Screen display information security control method and system

Abstract

The application relates to the technical field of information security control, and discloses a screen display information security control method and system. The method comprises the following steps: continuously collecting image data around a protected screen by a camera; a core computing unit identifies suspected shooting behavior based on the data; alignment stability parameters are calculated within a protection trigger inhibition window to determine real shooting behavior, and then the anti-peeping protection screen is switched to a uniform code printing anti-peeping state; during the protection, shooting behavior history information is recorded; when the shooting behavior disappears, the termination credibility is calculated based on the history information, and it is determined whether to release the anti-peeping protection according to the termination credibility. The method can accurately identify effective shooting behavior, dynamically guarantee the screen information security, balance the protection reliability and the use experience, and is suitable for high-sensitive information display scenes.

Description

Technical Field

[0001] This application relates to the field of information security control technology, specifically to a screen display information security control method and system. Background Technology

[0002] In highly sensitive scenarios with extremely high information security requirements, such as classified government meetings, financial decision-making meetings, and core technology reviews for enterprises, preventing the leakage of information displayed on screens is a crucial aspect of ensuring information security. With the widespread use of electronic surveillance devices, the risk of unauthorized recording and leakage of information displayed on screens continues to increase, highlighting the growing importance of related protective technologies.

[0003] While existing screen display information leakage prevention solutions have seen some application, several problems remain to be solved in engineering practice. First, the protection trigger mechanism is overly sensitive, immediately activating anti-spy protection upon detecting only suspected filming action, without determining whether the action qualifies for clear imaging. This leads to frequent triggering of protection by non-filming behaviors such as raising a hand or briefly checking electronic devices, causing frequent screen obstruction and severely impacting the continuity of meetings and other scenarios. Second, the anti-spy control method is simplistic, often employing binary control logic of "whether to blur or not," lacking a dynamic adjustment mechanism that matches the level of filming risk. It cannot adjust the protection strength based on differences in risk such as filming distance, alignment stability, and duration, resulting in excessive protection redundancy in low-risk filming scenarios, affecting the normal display experience. Third, the protection deactivation condition is simplistic, typically deactivating immediately upon detecting no filming action, failing to consider the possibility that the filmer might use evasive tactics such as briefly lowering the device or repeatedly probing to complete a sneaky shot the instant protection is deactivated, leading to insufficient protection reliability. Existing technologies cannot meet the refined and highly reliable information security protection requirements of highly sensitive scenarios. Summary of the Invention

[0004] The purpose of this application is to provide a screen display information security control method and system to solve the problems mentioned in the background art.

[0005] According to one aspect of this application, a screen display information security control method is provided, applied to a system including an analysis camera, a core computing unit, and an intelligent power-on privacy screen, the method comprising:

[0006] The analysis camera continuously collects image data of the area surrounding the protected screen.

[0007] The core computing unit identifies, based on the image data, whether there is any suspected filming behavior pointing at the protected screen;

[0008] If the suspected shooting behavior is detected, the core computing unit calculates the alignment stability parameters of the device corresponding to the suspected shooting behavior based on continuous image data within a preset protection trigger suppression window.

[0009] Within the protection trigger suppression window, if the alignment stability parameter does not reach the preset imaging threshold, the privacy protection will not be triggered; if the alignment stability parameter reaches or exceeds the preset imaging threshold, it will be determined as a real shooting behavior, and the smart power-on privacy protection screen will be controlled to switch from high-transparency standby state to uniform coding privacy state.

[0010] During the uniform blurring and privacy protection state, the core computing unit records historical information about the actual shooting behavior;

[0011] When the actual shooting behavior disappears, the core computing unit calculates the credibility that the actual shooting behavior has ended based on the historical information;

[0012] If the credibility does not reach the preset release threshold, the uniform coding anti-spy state is maintained; if the credibility reaches or exceeds the preset release threshold, the smart power-on anti-spy protection screen is controlled to return to the high-transparency standby state.

[0013] Preferably, calculating the alignment stability parameter includes: tracking the position of the device relative to the protected screen in continuous image data; calculating the magnitude of the alignment angle change of the device based on the position; calculating the duration of continuous alignment of the device based on the timestamps of the image data; and calculating the alignment stability parameter by weighted summation based on the magnitude of the alignment angle change and the duration.

[0014] Preferably, after switching to uniform coding anti-spy state, the method further includes: the core computing power unit assessing the shooting risk level based on the shooting distance, alignment angle stability and duration of the actual shooting behavior; the core computing power unit generating protection strength control parameters based on the shooting risk level; and adjusting the control parameters of the smart power-on anti-spy protection screen according to the protection strength control parameters to dynamically adjust the intensity of uniform coding.

[0015] Preferably, the assessment of the shooting risk level includes: calculating the shooting distance based on the image data and the parameters of the analysis camera; obtaining the range of change in the alignment angle of the actual shooting behavior; calculating the duration of the actual shooting behavior; calculating a risk level assessment value by weighted summation based on the shooting distance, the range of change in the alignment angle, and the duration; and determining the shooting risk level according to the preset range in which the risk level assessment value falls.

[0016] Preferably, adjusting the control parameters of the intelligent power-on privacy screen to dynamically adjust the intensity of uniform coding includes:

[0017] The shooting risk level includes a high-risk level and a low-risk level; the high-risk level corresponds to a first control parameter range, and the low-risk level corresponds to a second control parameter range, wherein the first control parameter range is greater than the second control parameter range.

