent split-screen method for a large-screen electronic whiteboard based on an AI algorithm comprises the following steps:

[0057] S1: Use image recognition algorithm and application identifier library to automatically identify the currently running application, and determine whether it supports the split-screen function by querying the preset database; the operation method of the split-screen function includes long pressing the sidebar application list, clicking the free window operation bar and the multi-tasking application list; the application identifier library includes the unique identifier of the application, the split-screen support information of the application, and the application attribute data related to the split-screen.

[0058] Specifically, an image recognition algorithm (such as OpenCV, TensorFlow, etc.) is run on the operation interface of the electronic whiteboard large screen to capture the currently displayed application interface in real time. The key elements of the application interface, such as icons, title bars, menu bars, buttons, etc., are extracted through the image recognition algorithm. A feature matching algorithm (such as SI FT, SURF) is used to determine the feature points of these elements. The extracted interface elements are analyzed, and the unique identifier of the application (such as the application package name, process ID, etc.) is extracted through the preset feature mapping rules (such as the correspondence between the icon and the application package name). The extracted application unique identifier is input into the preset database for retrieval. The database stores the unique identifier of each application, split-screen support information, and application attribute data related to split-screen. The retrieval result returns the split-screen support information of the application, including whether the application supports split-screen, the supported split-screen mode (such as horizontal split-screen, vertical split-screen, custom split-screen), and the split-screen related attributes of the application (such as minimized size, minimum window width, etc.).

[0059] It should be noted that the split screen function operation mode is as follows:

[0060] Long press on the sidebar application list: The system monitors whether the user long presses an application icon in the sidebar application list. If a long press operation is detected, it is considered that the user intends to perform a split-screen operation.

[0061] Click on the free window operation bar: The system monitors whether the user clicks the split screen button in the free window operation bar. The user's split screen operation intention is confirmed by analyzing the location and target control of the user's click event.

[0062] Multitasking application list: The system monitors whether the user has selected an application in the multitasking application list for split-screen operation. By monitoring the user's sliding, clicking and other operations in the multitasking interface, the system determines the split-screen demand.

[0063] Wherein, the step S1 specifically includes the following steps:

[0064] Get the window information of the application currently running on the electronic whiteboard, including window size, position and application name;

[0065] It should be noted that the detailed information of the currently active window is obtained, including the window size, position and application name.

[0066] Window size: Width and height in pixels.

[0067] Window position: The coordinates (x, y) of the upper left corner of the window on the screen.

[0068] Application name: Get the name of the application through the window handle.

[0069] The acquired window information is processed using an image recognition algorithm to extract the interface features of the application program, and the interface features of the application program in the application identifier library are matched to determine the currently running application program;

[0070] Specifically, the application identifier library contains the unique identifier of each application, split-screen support information and related attribute data. The library needs to be pre-built and regularly updated. A similarity matching algorithm (such as cosine similarity, Euclidean distance, etc.) is used to compare the extracted feature vector with the feature vector in the identifier library to find the best matching application.

[0071] Querying a preset database to obtain split-screen support information corresponding to the currently running application in the application identifier library;

[0072] Determine whether the currently running application supports the split-screen function;

[0073] The conditions for determining whether the currently running application supports the split-screen function are as follows:

[0074] If split screen is supported, the split screen support status and related attribute data of the current application are recorded;

[0075] If split screen is not supported, the current application is skipped and the split screen operation is not performed.

[0076] S2: Based on the user's split-screen requirements and the split-screen judgment results of the current application, an AI algorithm is used to dynamically generate the optimal split-screen layout;

[0077] Wherein, the step S2 specifically includes the following steps:

[0078] S21: receiving the user's split-screen requirement, and analyzing the number of applications that the user expects to split the screen and the specific layout requirements;

[0079] Specifically, the user inputs the split-screen requirement through the interactive interface, and the system receives the number of split-screen applications desired by the user and the specific layout requirements. These requirements may include the number of application windows, the relative size, position and priority of each window;

[0080] Number of application windows: The number of applications that the user wants to display simultaneously.

[0081] Specific layout requirements: User preferences for the size, position, and relative order of each window. For example, a user may want a large window on the left for the main work area, and two smaller windows on the right for auxiliary information display.

[0082] Priority: Users can specify the display priority of certain applications, ensuring that important application windows are always visible and in a premium position.

