Anti-shooting screen display control method and system based on dynamic grating interference

Abstract

The invention relates to the technical field of display, and discloses an anti-shooting screen display control method and system based on dynamic grating interference, and the method comprises the steps: obtaining display screen data; identifying a sensitive content area, enhancing the dynamic grating density for the sensitive content area, and generating a non-periodic dynamic grating interference pattern; acquiring ambient light parameters around the display screen, and judging whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters; and storing the adjusted dynamic grating interference pattern and the characteristic index in a historical adjustment scheme, and displaying the adjusted dynamic grating interference pattern on a display screen. Through regional dynamic monitoring and differential interference, protection of sensitive contents is realized.

Description

Technical Field

[0001] The present invention relates to the field of display technology, and in particular to an anti-shooting screen display control method and system based on dynamic grating interference. Background Art

[0002] With the rapid development of the digital age, the security of screen display content has become increasingly prominent. Whether it is commercial secrets, copyrighted film and television content, or sensitive information in public places, they are all at risk of being illegally photographed or recorded. Traditional information protection methods (such as encrypted transmission and permission management) are mainly aimed at data theft in digital environments, but lack effective protection against screen photography at the physical level. Especially today when smartphones and mini cameras are popular, stealing screen content by taking photos or recording the screen has become an important way of information leakage.

[0003] The patent document with publication number CN117037270A discloses a screen anti-shooting system and method based on image processing. Its processing means is to monitor the environment around the display screen through a monitoring module, and trigger screen switching by identifying the character action information in the image information, thereby preventing leakage. However, this technical means relies on post-monitoring of shooting actions or environmental threats. It is necessary to identify the risk first and then trigger the screen switching. There are algorithm delays in its action recognition, feature matching and other links, and the monitoring of personnel actions is easily affected by the environment, which may frequently trigger false alarms and cause unnecessary interface switching.

[0004] Therefore, it is necessary to design an anti-shooting screen display control method and system based on dynamic grating interference to solve the problems existing in the current technology. Summary of the invention

[0005] In view of this, the present invention proposes an anti-shooting screen display control method and system based on dynamic grating interference, aiming to solve the problem of poor anti-shooting effect at present.

[0006] In one aspect, the present invention provides an anti-shooting screen display control method based on dynamic grating interference, comprising: Acquire display screen data, divide the display screen into N monitoring areas, and construct a dynamic grating interference pattern based on the display screen data; Based on the N monitoring areas, a sensitive content area is identified, and when a sensitive content area is detected, the dynamic grating density is enhanced for the sensitive content area, and a non-periodic dynamic grating interference pattern is generated; Acquiring ambient light parameters around the display screen, and determining whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters; When it is determined to adjust the dynamic grating interference pattern, the dynamic grating density and the display screen data are used as the characteristic index of the ambient light parameter, and the characteristic index is compared with the historical adjustment scheme. According to the comparison result, an adjustment coefficient is determined to adjust the dynamic grating interference pattern; The adjusted dynamic grating interference pattern and the characteristic index are stored in the historical adjustment scheme, and the adjusted dynamic grating interference pattern is displayed on the display screen.

[0007] Further, when constructing the dynamic grating interference pattern based on the display screen data, it includes: The display screen data includes screen resolution, screen brightness, and screen refresh rate. Based on the screen refresh rate, the change frequency of the grating interference pattern is synchronized, and the change frequency > 60Hz. Based on the screen brightness, the grating interference pattern is superimposed on the normal display content with low transparency. Based on the screen resolution, the pixel density of the grating interference pattern is determined; Construct a security database based on the existing shooting device data; The grating interference pattern includes stripe high-frequency patterns, dot matrix high-frequency patterns, and grid high-frequency patterns, and the pixel density of the grating interference pattern matches the pixel pitch in the security database.

[0008] Further, when identifying sensitive content areas based on N monitoring areas, it includes: Store sensitive content in the security database, and the sensitive content includes text-based sensitive content, image-based sensitive content, and dynamic content-based sensitive content; Perform word frequency statistics on the text-based sensitive content and construct a text feature vector, extract deep image features from the image-based sensitive content and construct a sensitive image feature library, and mark the dynamic content-based sensitive content; Obtain the text content in the monitoring area and perform cosine similarity comparison based on the text feature vector; When the text content matches the sensitive text, trigger a sensitive sub-region mark for the text content; When the text content is fuzzy text, infer its semantic risk and trigger a sensitive sub-region mark based on its semantic risk; Obtain the image-based sensitive content in the monitoring area, extract the feature vector of the image-based sensitive content, compare the feature vector of the image-based sensitive content with the sensitive image feature library, and trigger a sensitive sub-region mark based on the comparison result; Obtain the dynamic content-based sensitive content in the monitoring area, perform continuous inter-frame difference analysis on the dynamic content-based sensitive content data, and trigger a sensitive sub-region mark.

[0009] Further, when a sensitive content area is detected and the dynamic grating density is enhanced for the sensitive content area, it includes: Based on the detected discrete sensitive sub-regions, density clustering based on the Euclidean distance is performed to merge adjacent or overlapping sensitive sub-regions, and edge smoothing processing is performed on the merged adjacent or overlapping sensitive sub-regions; Based on the sensitive sub-regions, the dynamic grating density is enhanced, and at the junction of the sensitive sub-regions and non-sensitive sub-regions, the dynamic grating density is transitioned based on linear interpolation; Independent grating layers are created based on the N monitoring regions, and a dynamic mask matrix is generated for the N monitoring regions; Based on the dynamic mask matrix, the detected sensitive sub-regions and non-sensitive sub-regions are marked, and the dynamic mask matrix is bound to the dynamic grating density through a shader.