[0018] Preferably, the historical information includes at least: the cumulative duration of the actual shooting behavior, the number of interruptions, and the duration of each interruption.

[0019] Preferably, calculating the credibility that the actual shooting behavior has ended includes: obtaining the duration of the disappearance of the actual shooting behavior; obtaining the cumulative duration and number of interruptions in the historical information; and calculating the credibility by weighted summation based on the disappearance duration, the cumulative duration, and the number of interruptions.

[0020] Preferably, before acquiring image data, the method further includes: the core computing unit loading a shooting behavior recognition model; establishing a data connection with the analysis camera and a control connection with the intelligent power-on privacy screen; and controlling the intelligent power-on privacy screen to enter a high-transparency standby state.

[0021] In another aspect, this application also provides a screen display information security control system, comprising:

[0022] The camera is used to continuously collect image data of the area surrounding the protected screen.

[0023] The intelligent power-on privacy screen is fitted onto the display surface of the screen being protected and can switch between a high-transparency standby state and a uniform coding privacy state in response to control commands.

[0024] The core computing unit, which is communicatively connected to the analysis camera and the intelligent power-on privacy screen, is used for:

[0025] Receive image data acquired by the analysis camera;

[0026] Based on the image data, identify whether there is any suspected filming behavior pointing at the protected screen;

[0027] If the suspected shooting behavior is detected, the alignment stability parameter of the device corresponding to the suspected shooting behavior is calculated based on continuous image data within a preset protection trigger suppression window.

[0028] Within the protection trigger suppression window, if the alignment stability parameter does not reach the preset imaging threshold, the privacy protection will not be triggered; if the alignment stability parameter reaches or exceeds the preset imaging threshold, it will be determined as a real shooting behavior, and a first control command will be sent to the smart power-on privacy protection screen to switch it from high-transparency standby state to uniform coding privacy state.

[0029] While the smart power-on privacy screen is in a uniformly coded privacy state, it records historical information about the actual shooting behavior;

[0030] When the actual shooting behavior disappears, the credibility of the actual shooting behavior being terminated is calculated based on the historical information;

[0031] If the credibility does not reach the preset release threshold, the system continues to send a status maintenance command to the smart power-on privacy screen; if the credibility reaches or exceeds the preset release threshold, the system sends a second control command to the smart power-on privacy screen to restore it from the uniform coding privacy state to the high transparency standby state.

[0032] Preferably, when calculating the alignment stability parameter, the core computing unit is specifically used to: track the position of the device relative to the protected screen in continuous image data; calculate the alignment angle change amplitude of the device based on the position; calculate the duration of continuous alignment of the device based on the timestamp of the image data; and calculate the alignment stability parameter by weighted summation based on the alignment angle change amplitude and the duration.

[0033] This application also provides a computer device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the screen display information security control method as described above.

[0034] In another aspect, this application provides a computer-readable storage medium having stored thereon computer program instructions that can be executed by a processor to implement the screen display information security control method described above.

[0035] Another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the screen display information security control method as described above.

[0036] This application achieves precise control over the entire process of preventing information leakage from the screen display by analyzing the collaborative work of the camera, core computing unit, and intelligent power-on anti-spy protection screen. Through a shooting alignment stability assessment and protection trigger suppression mechanism, it effectively solves the problem of false triggering in existing technologies, significantly reducing the false trigger rate and ensuring continuity in scenarios such as meetings. Through a shooting risk level assessment and dynamic adjustment mechanism for anti-spy strength, it achieves precise matching between protection strength and risk level, avoiding protection redundancy in low-risk scenarios and balancing information security and display experience. Through a trusted determination mechanism for protection disarming, it effectively resists probing spying attempts and improves the reliability of information protection in highly confidential scenarios. Attached Figure Description

[0037] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0039] Figure 1 A schematic diagram of a screen display information security control method provided in an embodiment of this application;

[0040] Figure 2 This is a schematic diagram of the alignment stability parameter calculation process provided in an embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the shooting risk level assessment process provided in the embodiments of this application;

[0042] Figure 4 This is a schematic diagram of the protection removal confidence calculation process provided in the embodiments of this application;

[0043] Figure 5 This is a schematic diagram of a screen display information security control system provided in an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] It should be noted that all user information (including but not limited to user device information, user personal information, object information corresponding to device usage data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, device usage data, etc.) involved in all embodiments of this application are information and data authorized by the user or fully authorized by all parties.

[0046] This method is applicable to display scenarios involving classified information, sensitive data, or situations where it is unsuitable to be photographed or intercepted, and is particularly suitable for locations with high information security requirements, such as classified government meetings, internal decision-making meetings of financial institutions, core technology reviews of enterprises, and classified command and dispatch centers. Implementation of this method typically requires a system comprising an analysis camera, a core computing unit, and an intelligent power-on privacy screen. The analysis camera continuously collects image data from the area surrounding the protected screen. The core computing unit handles core tasks such as image data processing, behavior recognition, parameter calculation, and control command issuance. The intelligent power-on privacy screen is fitted onto the display surface of the protected screen and can switch between a high-transparency standby state and a uniformly masked privacy state. Meeting the above hardware configuration and scenario requirements allows for the deployment and implementation of this method.