[0083] S22: Based on the user's split-screen requirements, the reinforcement learning algorithm is used to analyze the available screen space of the current electronic whiteboard and calculate the optimal size and position of each application window;

[0084] Furthermore, the construction of the reinforcement learning algorithm in step S22 includes the following steps:

[0085] Define a state space, an action space and a reward function, wherein the state space includes the available screen space information of the current electronic whiteboard, the size and position of the application window, the action space includes the operation of adjusting the size and position of the application window, and the reward function is set according to the user satisfaction and system resource utilization of the split-screen layout;

[0086] It should be noted that the state space includes the available screen space information of the current electronic whiteboard and the size and position of each application window. Specifically, the state space can be represented as a multi-dimensional vector, and each dimension corresponds to a specific screen parameter or window parameter, such as the width and height of the screen, the width and height of the window and its coordinates on the screen, etc.

[0087] The action space includes operations for adjusting the size and position of the application window. Each action can be expressed as resizing (increasing or reducing the width and height) and moving (moving up, down, left, and right) a window.

[0088] The reward function is set based on the user satisfaction and system resource utilization of the split-screen layout. User satisfaction can be evaluated by surveying user feedback or through user interaction data during use (such as window adjustment frequency, number of adjustments, etc.). System resource utilization can be evaluated through indicators such as screen space utilization, processor and memory occupancy.

[0089] Initialize the reinforcement learning model, perform initial strategy evaluation by randomly sampling initial states and actions; use the Q-learning algorithm to learn the initial strategy and record the Q value of each state-action pair

[0090] During the operation of the electronic whiteboard, user interaction data and system status data are collected in real time to update the parameters of the reinforcement learning model;

[0091] The updated reinforcement learning model is used to optimize and adjust the split-screen layout, and it is continuously iterated until the optimal strategy is converged. In terms of specific implementation, the experience replay and deep Q network (DQN) methods can be used to improve the efficiency and effect of reinforcement learning.

[0092] The final optimal split-screen layout solution is applied to the large electronic whiteboard screen.

[0093] S23: Referring to the split-screen support information in the application identifier library and combining with the historical split-screen layout data in the preset database, a preliminary split-screen layout plan is generated;

[0094] S24: using a reinforcement learning algorithm to iteratively optimize the preliminary split-screen layout solution to generate an optimal split-screen layout;

[0095] S25: Apply the optimal split-screen layout to the large electronic whiteboard screen to ensure that each application window can run and display normally in split-screen mode.

[0096] S3: Monitor the user's interactive operations through deep learning algorithms and automatically adjust the split-screen layout; the interactive operations include dragging the dividing line to adjust the window size, switching the window position, and converting the application to small window mode; the split-screen layout includes horizontal split-screen, vertical split-screen and custom split-screen layout, and also supports intelligent content-aware split-screen, which automatically adjusts the split-screen ratio and position according to the application content and user operations.

[0097] Wherein, the step S3 comprises the following steps:

[0098] S31: using a deep learning algorithm to collect and analyze the user's interactive operation data in real time to generate a user interaction model; the deep learning algorithm includes one or more of a recurrent neural network, a convolutional neural network, a self-supervised learning algorithm, and a long short-term memory network;

[0099] Specifically, sensors and log recording tools are used to collect real-time data on user interaction operations on the electronic whiteboard. Specific interaction operations include dragging the separator line to adjust the window size, switching the window position, and converting the application to small window mode. The collected interaction operation data is preprocessed to filter out noise data and extract effective feature values. Feature values ​​include operation frequency, operation time, window size change, etc.

[0100] S32: Based on the user interaction model, predict the user's split-screen operation trends and habits, and generate an analysis report;

[0101] Specifically, based on the trained user interaction model, the user's split-screen operation trends and habits are predicted in real time. For example, predict whether the user is more inclined to use horizontal split-screen or vertical split-screen in a specific time period, or predict whether the user is more inclined to adjust the window size or position. Using sliding window technology, the user's operation data is input in segments to capture short-term and long-term operation trends. Generate an analysis report containing the prediction results, and the report content includes: user's operation habits (such as commonly used split-screen layout types). Split-screen preferences (such as the frequency of window size adjustment). Frequency of use (such as the frequency with which a specific application is converted to small window mode). After the analysis report is generated, it is stored in the database for subsequent query and analysis.

[0102] S33: dynamically adjusting the current split-screen layout based on the analysis report;

[0103] Specifically, according to the analysis report, the system dynamically adjusts the current split-screen layout to adapt to the user's operating habits and trends. The system automatically adjusts the split-screen ratio and position according to the content of the application and the user's operation. For example, when the user uses a text editor and a browser, the system automatically sets the text editor window to a larger ratio and the browser window to a smaller ratio. If it is predicted that the user is more inclined to use horizontal split screen within a specific time period, the system automatically adjusts the layout to horizontal split screen. If the user frequently adjusts the window size within a certain period of time, the system will automatically optimize the allocation of window sizes to reduce the user's repeated operations. The system communicates with the split-screen management module of the electronic whiteboard through the API interface to achieve dynamic adjustment. After each adjustment, the system records the layout status before and after the adjustment for subsequent analysis and optimization.

