Automatic screensaver activation system for electronic whiteboard large-screen equipment

By identifying and analyzing the working mode of electronic whiteboard large screen devices, using cluster analysis and random forest models to set screen save activation time, the problem of inconsistent automatic activation screen save time and working mode requirements is solved, and image residual control effect and user experience are improved .

CN119003078APending Publication Date: 2024-11-22GUANGZHOU LANGO ELECTRONICS TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411143645.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art is difficult to coordinate the relationship between the time when automatically activating screen savers and the frequency requirements for screen use of different working modes, resulting in poor image residual control effect.

Method used

By identifying the started application of the current screen system, collecting screen work data from historical periods, using cluster analysis and random forest model, analyzing screen usage frequency of different working modes, setting appropriate screen saver activation time, combining the operationless detection module and screen saver Activate the module and automatically activate the screen saver.

Benefits of technology

Effectively coordinate the time of automatically activating screen savers, improve the control effect of image residues, and improve the user experience and device service life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119003078A_ABST
    Figure CN119003078A_ABST
Patent Text Reader

Abstract

The invention relates to an automatic screensaver activation system for electronic whiteboard large-screen equipment, which comprises the following steps of: determining a working mode of a current screen by identifying a started application of a current screen system; inputting the current working mode into a time setting model, outputting a predicted screen use frequency, and setting a screensaver activation time according to the predicted screen use frequency; and when the no-operation time of the screen exceeds the screensaver activation time, automatically activating the screensaver. The problem that in the prior art, it is difficult to coordinate the relation between the time opportunity of automatically activating the screensaver and the requirements of different working modes for the use frequency of the screen is solved. In the process, the started applications are classified by adopting a clustering analysis method, and the screen working data are divided into a plurality of working modes with the same or similar started application combination characteristics, so that the efficiency of identifying the current working mode is improved. The random forest model is constructed to quantify the relationship between different working modes and the screen use frequency thereof, and the accuracy of user demand prediction is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of display device screen savers and relates to an automatic screen saver activation system for electronic whiteboard large-screen equipment. Background Art

[0002] With the rapid development of information technology, electronic whiteboards, as an important tool for modern education and conferences, have gradually replaced traditional blackboards and whiteboards, providing richer multimedia presentation and interactive functions. However, in actual applications, electronic whiteboards are prone to image retention due to long-term display of static content, which not only affects the user experience but also shortens the service life of the device. Screen image retention refers to the situation where an "afterimage" may be left on the screen when the screen switches to another image after displaying a still image or menu for a short time.

[0003] At present, people can reduce the image retention problem by automatically activating dynamic screen savers when there is no operation. However, when the time for automatically activating the screen saver is set too short, the screen may frequently enter the screen saver state and affect normal use; when the time is set too long, it is difficult to solve the image retention problem. Therefore, how to coordinate the relationship between the time of automatically activating the screen saver and the screen working mode has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides an automatic screen saver activation system for electronic whiteboard large-screen equipment, which aims to use historical experience data to set different times for entering the screen saver without operation according to the screen usage frequency of different working modes, so as to solve the problem of inconsistency between automatic activation of the screen saver and the working state.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides an automatic screen saver activation system for an electronic whiteboard large-screen device, including an application identification module, a working mode analysis module, a time setting module, a no-operation detection module, a screen saver activation module, and a screen saver exit module, wherein the application identification module, the working mode analysis module, the time setting module, the no-operation detection module, the screen saver activation module, and the screen saver exit module are communicatively connected, wherein:

[0007] The application identification module is used to identify the started applications of the current screen system;

[0008] The working mode analysis module is used to input the started application into a preset working mode analysis model and output the current working mode; the working mode analysis model includes the following construction steps:

[0009] S1. Collect screen work data in historical periods, where the screen work data includes started applications and screen usage frequency, where the screen usage frequency includes operation duration and interval between adjacent operations;

[0010] S2, converting each started application type into numerical data;

[0011] S3, using a cluster analysis method to classify the launched applications, and dividing the screen work data into several work modes with the same or similar launched application combination characteristics;