[0047] The implementation process of the screen display information security control method described in this application will be described in detail below with reference to specific embodiments. It should be noted that this embodiment is only used to explain this application and is not intended to limit the scope of protection of this application. Conventional adjustments or substitutions of each step by those skilled in the art without departing from the concept of this application should be included in the protection scope of this application.

[0048] like Figure 1 As shown in the diagram, this application discloses a screen display information security control method, which includes the following steps:

[0049] S1, continuously collect image data of the area surrounding the protected screen through the analysis camera;

[0050] S2, the core computing unit identifies whether there is a suspected shooting behavior pointing at the protected screen based on the image data;

[0051] S3, if the suspected shooting behavior is detected, the core computing power unit calculates the alignment stability parameters of the device corresponding to the suspected shooting behavior based on continuous image data within a preset protection trigger suppression window;

[0052] S4, within the protection trigger suppression window, if the alignment stability parameter does not reach the preset imaging threshold, the privacy protection will not be triggered; if the alignment stability parameter reaches or exceeds the preset imaging threshold, it will be determined as a real shooting behavior, and the intelligent power-on privacy protection screen will be controlled to switch from high-transparency standby state to uniform coding privacy state.

[0053] S5, during the uniform coding anti-peeping state, the core computing unit records historical information of the actual shooting behavior;

[0054] S6, when the actual shooting behavior disappears, the core computing power unit calculates the credibility that the actual shooting behavior has been terminated based on the historical information;

[0055] S7. If the credibility does not reach the preset release threshold, the uniform coding anti-spy state is maintained; if the credibility reaches or exceeds the preset release threshold, the smart power-on anti-spy protection screen is controlled to return to the high-transparency standby state.

[0056] In some embodiments, system initialization operations can be completed before analyzing the image data acquired by the camera. Specifically, the core computing unit first loads the shooting behavior recognition model, which can be a convolutional neural network structure, including an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The input layer receives image data, the convolutional layer extracts low-level features such as edges and textures from the image through convolutional kernels, the pooling layer performs dimensionality reduction on the output features of the convolutional layer, retaining key feature information, the fully connected layer fuses the dimensionality-reduced features and maps them to the classification space, and the output layer uses the Softmax activation function to output the probability values ​​of whether a handheld electronic device exists and whether the electronic device is pointing at the protected screen.

[0057] Optionally, the training process of the model is based on a dataset of sample images containing a large number of different scenes, angles, and lighting conditions. The sample images include various situations such as handheld electronic devices pointing at the screen, handheld electronic devices not pointing at the screen, and no electronic devices. Each sample image is labeled with a corresponding category label. The model is trained iteratively through the stochastic gradient descent algorithm, and the model parameters are continuously adjusted until the recognition accuracy of the model on the validation set reaches the preset requirements.

[0058] After the model is loaded, the core computing unit establishes a data connection with at least one set of analysis cameras. This data connection can be achieved via wired Ethernet, wireless LAN, or other methods to ensure that the image data collected by the analysis cameras can be transmitted to the core computing unit in real time and completely. Simultaneously, the core computing unit establishes a control connection with the intelligent power-on privacy screen. This control connection can be achieved via serial port, bus, or other communication methods, and is used to subsequently issue control commands such as status switching and parameter adjustments to the intelligent power-on privacy screen.

[0059] The core computing unit sends control commands to the intelligent power-on privacy screen via the control connection, controlling the intelligent power-on privacy screen to enter a high-transparency standby state. In this state, the intelligent power-on privacy screen has high light transmittance, which does not affect the normal display of the content on the protected screen, ensuring the normal conduct of meetings, reviews and other scenarios.

[0060] In some embodiments, after the system completes initialization and connection establishment in step S1, the analysis camera begins to continuously collect image data of the area surrounding the protected screen. The shooting angle and shooting range of the analysis camera can be adjusted according to the size of the protected screen, its installation location, and the usage scenario to ensure comprehensive coverage of the area around the protected screen where shooting activities may occur. The collected image data includes continuous frame video data, timestamp information corresponding to each frame, and spatial location information of the detected target in the image. The continuous frame video data provides continuous image sequence support for subsequent shooting behavior recognition, device tracking, and parameter calculation. The timestamp information is used to record the time sequence of image acquisition, providing a basis for calculating time-related parameters such as duration and disappearance time. The spatial location information of the detected target in the image is obtained through a target detection algorithm and is used to locate the position and movement trajectory of the suspected shooting device.

[0061] After analyzing the image data captured by the camera, it is transmitted to the core computing unit in chronological order. A data verification mechanism is employed during transmission to ensure data integrity and accuracy, preventing data loss or errors from affecting subsequent processing. Upon receiving the image data, the core computing unit stores it in a preset cache and performs preliminary preprocessing, including image denoising, image enhancement, and image size normalization. Image denoising uses a Gaussian filtering algorithm to remove Gaussian noise from the image. Image enhancement improves image quality by adjusting brightness and contrast. Image size normalization adjusts images of different resolutions to a uniform size for processing by the behavior recognition model.