[0104] S34: When it is detected that the user frequently adjusts the split-screen layout, an optimized split-screen solution is generated and recommended.

[0105] Furthermore, the formula of the user interaction model is as follows:

[0106]

[0107] Among them, UIM(t) represents the output of the user interaction model, the split-screen operation trend and habits at time t; N represents the number of user interaction features; w i represents the importance of each user interaction feature in the model; f i represents the user interaction feature function, which is used to process specific interaction data; X i represents the input data of the i-th user interaction feature, including the user's specific interaction operations on the electronic whiteboard; Δt represents the time interval, which is used to capture the dynamic changes of user interaction operations; b represents the output of the adjustment model.

[0108] S4: When the user chooses to exit the split screen, the split screen state is evaluated through the event monitoring and state management algorithm to determine the exit strategy. The event monitoring and state management algorithm is implemented through the edge computing architecture, using local computing resources to improve the event response speed.

[0109] It should be noted that an event listener (such as addEventListener in JavaScript or the event processing interface provided by the operating system) is used to capture the user's exit split screen operation. When the listener detects an exit event, the event information (such as event type, trigger position, trigger time, etc.) is passed to the state management module.

[0110] Once the split-screen exit event is captured, the system immediately collects data about the current split-screen state, including the number of currently active split-screen windows, application information for each window, window size and position, and window content type.

[0111] Using a state management algorithm (such as a finite state machine algorithm), the system analyzes the collected data.

[0112] The analysis includes:

[0113] Number of active windows: Determines how many split-screen windows are currently running.

[0114] Content Priority: Evaluates the priority of each window's content (for example, a video conference window takes precedence over a document window).

[0115] User history operations: Refer to the user's previous operation habits (for example, windows that the user often keeps).

[0116] To improve the speed of event response, the system adopts edge computing architecture to execute event monitoring and state management algorithms on local computing resources. The built-in computing power of the electronic whiteboard (such as CPU, GPU, etc.) is used to process user operation events to ensure immediate response to operations. Edge computing nodes work in collaboration with cloud servers through a distributed computing architecture. Preliminary event processing and state evaluation are performed locally, and complex computing tasks (such as machine learning model training) are handed over to the cloud for processing. Ensure that the system can still efficiently respond to events and manage split-screen states even when network conditions are poor.

[0117] The exit strategy is determined as follows:

[0118] Single Window Exit: When the system detects that there is only one split-screen window, it will directly exit split-screen mode and return to single-window mode. At this time, the only window will be enlarged to full screen, ensuring that the user can continue to use the application without interruption.

[0119] Multiple window exit:

[0120] 1. Priority sorting: The system sorts the split-screen windows by importance based on content priority and user history operations.

[0121] 2. Gradually exit: The system gradually closes the split-screen windows in order of priority from low to high. For each window, the system will pop up a confirmation prompt to ask the user whether to close the window. The user can choose to keep the important windows.

[0122] 3. Final integration: When only one or a few high-priority windows remain, the system will automatically integrate these windows into a suitable layout. For example, the remaining two windows are displayed side by side, or the most important window is enlarged to the main display area.

[0123] Smart recovery: The system records the user's exit split-screen selection and current status so that the next time the split-screen function is used, the previous split-screen layout can be automatically restored according to the user's preference.

[0124] When exiting split-screen mode, the system will provide real-time visual feedback, such as gradient animation, window zooming effects, etc., to make the whole process smoother and more natural. The system will provide operation prompts when exiting split-screen mode, guiding users on how to restore to single-window mode or perform other operations, improving the user experience.

[0125] Example 2

[0126] An intelligent split-screen system for electronic whiteboards based on AI algorithms, comprising an application identification module, a split-screen layout generation module, a user interaction monitoring module, a state management module and a display control module that are sequentially connected in communication;

[0127] The application identification module is used to automatically identify the currently running application through an image recognition algorithm and an application identifier library, and query a preset database to determine whether it supports the split-screen function;

[0128] The split-screen layout generation module is used to dynamically generate the optimal split-screen layout using an AI algorithm based on the user's split-screen requirements and the split-screen judgment result of the current application;

[0129] The user interaction monitoring module is used to monitor the user's interactive operations through a deep learning algorithm and automatically adjust the split-screen layout;

[0130] The state management module is used to evaluate the split-screen state through event monitoring and state management algorithm and determine the exit strategy when the user chooses to exit the split-screen;

[0131] The display control module is used to apply the generated optimal split-screen layout to the large electronic whiteboard screen, so that each application window can run and display normally in the split-screen mode.