[0012] The time setting module is used to input the current working mode into a time setting model, output a predicted screen usage frequency, and set the screen saver activation time according to the predicted screen usage frequency; the time setting model is configured as a random forest model, including the following construction steps:

[0013] T1. Data preparation: prepare a data set containing explanatory variables and response variables, the explanatory variable is the working mode, and the response variable is the screen usage frequency;

[0014] T2. Dataset division: Divide the collected data set into training set and test set, where 70% of the data samples in the data set are used as the training set and 30% of the data samples are used as the test set;

[0015] T3, random sampling: randomly extract several explanatory variables and data samples from the training set, and construct multiple different training sets with replacement;

[0016] T4. Build a decision tree: For each randomly sampled training set, build a decision tree model;

[0017] T5. Integrated decision tree: Integrate multiple decision tree models into a random forest model and use the average value to make the final prediction;

[0018] T6. Model evaluation: Use evaluation indicators to evaluate the prediction performance of the random forest model on the test set and determine the final model with good prediction performance;

[0019] The no-operation detection module is used to monitor whether the current screen is being operated, and to use a timer to start calculating the no-operation time when no operation is performed;

[0020] The screen saver activation module is used to automatically activate the screen saver when the screen is not operated for a period exceeding the screen saver activation time;

[0021] The screen saver exit module is used to exit the screen saver mode when it is detected that the user touches the screen or uses the remote controller.

[0022] Furthermore, the working modes include teaching mode, meeting mode, display mode, leisure mode and editing mode.

[0023] Furthermore, in step S3, the cluster analysis method is configured as a K-means clustering method, comprising the following steps:

[0024] S31, normalization processing: normalizing the started application data variables;

[0025] S32, initializing cluster centers: randomly selecting several data objects in the data space as initial cluster centers;

[0026] S33, initializing clusters: calculating the Euclidean distance between all data objects and the initial cluster center, and dividing each data object into the initial cluster center with the smallest Euclidean distance to form an initial cluster;

[0027] S34, updating the cluster center: calculating the average value of the data objects of each initial cluster, and taking the average value as the new cluster center;

[0028] S35. Determine the final cluster: repeatedly calculate the Euclidean distance between all data objects and the new cluster center, divide each data object into the new cluster center with the smallest Euclidean distance to form a new cluster; calculate the average value of each new cluster as the new cluster center again, and determine the final cluster after the new cluster center no longer changes, and determine the corresponding working mode according to the combination of started applications in each final cluster.

[0029] Furthermore, in step S31, the normalization process is calculated using the following formula:

[0030]

[0031] Where Y i is the normalized data sample of the ith launched application; K i is the i-th launched application data sample; K max Indicates the maximum value of all launched application data samples; K min Indicates the minimum value of all launched app data samples.

[0032] Furthermore, in step S33, the Euclidean distance is calculated by the following formula:

[0033]

[0034] In the formula, d(x,C i ) represents the Euclidean distance function; x is the normalized data object; C i represents the i-th cluster center; n is the number of samples in the data set; xj Represents the data object of the jth variable in the data set; C ij represents the i-th cluster center of the j-th variable.

[0035] Furthermore, in step T4, the decision tree model is configured as a CART model.

[0036] Furthermore, in step T6, the evaluation index adopts accuracy, precision, recall or F1 value.

[0037] Furthermore, the time setting module, after selecting to set the time, stores the time setting in a non-volatile memory of the device so that the setting is maintained when the same working mode is started next time.

[0038] Furthermore, the no-operation detection module resets the timer when detecting that the user starts an operation.

[0039] Furthermore, the screen saver displays a black screen and a clock UI, and the clock UI displays the current time and date in a format consistent with the system settings and moves every two seconds.

[0040] Furthermore, the screen saver exit module restores the previous display content after exiting the screen saver.

[0041] Beneficial effects of the present invention:

[0042] (1) By identifying the started applications of the current screen system, the working mode of the current screen is determined; the current working mode is input into the time setting model, the predicted screen usage frequency is output, and the screen saver activation time is set according to the predicted screen usage frequency; when the screen is not operated for a time exceeding the screen saver activation time, the screen saver is automatically activated. The present invention solves the problem that it is difficult to coordinate the relationship between the time opportunity of automatically activating the screen saver and the screen usage frequency requirements of different working modes in the prior art, resulting in poor image retention control effect.