[0062] In some embodiments, for step S2, the core computing unit identifies whether there is a suspected shooting behavior pointing at the protected screen based on the preprocessed image data. This identification process can be divided into two steps. First, the core computing unit identifies whether there is a handheld electronic device in the image data through a shooting behavior recognition model. Specifically, the shooting behavior recognition model extracts features from the preprocessed image, matches the extracted features with the handheld electronic device features learned during training, calculates the matching degree, and if the matching degree is greater than a preset device recognition threshold, it determines that there is a handheld electronic device in the image data and outputs the bounding box coordinates of the handheld electronic device in the image to determine its spatial location.

[0063] After identifying the handheld electronic device, the system further determines whether the device is located in a spatial region that might be pointing towards the protected screen. Specifically, the core computing unit sets a range of spatial regions that might point towards the protected screen based on the screen's position coordinates in the image. This range can be preset based on the screen's size, the camera's shooting parameters, and the shooting angle. For example, a cone-shaped spatial region can be set with the center point of the protected screen as its vertex. By calculating the relationship between the handheld electronic device's center point coordinates, the lens's orientation angle, and the preset spatial region, the system determines whether the electronic device is within that spatial region.

[0064] If the center point coordinates of the electronic device are located within a preset spatial area, and the angle between the lens of the electronic device and the center line of the preset spatial area is less than a preset angle threshold, then the handheld electronic device is determined to be in a spatial area that may be pointing at the protected screen, i.e., suspected shooting behavior is identified; if the handheld electronic device is not identified, or if the handheld electronic device is identified but the device is not in a spatial area that may be pointing at the protected screen, then it is determined that there is no suspected shooting behavior, and the core computing unit continues to receive and analyze the image data transmitted by the camera and repeats the identification operation of this step.

[0065] In some embodiments, step S3 involves calculating alignment stability parameters and determining protection triggers. This step aims to address the technical problems in the prior art where protection triggers are overly "motion-sensitive," lack effective imaging determination, and are prone to false triggers. By calculating alignment stability parameters within a preset protection trigger suppression window, protection is only triggered when the parameter reaches or exceeds a preset imaging threshold, effectively distinguishing between valid shooting and brief, non-imaging actions, reducing false trigger rates, and ensuring continuity in scenarios such as meetings. The principle is that the shooting device needs to maintain stable alignment for a certain period of time to form a clear image. By evaluating alignment stability, it is possible to accurately determine whether the shooting action meets the conditions for effective imaging.

[0066] Optionally, if a suspected shooting behavior is detected, the core computing unit activates a preset protection trigger suppression window. The duration of the preset protection trigger suppression window can be configured according to the actual application scenario, for example, it can be configured to a few seconds. The setting principle is to be able to fully evaluate the alignment stability of the suspected shooting behavior, ensure that there is enough time to determine whether the behavior has the conditions to form a clear image, and at the same time avoid the effective shooting behavior not being protected in time due to the window duration being too long.

[0067] Within the protection trigger suppression window, the core computing unit calculates the alignment stability parameters of the device corresponding to the suspected shooting behavior based on continuous image data. (Please refer to...) Figure 2 , Figure 2This is a schematic diagram illustrating the alignment stability parameter calculation process provided in an embodiment of this application. The specific calculation process includes:

[0068] In step S201, the suspected camera device is continuously tracked, and its position coordinate sequence is recorded in multiple consecutive image frames. The core computing unit uses a target tracking algorithm to track the position of the suspected camera device relative to the protected screen within continuous image data. Based on the bounding box coordinates of the suspected camera device in the current frame, combined with the device's position information and motion trend in the previous frame, the algorithm predicts the device's possible position in the current frame. Then, a template matching algorithm searches near the predicted position to determine the device's accurate position coordinates in the current frame, thus achieving continuous tracking of the suspected camera device and recording its position coordinate sequence in multiple consecutive image frames.

[0069] In S202, the alignment angle change range of the device is calculated based on the tracked position coordinate sequence. First, the center point of the protected screen is set as the reference point. Based on the size of the protected screen and its position coordinates in the image, the coordinate value of the reference point in the image is calculated. For each frame in a continuous image frame, based on the position coordinates of the suspected shooting device in that frame and the coordinates of the reference point, the vector pointing from the device lens to the reference point is calculated. Then, the angle between this vector and a preset reference vector (e.g., a vector perpendicular to the plane of the protected screen) is calculated. This angle is the alignment angle of the device in that frame. The absolute values ​​of the alignment angle differences between two adjacent frames in a continuous image are summed to obtain the total change in alignment angle. This total change is then divided by the number of consecutive frames to obtain the alignment angle change range. The smaller the alignment angle change range, the higher the alignment stability of the device.

[0070] In S203, the duration of continuous alignment of the device is calculated based on the timestamps of the image data. The core computing unit records the starting timestamp from the moment it first identifies a suspected camera device in a spatial area that might be pointing at the protected screen and begins stable tracking. Within the protection trigger suppression window, if the device remains in the spatial area that might be pointing at the protected screen in consecutive frames and the change in alignment angle is less than a preset stable angle threshold, the time is continuously accumulated, and this accumulated time is the duration of continuous alignment. If the device leaves the spatial area that might be pointing at the protected screen in a certain frame, or the change in alignment angle exceeds the preset stable angle threshold, the accumulation is paused until the device meets the conditions again, and then continues accumulating, ultimately obtaining the total duration of continuous alignment of the device within the protection trigger suppression window.