[0132] In this embodiment, an intelligent split-screen system for a large electronic whiteboard based on an AI algorithm is applied to an intelligent split-screen method for a large electronic whiteboard based on an AI algorithm described in Example 1, which will not be repeated here.

[0133] In summary, the present invention utilizes image recognition algorithms and application identifier libraries, so that the system can automatically identify the currently running application and query the preset database to determine whether it supports the split-screen function. This automated recognition and judgment process improves the intelligence level of the system and reduces the complexity of manual operations by users. It supports multiple split-screen operation modes such as long pressing the sidebar application list, clicking the free window operation bar and the multi-tasking application list, so that users can flexibly choose the appropriate split-screen mode according to their personal habits and needs, thereby improving the user experience.

[0134] The present invention uses reinforcement learning algorithms and deep learning algorithms, and the system can dynamically generate the optimal split-screen layout according to the user's split-screen requirements and the split-screen judgment results of the current application. The reinforcement learning algorithm takes into account user satisfaction and system resource utilization, and the deep learning algorithm monitors user interaction operations to achieve real-time optimization and adjustment of the split-screen layout, ensuring the intelligence and efficiency of the split-screen layout. The deep learning algorithm is used to analyze the user's interactive operation data, generate a user interaction model, and predict the user's split-screen operation trends and habits. According to the analysis results, the current split-screen layout is dynamically adjusted so that the system can better adapt to the user's operating habits and enhance the user's operating experience.

[0135] The present invention implements event monitoring and state management algorithms through edge computing architecture, uses local computing resources to improve event response speed, ensures that the system can still efficiently perform event response and split-screen state management under poor network conditions, and enhances the stability and reliability of the system. When the user chooses to exit the split screen, the system can evaluate the split-screen state through event monitoring and state management algorithms to determine the optimal exit strategy. The strategy includes single-window exit, multi-window exit, intelligent recovery, etc., to ensure that the user can still use the electronic whiteboard efficiently after exiting the split-screen mode, and improve the continuity and smoothness of the user experience. During the process of splitting and exiting the split screen, the system provides real-time visual feedback and operation prompts, making the entire operation process smoother and more natural, while guiding the user on how to perform related operations to improve the user's operational convenience.

[0136] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.

Claims

1. An intelligent split-screen method for large-screen electronic whiteboards based on AI algorithms. It is characterized in that The following steps are involved: S1: Automatically identify the currently running application using an image recognition algorithm and an application identifier library, and determine whether it supports the split-screen function by querying a preset database; S2: Based on the user's split-screen requirements and the split-screen judgment results of the current application, an AI algorithm is used to dynamically generate the optimal split-screen layout; S3: Monitor user interactions through deep learning algorithms and automatically adjust split-screen layouts; S4: When the user chooses to exit the split screen, the split screen status is evaluated through event monitoring and state management algorithm to determine the exit strategy.

2. According to claim 1, a large-screen intelligent split-screen method of an electronic whiteboard based on an AI algorithm, It is characterized in that The operation method of the split-screen function includes long pressing the sidebar application list, clicking the free window operation bar and the multi-tasking application list.

3. According to claim 1, a large-screen intelligent split-screen method of an electronic whiteboard based on an AI algorithm, It is characterized in that The application identifier library includes a unique identifier of an application program, split-screen support information of the application program, and application program attribute data related to split-screen.

4. According to claim 1, a large-screen intelligent split-screen method of an electronic whiteboard based on an AI algorithm, It is characterized in that The step S1 specifically includes the following steps: Get the window information of the application currently running on the electronic whiteboard, including window size, position and application name; The acquired window information is processed using an image recognition algorithm to extract the interface features of the application program, and the interface features of the application program in the application identifier library are matched to determine the currently running application program; Querying a preset database to obtain split-screen support information corresponding to the currently running application in the application identifier library; Determine whether the currently running application supports the split-screen function.

5. According to claim 4, a method for intelligent splitting of electronic whiteboard large screen based on AI algorithm, It is characterized in that The conditions for determining whether the currently running application supports the split-screen function are as follows: If split screen is supported, the split screen support status and related attribute data of the current application are recorded; If split screen is not supported, skip the current application.