[0043] (2) By collecting screen work data of historical periods, the screen work data includes launched applications and screen usage frequency, and using a cluster analysis method to classify the launched applications, the screen work data is divided into several work modes with the same or similar launched application combination characteristics, thereby improving the efficiency of identifying the current work mode.

[0044] (3) Construct a random forest model to quantify the relationship between different working modes and their screen usage frequency. By monitoring the screen usage frequency of different working modes, the screen saver activation time is set to meet user needs and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0046] Figure 1 The present invention is a structural diagram of an automatic screen saver activation system for an electronic whiteboard large-screen device. DETAILED DESCRIPTION

[0047] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0048] See also Figure 1 The present application provides an automatic screen saver activation system for an electronic whiteboard large-screen device, including an application identification module, a working mode analysis module, a time setting module, a no-operation detection module, a screen saver activation module, and a screen saver exit module, wherein the application identification module, the working mode analysis module, the time setting module, the no-operation detection module, the screen saver activation module, and the screen saver exit module are communicatively connected, wherein:

[0049] The application identification module is used to identify the started applications of the current screen system;

[0050] The working mode analysis module is used to input the started application into a preset working mode analysis model and output the current working mode;

[0051] In this embodiment, in order to identify the applications that have been started by the current screen system and determine the working mode, monitoring can be performed by using the APIs and tools provided by the system. First of all, application monitoring is the key. By calling APIs such as `GetForegroundWindow` of the Windows system, the name of the current active window can be obtained, so that the running application can be identified. After understanding the current application, it needs to be classified into different working modes. Working modes generally include teaching mode, meeting mode, presentation mode, leisure mode, and editing mode. For example, when using PowerPoint or Keynote for presentations, it can be classified as presentation mode, while when conducting online teaching, such as using Zoom and Teams, it can be classified as teaching mode. By establishing a simple mapping table, specific applications can be associated with corresponding working modes, thereby achieving automatic identification.

[0052] During this process, the rule engine can automatically map the identified applications to predefined working modes. For different application names, such as Word and Google Docs, they can be classified as editing mode, while VLC Player and Steam are classified as leisure mode. Monitoring changes in application status is an important step, which is usually implemented through the operating system's event listening function or timer to periodically check the status of the currently active window. Throughout the monitoring process, feedback can also be provided to the user, converting the identified working mode into visual information, and even automatically adjusting the screen saver settings. For example, in teaching mode, the system can extend the screen saver activation time, while in leisure mode it can shorten the time to improve the user experience.

[0053] Furthermore, the working modes include teaching mode, meeting mode, display mode, leisure mode and editing mode.

[0054] It should be noted that different working modes have differences in the types and numbers of started applications. In order to better identify the current working mode, this embodiment uses a clustering algorithm to determine the working mode types corresponding to different combinations of started applications. Thus, the system can determine the current working mode by identifying the currently started applications.

[0055] Furthermore, the working mode analysis model includes the following construction steps:

[0056] S1. Collect screen work data in historical periods, where the screen work data includes started applications and screen usage frequency, where the screen usage frequency includes operation duration and interval between adjacent operations;

[0057] In this embodiment, the combination of activated applications can determine the current working mode, and the screen usage frequency refers to the frequency of operations performed by the user when interacting with the electronic device, which usually involves two aspects: operation duration and interval between adjacent operations. Operation duration refers to the time a user interacts with a specific application or interface, while the interval between adjacent operations is the time difference between two operations (average value of multiple operations). Understanding these frequency indicators not only helps to reveal users' attention to various applications and usage habits, but also provides companies and developers with an important basis for optimizing applications and improving user experience.

[0058] Data collection can be achieved through methods such as event monitoring and timed sampling. The former records all user interactions with the screen, including timestamps and operation types, and the latter regularly records the currently used applications and status to provide a basis for subsequent analysis. Statistical analysis can reveal the user's total usage time, operation frequency and time pattern, identify which applications are most popular, and the user's active time periods and work habits. For example, if an application is operated for a long time and at a high frequency, this may indicate that the application meets the user's needs.