[0071] In S204, based on the magnitude and duration of the alignment angle change, the alignment stability parameter is calculated by weighted summation, and the calculation formula is as follows:

[0072]

[0073] in, This represents the alignment stability parameter. This indicates the range of change in the alignment angle. Indicates the duration of continuous alignment of the equipment. and These are the weighting coefficients for the magnitude and duration of the alignment angle change, respectively. and The values ​​of are all in the range [0,1], and satisfy . The settings can be adjusted based on the degree of influence of the two factors on alignment stability in the actual application scenario. For example, in scenarios where high stability of the alignment angle is required, the following settings can be configured: Greater than .

[0074] Within the protection trigger suppression window, the core computing unit continuously updates the alignment stability parameters and compares them with the preset imaging threshold. The preset imaging threshold is a critical value for determining whether the shooting behavior meets the conditions for forming a clear image. It can be obtained through a large amount of experimental data. For example, by collecting the image sharpness obtained by the shooting device under different alignment angle changes and different durations, the range of alignment stability parameters corresponding to forming a clear image can be determined, and the lower limit of this range can be set as the preset imaging threshold.

[0075] If the alignment stability parameter does not reach the preset imaging threshold within the protection trigger suppression window, the suspected shooting behavior is determined not to constitute valid shooting and will not trigger anti-spy protection. The core computing unit continues to receive and analyze the image data transmitted by the camera and repeats the subsequent identification and evaluation process. If the alignment stability parameter reaches or exceeds the preset imaging threshold within the protection trigger suppression window, it is determined to be a real shooting behavior. The core computing unit sends a state switching command to the intelligent power-on anti-spy protection screen, controlling the intelligent power-on anti-spy protection screen to switch from high-transparency standby state to uniform coding anti-spy state. The uniform coding anti-spy state is achieved by forming a uniformly distributed blocking pattern on the anti-spy protection screen, which can physically block the screen display content and prevent the shooting device from obtaining valid image information.

[0076] In some embodiments, step S4 involves assessing the shooting risk level and dynamically adjusting the anti-spying strength. This step addresses the technical problems in existing technologies, such as the simplistic anti-spying methods, the lack of a mechanism for matching protection strength with risk level, and excessive redundancy in protection for low-risk shooting behaviors. By assessing the shooting risk level based on the characteristics of actual shooting behaviors and dynamically adjusting the anti-spying strength based on the risk level, the system ensures screen information security while also considering the normal display experience. The principle is that shooting behaviors with different risk levels pose different threats to screen information leakage. High-risk shooting behaviors require high-strength protection to completely prevent information leakage, while low-risk shooting behaviors can appropriately reduce the protection strength to minimize interference with normal viewing of screen content.

[0077] After the smart power-on privacy screen switches to uniform pixelation privacy mode, the core computing unit begins to assess the risk level of the shooting. Please refer to [link / reference]. Figure 3 , Figure 3 This is a schematic diagram of the shooting risk level assessment process provided in the embodiments of this application.

[0078] First, in S301, the shooting distance is calculated based on image data and the parameters of the analysis camera, including known parameters such as focal length and sensor size. The core computing unit obtains the pixel size of the actual shooting device in the image through a target detection algorithm. Combined with the focal length and sensor size of the analysis camera, the distance between the shooting device and the analysis camera is calculated based on the principle of similar triangles. Then, combined with the preset distance and relative position relationship between the analysis camera and the protected screen, the shooting distance between the shooting device and the protected screen is obtained through geometric calculation. The closer the shooting distance, the higher the probability of the shooting device obtaining a clear image, and the higher the shooting risk level.

[0079] In S302, the stability of the alignment angle of the actual shooting behavior is obtained; the stability of the alignment angle is characterized by the range of alignment angle change calculated in the previous steps. The smaller the range of alignment angle change, the higher the alignment stability of the shooting device and the higher the shooting risk level.

[0080] In S303, the duration of the actual shooting behavior is calculated; the core computing unit records the time interval from the moment it is determined to be an actual shooting behavior to the current moment. This time interval is the duration of the actual shooting behavior. The longer the duration, the higher the shooting risk level.

[0081] In S304, based on the shooting distance, the range of change in the alignment angle, and the duration calculated above, the risk level assessment value is calculated by weighted summation. The calculation formula is as follows:

[0082]

[0083] in, This indicates the risk level assessment value. Indicates the shooting distance. This indicates the range of change in the alignment angle. Indicates the duration of the actual filming action. , , These are the weighting coefficients for the three factors. , , The values ​​of are all in the range [0,1], and satisfy . The settings can be adjusted according to the degree of impact of various factors on shooting risks in the actual application scenario. For example, in scenarios where shooting distance has a significant impact on shooting clarity, the settings can be increased. The value of .

[0084] Optionally, the core computing unit presets multiple risk level assessment value ranges, each range corresponding to a shooting risk level. The shooting risk level includes at least a high-risk level and a low-risk level. For example, a risk level assessment value in the range [0, R1) can be classified as a low-risk level, and a value in the range [R1, +∞) can be classified as a high-risk level, where R1 is a preset risk level classification threshold that can be calibrated according to actual application requirements. The corresponding shooting risk level is determined based on the preset range in which the calculated risk level assessment value falls.