6. According to claim 1, a method for intelligent splitting of electronic whiteboard large screen based on AI algorithm, It is characterized in that The step S2 specifically includes the following steps: S21: receiving the user's split-screen requirement, and analyzing the number of applications that the user expects to split the screen and the specific layout requirements; S22: Based on the user's split-screen requirements, the reinforcement learning algorithm is used to analyze the available screen space of the current electronic whiteboard and calculate the optimal size and position of each application window; S23: Referring to the split-screen support information in the application identifier library and combining with the historical split-screen layout data in the preset database, a preliminary split-screen layout plan is generated; S24: using a reinforcement learning algorithm to iteratively optimize the preliminary split-screen layout solution to generate an optimal split-screen layout; S25: Apply the optimal split-screen layout to the large electronic whiteboard screen to ensure that each application window can run and display normally in split-screen mode.

7. According to claim 6, a method for intelligently splitting a large-screen electronic whiteboard based on an AI algorithm, It is characterized in that The construction of the reinforcement learning algorithm in step S22 includes the following steps: Define a state space, an action space and a reward function, wherein the state space includes the available screen space information of the current electronic whiteboard, the size and position of the application window, the action space includes the operation of adjusting the size and position of the application window, and the reward function is set according to the user satisfaction and system resource utilization of the split-screen layout; Initialize the reinforcement learning model and perform initial strategy evaluation by randomly sampling initial states and actions; During the operation of the electronic whiteboard, user interaction data and system status data are collected in real time to update the parameters of the reinforcement learning model; Use the updated reinforcement learning model to optimize the split-screen layout and iterate until the optimal strategy is reached. The final optimal split-screen layout solution is applied to the large electronic whiteboard screen.

8. According to claim 1, a method for intelligent splitting of electronic whiteboard large screen based on AI algorithm, It is characterized in that The interactive operations include dragging a separator line to adjust the window size, switching the window position, and converting the application to a small window mode.

9. According to claim 1, a method for intelligently splitting a large-screen electronic whiteboard based on an AI algorithm, It is characterized in that The step S3 comprises the following steps: S31: Using a deep learning algorithm to collect and analyze user interaction operation data in real time to generate a user interaction model; S32: Based on the user interaction model, predict the user's split-screen operation trends and habits, and generate an analysis report; S33: dynamically adjusting the current split-screen layout based on the analysis report; S34: When it is detected that the user frequently adjusts the split-screen layout, an optimized split-screen solution is generated and recommended.

10. The method for intelligently splitting a large-screen electronic whiteboard based on an AI algorithm according to claim 9, It is characterized in that The formula of the user interaction model is as follows: Among them, UIM(t) represents the output of the user interaction model, the split-screen operation trend and habits at time t; N represents the number of user interaction features; w i represents the importance of each user interaction feature in the model; f i represents the user interaction feature function, which is used to process specific interaction data; X i represents the input data of the i-th user interaction feature, including the user's specific interaction operations on the electronic whiteboard; Δt represents the time interval, which is used to capture the dynamic changes of user interaction operations; b represents the output of the adjustment model.

11. The method for intelligently splitting a large-screen electronic whiteboard based on an AI algorithm according to claim 1, It is characterized in that The event monitoring and state management algorithm is implemented through an edge computing architecture, utilizing local computing resources to improve event response speed.

12. The method for intelligently splitting a large-screen electronic whiteboard based on an AI algorithm according to claim 1, It is characterized in that The split-screen layout includes horizontal split-screen, vertical split-screen and custom split-screen layout, and also supports intelligent content-aware split-screen, which automatically adjusts the split-screen ratio and position according to application content and user operations.

13. An intelligent split-screen system for electronic whiteboards based on AI algorithms. It is characterized in that The system is applied to an intelligent split-screen method for a large-screen electronic whiteboard based on an AI algorithm as described in any one of claims 1 to 12, comprising an application identification module, a split-screen layout generation module, a user interaction monitoring module, a state management module, and a display control module that are sequentially connected in communication; The application identification module is used to automatically identify the currently running application through an image recognition algorithm and an application identifier library, and query a preset database to determine whether it supports the split-screen function; The split-screen layout generation module is used to dynamically generate the optimal split-screen layout using an AI algorithm based on the user's split-screen requirements and the split-screen judgment result of the current application; The user interaction monitoring module is used to monitor the user's interactive operations through a deep learning algorithm and automatically adjust the split-screen layout; The state management module is used to evaluate the split-screen state through event monitoring and state management algorithm and determine the exit strategy when the user chooses to exit the split-screen; The display control module is used to apply the generated optimal split-screen layout to the large electronic whiteboard screen, so that each application window can run and display normally in the split-screen mode.

Citation Information

Cited By

  • Dynamic display method and system for display screen of mobile communication equipment

    CN120034605A

  • Intelligent screen connection method and system for double-screen display screen

    CN120066440A