[0059] S2, converting each started application type into numerical data;

[0060] In this embodiment, converting the launched application type into numerical data is an important step in cluster analysis. There are several commonly used methods. The first is label encoding, which assigns a unique integer to each application type, such as 0 for social media, 1 for games, 2 for office software, and 3 for entertainment. This method is suitable for ordered categories. The second is unique hot encoding, which is suitable for unordered categories. Each application type is converted into multiple binary variables, such as social media becomes [1,0,0,0], and games become [0,1,0,0], which can effectively eliminate the order effect between categories. In addition, binary encoding is also an effective way to convert the results after label encoding into binary format, thereby reducing dimensions and improving efficiency. Finally, frequency encoding calculates the frequency of occurrence of each application type and converts it into a numerical value to reflect the actual usage, such as 40% for social media and 30% for games. Choosing an appropriate encoding method depends on the data characteristics and analysis objectives. After the conversion is completed, these numerical data can be used for cluster analysis, such as K-means and hierarchical clustering, which helps to mine potential information in the data and improve the effectiveness and depth of analysis.

[0061] S3, using a cluster analysis method to classify the launched applications, and dividing the screen work data into several work modes with the same or similar launched application combination characteristics;

[0062] Furthermore, in step S3, the cluster analysis method is configured as a K-means clustering method, comprising the following steps:

[0063] S31, normalization processing: normalizing the started application data variables;

[0064] In this embodiment, the purpose of normalizing the activated application data variables is to unify the data ranges between different numerical features so that they have the same scale. This can avoid the problem of weight imbalance between different features due to different data ranges, and ensure that each feature can be properly reflected in the clustering process. Through normalization, the dimensional influence between data can be eliminated, making the data easier to compare and analyze, thereby improving the accuracy and efficiency of clustering. In addition, normalization can also make the clustering algorithm more stable and converge faster, which is conducive to obtaining more accurate and reliable clustering results. Therefore, before performing cluster analysis on the activated application data variables, the data is usually normalized to achieve better clustering effects.

[0065] S32, initializing cluster centers: randomly selecting several data objects in the data space as initial cluster centers;

[0066] In this embodiment, when initializing the cluster centers, a common practice is to randomly select several data objects in the data space as the initial cluster centers. The reason for this is that by randomly selecting the initial cluster centers, it can be ensured that the algorithm will not be affected by the position of a specific initial cluster center, thereby avoiding falling into a local optimal solution. By randomly selecting data objects in the data space as the initial cluster centers, the algorithm can have a certain degree of randomness, which helps to explore different aspects of the data, and can increase the robustness and reliability of the algorithm, and improve the quality of the final clustering results. Randomly selecting data objects as initial cluster centers is a common and effective initialization method.

[0067] S33, initializing clusters: calculating the Euclidean distance between all data objects and the initial cluster center, and dividing each data object into the initial cluster center with the smallest Euclidean distance to form an initial cluster;

[0068] S34, updating the cluster center: calculating the average value of the data objects of each initial cluster, and taking the average value as the new cluster center;

[0069] S35. Determine the final cluster: repeatedly calculate the Euclidean distance between all data objects and the new cluster center, divide each data object into the new cluster center with the smallest Euclidean distance to form a new cluster; calculate the average value of each new cluster as the new cluster center again, and determine the final cluster after the new cluster center no longer changes, and determine the corresponding working mode according to the combination of started applications in each final cluster.

[0070] Furthermore, in step S31, the normalization process is calculated using the following formula:

[0071]

[0072] Where Y i is the normalized data sample of the ith launched application; K i is the i-th launched application data sample; K max Indicates the maximum value of all launched application data samples; K min Indicates the minimum value of all launched app data samples.

[0073] Furthermore, in step S33, the Euclidean distance is calculated by the following formula:

[0074]

[0075] In the formula, d(x,C i ) represents the Euclidean distance function; x is the normalized data object; C irepresents the i-th cluster center; n is the number of samples in the data set; x j Represents the data object of the jth variable in the data set; C ij represents the i-th cluster center of the j-th variable.