[0085] In one embodiment, the core computing unit generates protection strength control parameters based on the determined shooting risk level. Different shooting risk levels correspond to different protection strength control parameters. High risk levels correspond to a first control parameter range, and low risk levels correspond to a second control parameter range. The numerical range of the first control parameter range is greater than that of the second control parameter range. The protection strength control parameters correspond to the control parameters of the smart power-on privacy screen, such as the power supply. The larger the control parameter, the higher the coding density and contrast of the privacy screen, and the stronger the privacy protection.

[0086] The core computing unit sends the generated protection strength control parameters to the control interface of the intelligent power-on privacy screen. Based on these parameters, the control parameters of the intelligent power-on privacy screen are adjusted to dynamically regulate the intensity of the uniform masking. In high-risk shooting situations, the control parameters of the intelligent power-on privacy screen are in the first control parameter range, providing high-intensity uniform masking with high density and contrast, maximizing the obscuring of screen content and preventing the shooting device from obtaining a valid image. In low-risk shooting situations, the control parameters of the intelligent power-on privacy screen are in the second control parameter range, providing relatively reduced interference with uniform masking, with lower density and contrast, minimizing interference with normal screen viewing while ensuring that screen information is not leaked.

[0087] During the adjustment of the privacy protection intensity, the core computing unit continuously monitors the characteristic changes of the actual shooting behavior. If the shooting distance, alignment angle, or duration of the change changes, resulting in a change in the shooting risk level, the core computing unit promptly recalculates the risk level assessment value, determines the new shooting risk level, generates corresponding protection intensity control parameters, and adjusts the control parameters of the smart power-on privacy screen to ensure that the protection intensity and risk level always match. Simultaneously, it maintains uniform masking across the entire screen, ensuring privacy protection covers the entire screen area without any partial removal or partial transparency, thus preventing information leakage due to gaps in local protection.

[0088] In some embodiments, for step S5, the shooting behavior history and protection status are maintained. During the uniform masking anti-spying state, the core computing unit continuously monitors the actual shooting behavior and records the historical information of the actual shooting behavior. The historical information includes at least the cumulative duration of the actual shooting behavior, the number of interruptions, and the duration of each interruption.

[0089] Specifically, the core computing unit continuously analyzes the received image data to determine whether the actual shooting behavior continues. If, in multiple consecutive frames, the shooting device remains in the space area that may point to the protected screen, and the alignment stability parameter remains above the preset imaging threshold, then the shooting behavior is determined to continue, and the cumulative time is the cumulative duration of the actual shooting behavior. If, within a certain time period, the shooting device leaves the space area that may point to the protected screen, or the alignment stability parameter falls below the preset imaging threshold, then the shooting behavior is determined to be interrupted, and the start timestamp of the interruption is recorded. When the shooting device meets the conditions for the actual shooting behavior again, the end timestamp of the interruption is recorded, the difference between the two timestamps is calculated to obtain the duration of this interruption, and the interruption count is incremented by 1.

[0090] The aforementioned historical information can be stored in real time in the shooting behavior history buffer. The shooting behavior history buffer adopts a first-in-first-out storage mechanism to ensure that historical information within a preset time period can be stored, providing complete and accurate data support for subsequent reliable determination of protection removal. During the protection state maintenance, the core computing power unit continuously sends state maintenance commands to the intelligent power-on privacy screen to ensure that the privacy screen stably maintains the current uniform coding privacy state and avoids protection failure due to command interruption or equipment failure.

[0091] In some embodiments, step S6 involves determining the credibility of protection disarming and restoring the state. This step aims to address the technical problem in the prior art where the disarming conditions for spying are simple and easily circumvented by probing shots. By calculating the credibility of a genuine shooting action based on historical shooting behavior information, protection is only disarmed when the credibility reaches a preset disarming threshold. This effectively prevents the photographer from circumventing protection by briefly putting down the device and repeatedly probing, thus improving the reliability of information protection in highly confidential scenarios. The principle is that probing shooting behavior usually has the characteristic of recurring after interruption. By analyzing the historical record of shooting behavior, it is possible to accurately distinguish between genuinely terminated shooting behavior and the interrupted state of probing shooting behavior.

[0092] The core computing unit continuously monitors the status of real shooting behavior. When it detects that no real shooting behavior has occurred at the current moment, that is, the shooting device has moved away from the space area that may be pointing to the protected screen and the alignment stability parameter is lower than the preset imaging threshold, it does not immediately remove the protection. Instead, it calculates the credibility that the real shooting behavior has been terminated based on the historical information stored in the shooting behavior history record buffer.

[0093] Please see Figure 4 , Figure 4 A schematic diagram illustrating the protection disarming reliability calculation process provided in this application embodiment. Specifically, it includes:

[0094] In S401, the disappearance duration of the actual shooting behavior is obtained; the core computing unit records the time interval between the current moment and the last time the actual shooting behavior was detected, and this time interval is the disappearance duration of the actual shooting behavior.

[0095] In S402, the cumulative duration and number of interruptions of the actual shooting behavior are obtained from the historical information; the cumulative duration is the total duration of the shooting behavior in the historical record, and the number of interruptions is the total number of times the shooting behavior was interrupted in the historical record.

[0096] In S403, the credibility is calculated by weighted summation based on the disappearance duration, cumulative duration, and number of interruptions. The calculation formula is as follows:

[0097]

[0098] in, The credibility of indicating that the actual filming has ended. This indicates the duration of the actual filming activity. This indicates the cumulative duration of the actual filming activity. This indicates the number of interruptions in the actual filming process. and These are the weighting coefficients for the two factors, respectively. and The values ​​of are all in the range [0,1], and satisfy . The reliability assessment can be adjusted based on the influence of various factors on the reliability judgment in the actual application scenario. For example, in scenarios sensitive to the number of interruptions, the reliability can be increased. The value of .

[0099] The core computing unit compares the calculated credibility with a preset release threshold. The preset release threshold is the critical value for determining whether the shooting behavior has truly terminated. It can be obtained through experimental data calibration. For example, by statistically analyzing the credibility distribution of shooting behaviors that have truly terminated and those that have been interrupted during trial shooting, the minimum credibility of the truly terminated shooting behavior can be set as the preset release threshold. If the credibility does not reach the preset release threshold, it is determined that the shooting behavior may be a trial interruption. The system continues to maintain a uniform masking anti-spying state, and the core computing unit returns to the shooting behavior history record and protection state maintenance steps to continuously monitor the shooting behavior and record historical information. If the credibility reaches or exceeds the preset release threshold, it is determined that the actual shooting behavior has terminated. The core computing unit sends a power-off control command to the smart power-on anti-spying protection screen, controlling the smart power-on anti-spying protection screen to return to a high-transparency standby state, and the content of the protected screen is displayed normally again.

[0100] Optionally, after the smart power-on privacy screen returns to high-transparency standby mode, the core computing unit clears the shooting behavior history buffer to provide a clean storage environment for the next round of shooting behavior monitoring and protection control. At the same time, the system protection status indicator is updated to unprotected. At this point, one complete process of this method ends, and the core computing unit returns to the image data acquisition step to enter the next round of shooting behavior monitoring and protection control cycle, ensuring continuous security protection for the screen display information.

[0101] This method achieves precise control over the entire process of preventing information leakage from the screen display by analyzing the collaborative work of the camera, core computing unit, and intelligent power-on anti-spyware protection screen. Through shooting alignment stability assessment and protection trigger suppression mechanisms, it effectively solves the problem of false triggering in existing technologies, significantly reducing the false trigger rate and ensuring continuity in scenarios such as meetings. Through shooting risk level assessment and dynamic adjustment mechanisms for anti-spyware strength, it achieves precise matching between protection strength and risk level, avoiding protection redundancy in low-risk scenarios and balancing information security and display experience. Through a trusted determination mechanism for protection disarming, it effectively resists probing spying attempts and improves the reliability of information protection in highly confidential scenarios.

[0102] Please see Figure 5 , Figure 5 This application provides a screen display information security control system 500. This system embodiment is related to... Figure 1 The method embodiment shown corresponds to this. The system specifically includes:

[0103] Analysis camera 501 is used to continuously collect image data of the area surrounding the protected screen;

[0104] The intelligent power-on privacy screen 502 is attached to the display surface of the screen being protected and can switch between a high-transparency standby state and a uniform coding privacy state in response to control commands.

[0105] The core computing unit 503 is communicatively connected to the analysis camera and the intelligent power-on privacy screen, and is used for:

[0106] Receive image data acquired by the analysis camera;

[0107] Based on the image data, identify whether there is any suspected filming behavior pointing at the protected screen;

[0108] If the suspected shooting behavior is detected, the alignment stability parameter of the device corresponding to the suspected shooting behavior is calculated based on continuous image data within a preset protection trigger suppression window.

[0109] Within the protection trigger suppression window, if the alignment stability parameter does not reach the preset imaging threshold, the privacy protection will not be triggered; if the alignment stability parameter reaches or exceeds the preset imaging threshold, it will be determined as a real shooting behavior, and a first control command will be sent to the smart power-on privacy protection screen to switch it from high-transparency standby state to uniform coding privacy state.

[0110] While the smart power-on privacy screen is in a uniformly coded privacy state, it records historical information about the actual shooting behavior;

[0111] When the actual shooting behavior disappears, the credibility of the actual shooting behavior being terminated is calculated based on the historical information;

[0112] If the credibility does not reach the preset release threshold, the system continues to send a status maintenance command to the smart power-on privacy screen; if the credibility reaches or exceeds the preset release threshold, the system sends a second control command to the smart power-on privacy screen to restore it from the uniform coding privacy state to the high transparency standby state.

[0113] Preferably, when calculating the alignment stability parameter, the core computing unit is specifically used to: track the position of the device relative to the protected screen in continuous image data; calculate the magnitude of the alignment angle change of the device based on the position; calculate the duration of continuous alignment of the device based on the timestamp of the image data; and calculate the alignment stability parameter by weighted summation based on the magnitude of the alignment angle change and the duration.

[0114] It should be noted that the working process of each module in the screen display information security control system described in this embodiment can refer to the working process of the screen display information security control method described in the above embodiments, and the technical effect achieved is the same as that of the screen display information security control method described in the above embodiments, so it will not be repeated here.