[0076] The time setting module is used to input the current working mode into the time setting model, output the predicted screen usage frequency, and set the screen saver activation time according to the predicted screen usage frequency;

[0077] In this embodiment, different screen working modes have their corresponding screen usage frequencies. By establishing the relationship between the working mode and the screen usage frequency, the operation intervals and durations in different working modes can be predicted, thereby providing a good reference for the opportunity to activate the screen saver.

[0078] Furthermore, the time setting model is configured as a random forest model, including the following construction steps:

[0079] T1. Data preparation: prepare a data set containing explanatory variables and response variables, the explanatory variable is the working mode, and the response variable is the screen usage frequency;

[0080] T2. Dataset division: Divide the collected data set into training set and test set, where 70% of the data samples in the data set are used as the training set and 30% of the data samples are used as the test set;

[0081] T3, random sampling: randomly extract several explanatory variables and data samples from the training set, and construct multiple different training sets with replacement;

[0082] T4. Build a decision tree: For each randomly sampled training set, build a decision tree model;

[0083] Furthermore, in step T4, the decision tree model is configured as a CART model.

[0084] Classification and Regression Trees (CART) is a decision tree algorithm used for classification and regression analysis. CART recursively divides the data set into smaller subsets, selects the best features and split points at each node to minimize the Gini impurity (for classification) or the mean square error (for regression), and finally generates a tree for prediction. The CART model is easy to understand and interpretable, and can handle nonlinear relationships and high-dimensional data. By repeatedly dividing the data set, CART can effectively capture complex patterns in the data and is also robust to missing values ​​and outliers. In a random forest, each decision tree is built based on the Classification and Regression Tree (CART) algorithm. Specifically, each tree in a random forest is an independent CART decision tree that randomly selects features for modeling. Random forests make the final decision by integrating the prediction results of multiple CART decision trees, thereby improving the accuracy and generalization ability of the overall model. Each tree is built for a different random subset of the training data, and only one random subset of features is considered when selecting the best feature at each node, which makes the random forest have a certain degree of randomness and reduces the risk of overfitting. Therefore, the random forest takes advantage of the CART decision tree, combines the prediction results of multiple trees, improves the stability and prediction ability of the model, and has achieved widespread success in practical applications.

[0085] T5. Integrated decision tree: Integrate multiple decision tree models into a random forest model and use the average value to make the final prediction;

[0086] It should be noted that in a random forest, each decision tree is built based on a different training data set and feature subset, and has a certain degree of randomness. The final prediction result can be determined by a voting mechanism or by taking the average. In classification problems, a majority vote can be used to select the category with the most votes as the final prediction result; in regression problems, the prediction results of multiple trees can be averaged as the final output. By integrating multiple decision trees into a random forest model, the risk of overfitting can be effectively reduced and the robustness and accuracy of the model can be improved.

[0087] T6. Model evaluation: Use evaluation indicators to evaluate the prediction performance of the random forest model on the test set and determine the final model with good prediction performance.

[0088] Furthermore, in step T6, the evaluation index adopts accuracy, precision, recall or F1 value.

[0089] In this embodiment, the accuracy rate is the ratio of the number of samples correctly predicted by the model to the total number of samples, which is one of the most commonly used evaluation indicators. The calculation formula is: Accuracy Rate = (TP+TN) / (TP+TN+FP+FN), where TP represents true positive examples, TN represents true negative examples, FP represents false positive examples, and FN represents false negative examples.

[0090] Precision measures how many of the positive examples predicted by the model are truly positive examples. It is an important indicator for evaluating the accuracy of model predictions. The calculation formula is: Precision = TP / (TP+FP).

[0091] The recall rate measures the ratio of the number of positive examples that the model can correctly predict to the actual number of positive examples, also known as the recall rate. The calculation formula is: Recall rate = TP / (TP+FN).

[0092] The F1 value is the harmonic mean of precision and recall, which comprehensively considers the accuracy and comprehensiveness of the model. The higher the F1 value, the better the balance between precision and recall. The calculation formula is: F1 = 2×(precision×recall) / (precision+recall).

[0093] Furthermore, the time setting module, after selecting to set the time, stores the time setting in a non-volatile memory of the device so that the setting is maintained when the same working mode is started next time.