[0115] The above description represents the preferred embodiments of the present invention. It should be noted that, for those skilled in the art, various improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for controlling the security of screen display information, characterized in that, The method, applicable to a system comprising an analysis camera, a core computing unit, and an intelligent power-on privacy screen, includes: The analysis camera continuously collects image data of the area surrounding the protected screen. The core computing unit identifies, based on the image data, whether there is any suspected filming behavior pointing at the protected screen; If the suspected shooting behavior is detected, the core computing unit calculates the alignment stability parameters of the device corresponding to the suspected shooting behavior based on continuous image data within a preset protection trigger suppression window. Within the protection trigger suppression window, if the alignment stability parameter does not reach the preset imaging threshold, the privacy protection will not be triggered; if the alignment stability parameter reaches or exceeds the preset imaging threshold, it will be determined as a real shooting behavior, and the smart power-on privacy protection screen will be controlled to switch from high-transparency standby state to uniform coding privacy state. During the uniform blurring and privacy protection state, the core computing unit records historical information about the actual shooting behavior; When the actual shooting behavior disappears, the core computing unit calculates the credibility that the actual shooting behavior has ended based on the historical information; If the credibility does not reach the preset release threshold, the uniform coding anti-spy state is maintained; if the credibility reaches or exceeds the preset release threshold, the smart power-on anti-spy protection screen is controlled to return to the high-transparency standby state.

2. The screen display information security control method according to claim 1, characterized in that, Calculating the alignment stability parameter includes: tracking the position of the device relative to the protected screen in continuous image data; calculating the magnitude of the alignment angle change of the device based on the position; calculating the duration of continuous alignment of the device based on the timestamps of the image data; and calculating the alignment stability parameter by weighted summation based on the magnitude of the alignment angle change and the duration.

3. The screen display information security control method according to claim 1, characterized in that, After switching to uniform coding anti-spy mode, the method further includes: the core computing power unit assessing the shooting risk level based on the shooting distance, alignment angle stability, and duration of the actual shooting behavior; the core computing power unit generating protection strength control parameters based on the shooting risk level; and adjusting the control parameters of the smart power-on anti-spy protection screen according to the protection strength control parameters to dynamically adjust the intensity of uniform coding.

4. The screen display information security control method according to claim 3, characterized in that, The risk assessment of the shooting level includes: calculating the shooting distance based on the image data and the parameters of the analysis camera; obtaining the range of change in the alignment angle of the actual shooting behavior; calculating the duration of the actual shooting behavior; calculating a risk level assessment value by weighted summation based on the shooting distance, the range of change in the alignment angle, and the duration; and determining the shooting risk level according to the preset range in which the risk level assessment value falls.

5. A screen display information security control method according to claim 3, characterized in that, Adjusting the control parameters of the intelligent power-on privacy screen to dynamically adjust the intensity of uniform coding includes: The shooting risk level includes a high-risk level and a low-risk level; the high-risk level corresponds to a first control parameter range, and the low-risk level corresponds to a second control parameter range, wherein the first control parameter range is greater than the second control parameter range.

6. A screen display information security control method according to claim 3, characterized in that, The historical information includes at least: the cumulative duration of the actual shooting behavior, the number of interruptions, and the duration of each interruption.

7. A screen display information security control method according to claim 6, characterized in that, Calculating the credibility that the actual shooting behavior has ended includes: obtaining the duration of the disappearance of the actual shooting behavior; obtaining the cumulative duration and number of interruptions in the historical information; and calculating the credibility by weighted summation based on the disappearance duration, the cumulative duration, and the number of interruptions.

8. A screen display information security control method according to claim 1, characterized in that, Before acquiring image data, the method further includes: the core computing unit loading a shooting behavior recognition model; establishing a data connection with the analysis camera and a control connection with the intelligent power-on privacy screen; and controlling the intelligent power-on privacy screen to enter a high-transparency standby state.

9. A screen display information security control system, characterized in that, include: The camera is used to continuously collect image data of the area surrounding the protected screen. The intelligent power-on privacy screen is fitted onto the display surface of the screen being protected and can switch between a high-transparency standby state and a uniform coding privacy state in response to control commands. The core computing unit, which is communicatively connected to the analysis camera and the intelligent power-on privacy screen, is used for: Receive image data acquired by the analysis camera; Based on the image data, identify whether there is any suspected filming behavior pointing at the protected screen; If the suspected shooting behavior is detected, the alignment stability parameter of the device corresponding to the suspected shooting behavior is calculated based on continuous image data within a preset protection trigger suppression window. Within the protection trigger suppression window, if the alignment stability parameter does not reach the preset imaging threshold, the privacy protection will not be triggered. If the alignment stability parameter reaches or exceeds the preset imaging threshold, it is determined to be a real shooting behavior, and a first control command is sent to the smart power-on privacy screen to switch it from high-transparency standby state to uniform coding privacy state. While the smart power-on privacy screen is in a uniformly coded privacy state, it records historical information of the actual shooting behavior; When the actual shooting behavior disappears, the credibility of the actual shooting behavior being terminated is calculated based on the historical information; If the credibility does not reach the preset release threshold, the system continues to send a status maintenance command to the smart power-on privacy screen; if the credibility reaches or exceeds the preset release threshold, the system sends a second control command to the smart power-on privacy screen to restore it from the uniform coding privacy state to the high transparency standby state.

10. A screen display information security control system according to claim 9, characterized in that, When calculating alignment stability parameters, the core computing unit is specifically used to: track the position of the device relative to the protected screen in continuous image data; calculate the magnitude of the alignment angle change of the device based on the position; and calculate the duration of continuous alignment of the device based on the timestamp of the image data. The alignment stability parameter is calculated by weighted summation based on the magnitude of the alignment angle change and the duration.

Images