[0094] The no-operation detection module is used to monitor whether the current screen is being operated, and to use a timer to start calculating the no-operation time when no operation is performed;

[0095] In this embodiment, in order to monitor whether the current screen is in operation and calculate the inactivity time when there is no operation, a simple monitoring system can be designed. The system first determines whether there is activity by monitoring the user's input events (such as mouse movement, keyboard input, etc.). If there is activity, the timer will be reset to zero, indicating that the user is operating. On the contrary, when no input is detected within the set time range, the system will start timing and gradually increase the inactivity time. If the inactivity time reaches the preset threshold, the system will trigger the corresponding processing, such as starting the screen saver. To achieve this function, the program needs to create a loop to monitor user activity and maintain a timer to record the duration of inactivity. This process can be implemented in pseudo code, using a simple thread to continuously check the status and reset the timer when the user is active. This design not only improves the effectiveness of the system, but also helps protect the screen from burn-in, while providing users with a good user experience, ensuring that the system will not remain active in an inactive state, thereby improving the safety and energy saving of the device.

[0096] Furthermore, the no-operation detection module resets the timer when detecting that the user starts an operation.

[0097] The screen saver activation module is used to automatically activate the screen saver when the screen is not operated for a period exceeding the screen saver activation time;

[0098] Furthermore, the screen saver displays a black screen and a clock UI, and the clock UI displays the current time and date in a format consistent with the system settings and moves every 2 seconds.

[0099] In this embodiment, the screen saver function is designed to display a black screen and a clock user interface (UI) on the screen, which is specifically implemented as follows:

[0100] 1) Background setting: When the screen saver is activated, the screen background will turn into a black background to reduce energy consumption and prevent screen burn-in.

[0101] 2) Clock UI display: The core part of the black screen is the clock UI, which displays the current time and date. The format of the time and date should be consistent with the user's system settings, such as 24-hour or 12-hour format, to ensure that it matches the user's system habits.

[0102] 3) Dynamic movement: To prevent residual images caused by fixed screen pixels, the clock UI will move on the screen every 2 seconds. The movement method can be random position, smooth animation movement, or follow a specific path, such as along the diagonal or from left to right, to ensure that the clock is always visible and not prone to residual images.

[0103] 4) Setting options: Users can choose whether to enable the clock movement function, adjust the movement frequency, and even customize the font, color and size of the clock in the screen saver settings to enhance the personalized experience.

[0104] 5) Exit conditions: The screen saver can be automatically exited by any input signal (such as keyboard or mouse activity) and restore the normal desktop interface.

[0105] The screen saver exit module is used to exit the screen saver mode when it is detected that the user touches the screen or uses the remote controller.

[0106] Furthermore, the screen saver exit module restores the previous display content after exiting the screen saver.

[0107] Beneficial effects of the present invention:

[0108] (1) By identifying the started applications of the current screen system, the working mode of the current screen is determined; the current working mode is input into the time setting model, the predicted screen usage frequency is output, and the screen saver activation time is set according to the predicted screen usage frequency; when the screen is not operated for a time exceeding the screen saver activation time, the screen saver is automatically activated. The present invention solves the problem that it is difficult to coordinate the relationship between the time opportunity of automatically activating the screen saver and the screen usage frequency requirements of different working modes in the prior art, resulting in poor image retention control effect.

[0109] (2) By collecting screen work data of historical periods, the screen work data includes launched applications and screen usage frequency, and using a cluster analysis method to classify the launched applications, the screen work data is divided into several work modes with the same or similar launched application combination characteristics, thereby improving the efficiency of identifying the current work mode.

[0110] (3) Construct a random forest model to quantify the relationship between different working modes and their screen usage frequency. By monitoring the screen usage frequency of different working modes, the screen saver activation time is set to meet user needs and improve user experience.

[0111] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An automatic screen saver activation system for electronic whiteboard large-screen equipment, characterized by: It includes an application identification module, a working mode analysis module, a time setting module, a no-operation detection module, a screen saver activation module and a screen saver exit module, wherein the application identification module, the working mode analysis module, the time setting module, the no-operation detection module, the screen saver activation module and the screen saver exit module are connected in communication, wherein: The application identification module is used to identify the started applications of the current screen system; The working mode analysis module is used to input the started application into a preset working mode analysis model and output the current working mode; the working mode analysis model includes the following construction steps: S1. Collect screen work data in historical periods, where the screen work data includes started applications and screen usage frequency, where the screen usage frequency includes operation duration and interval between adjacent operations; S2, converting each started application type into numerical data; S3, using a cluster analysis method to classify the launched applications, and dividing the screen work data into several work modes with the same or similar launched application combination characteristics; The time setting module is used to input the current working mode into the time setting model, output the predicted screen usage frequency, and set the screen saver activation time according to the predicted screen usage frequency; the time setting model is configured as a random forest model; The no-operation detection module is used to monitor whether the current screen is being operated, and to use a timer to start calculating the no-operation time when no operation is performed; The screen saver activation module is used to automatically activate the screen saver when the screen is not operated for a period exceeding the screen saver activation time; The screen saver exit module is used to exit the screen saver mode when it is detected that the user touches the screen or uses the remote controller.

2. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: The working modes include teaching mode, meeting mode, display mode, leisure mode and editing mode.

3. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: In step S3, the cluster analysis method is configured as a K-means clustering method, including the following steps: S31, normalization processing: normalizing the started application data variables; S32, initializing cluster centers: randomly selecting several data objects in the data space as initial cluster centers; S33, initializing clusters: calculating the Euclidean distance between all data objects and the initial cluster center, and dividing each data object into the initial cluster center with the smallest Euclidean distance to form an initial cluster; S34, updating the cluster center: calculating the average value of the data objects of each initial cluster, and taking the average value as the new cluster center; S35. Determine the final cluster: repeatedly calculate the Euclidean distance between all data objects and the new cluster center, divide each data object into the new cluster center with the smallest Euclidean distance to form a new cluster; calculate the average value of each new cluster as the new cluster center again, and determine the final cluster after the new cluster center no longer changes, and determine the corresponding working mode according to the combination of started applications in each final cluster.

4. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 3, characterized in that: In step S31, the normalization process is calculated using the following formula: Where Y i is the normalized data sample of the ith launched application; K i is the i-th launched application data sample; K max Indicates the maximum value of all launched application data samples; K min Indicates the minimum value of all launched app data samples.

5. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 3 is characterized by: In step S33, the Euclidean distance is calculated using the following formula: In the formula, d(x,C i ) represents the Euclidean distance function; x is the normalized data object; C i represents the i-th cluster center; n is the number of samples in the data set; x j Represents the data object of the jth variable in the data set; C ij represents the i-th cluster center of the j-th variable.

6. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: The random forest model includes the following construction steps: T1. Data preparation: prepare a data set containing explanatory variables and response variables, the explanatory variable is the working mode, and the response variable is the screen usage frequency; T2. Dataset division: Divide the collected data set into training set and test set, where 70% of the data samples in the data set are used as the training set and 30% of the data samples are used as the test set; T3, random sampling: randomly extract several explanatory variables and data samples from the training set, and construct multiple different training sets with replacement; T4. Build a decision tree: For each randomly sampled training set, build a decision tree model; T5. Integrated decision tree: Integrate multiple decision tree models into a random forest model and use the average value to make the final prediction; T6. Model evaluation: Use evaluation indicators to evaluate the prediction performance of the random forest model on the test set and determine the final model with good prediction performance.

7. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 6, characterized in that: In step T4, the decision tree model is configured as a CART model.

8. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 6, characterized in that: In step T6, the evaluation index adopts accuracy, precision, recall or F1 value.

9. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: The time setting module, after selecting to set the time, stores the time setting in the non-volatile memory of the device so that the setting is maintained when the same working mode is started next time.

10. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: The no-operation detection module resets the timer when detecting that the user starts an operation.

11. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: The screen saver displays a black screen and a clock UI. The clock UI displays the current time and date in a format consistent with the system settings and moves every two seconds.

12. The automatic screen saver activation system for electronic whiteboard large screen device according to claim 1, characterized in that: The screen saver exit module restores the previous display content after exiting the screen saver.