[0010] Further, when generating the non-periodic dynamic grating interference pattern, it includes: Based on the sensitive sub-regions and the non-sensitive sub-regions, a dynamic rotation pattern is generated within a predetermined time through a pseudo-random number generator; Based on the sensitive sub-regions and the non-sensitive sub-regions, a non-repeating scaling pattern is generated; Based on the sensitive sub-regions, the sensitive sub-blocks are divided, and the dynamic rotation pattern or the non-repeating scaling pattern is independently run based on the sensitive sub-blocks; Based on Alpha blending, the dynamic grating interference pattern is fused with the content of the display screen, and the grating operation mode is re-randomized based on a preset time.

[0011] Further, when obtaining the ambient light parameters around the display screen and determining whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters, it includes: Based on the ambient light parameters, the light intensity is obtained, and the light intensity levels are divided; The light intensity levels are divided into strong light, dim light, and normal light; When it is determined to be dim light, the contrast of the dynamic grating interference pattern is reduced, and the transparency of the dynamic grating interference pattern is increased; When it is determined to be normal light, the contrast and transparency of the current dynamic grating interference pattern are maintained; When it is determined to be strong light, the contrast of the dynamic grating interference pattern is increased, and the transparency of the dynamic grating interference pattern is reduced.

[0012] Further, when comparing the characteristic index with the historical adjustment scheme and determining an adjustment coefficient to adjust the dynamic grating interference pattern according to the comparison result, it includes: The historical adjustment scheme includes a historical feature index and a historical adjustment coefficient; Calculate the similarity between the feature index and each historical feature index, and determine the adjustment coefficient according to the similarity comparison result to adjust the dynamic grating interference pattern; When there is data in the historical adjustment scheme whose similarity to the feature index is greater than the similarity threshold, adjust the dynamic grating interference pattern according to the historical adjustment coefficient corresponding to the maximum similarity; When there is no data in the historical adjustment scheme whose similarity to the feature index is greater than the similarity threshold, determine the similarity set and select the historical feature index corresponding to the maximum similarity in the similarity set as the initial value, and adjust the initial value according to the remaining historical adjustment coefficients in the similarity set to obtain the adjustment coefficient to adjust the dynamic grating interference pattern.

[0013] Further, when determining the similarity set and selecting the historical feature index corresponding to the maximum similarity in the similarity set as the initial value, and adjusting the initial value according to the remaining historical adjustment coefficients in the similarity set, it includes: Evaluate the moiré coverage rate and readability score of all the historical feature indexes, and sort them based on the moiré coverage rate and the readability score, and screen out the historical feature index with the highest moiré coverage rate and the lowest readability score as the candidate; Based on the candidate historical feature index, perform univariate iteration on the grating density, transparency, and dynamic speed respectively; When the difference in coverage rate between two adjacent iterations is less than 5%, stop the iteration; Based on the historical feature index after stopping the iteration, perform rule solidification, and determine the adjustment coefficient based on the historical feature index after rule solidification to adjust the dynamic grating interference pattern.

[0014] Further, the rule solidification includes: Take the mean value of the grating density interval and round it to a 5% step size; Limit the transparency adjustment range to ≤±15%; Limit the dynamic speed ≤15 revolutions per second.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: Through regional dynamic monitoring and differential interference, the protection of sensitive content is achieved. The dynamic grating density enhancement based on real-time content recognition can apply high-intensity interference to the core sensitive area, improving the active defense ability against secret shooting behavior. The non-periodic grating generation algorithm breaks the temporal and spatial regularity of the traditional static interference pattern, increasing the difficulty for shooting devices to crack. The real-time matching of dynamic grating parameters with the screen content and ambient light forms a multi-level optical interference barrier, making it difficult for illegal shooting devices to avoid protection through conventional parameter adjustment. The transparent overlay and regional control method are adopted to minimize the impact on normal viewing while ensuring the protection effect. By positioning the sensitive area and weakening the interference in the non-sensitive area, visual fatigue caused by full-screen unified interference is avoided. The ambient light adaptive adjustment of grating transparency and contrast ensures the visibility of the content under different lighting conditions. The fusion analysis of ambient light parameters enables the grating interference effect to vary dynamically with the lighting conditions. The interference contrast is enhanced in strong light environments, and the visibility of the grating is reduced in low light scenarios to ensure the protection stability under different lighting scenarios. Based on the feature matching and parameter adjustment of historical data, combined with the random perturbation of the non-periodic grating pattern, cracking attempts based on algorithms such as multi-frame synthesis and deep learning are resisted. The synchronization mechanism of dynamic parameters and the screen refresh rate eliminates the protection loopholes caused by timing misalignment.

[0016] On the other hand, the present application also provides an anti-shooting screen display control system based on dynamic grating interference, including: An acquisition module, configured to obtain display screen data, and the acquisition module is further configured to obtain ambient light parameters around the display screen; A judgment module, configured to identify sensitive content areas. When a sensitive content area is detected, the dynamic grating density is enhanced for the sensitive content area, and the non-periodic dynamic grating interference pattern is generated. The judgment module is further configured to judge whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters; A storage module, configured to store the adjusted dynamic grating interference pattern and the feature index into the historical adjustment scheme; An adjustment module, configured to use the dynamic grating density and the display screen data as the feature index of the ambient light parameters, compare the feature index with the historical adjustment scheme, and determine an adjustment coefficient according to the comparison result to adjust the dynamic grating interference pattern.

[0017] It can be understood that the above anti-shooting screen display control method and system based on dynamic grating interference have the same beneficial effects, which will not be elaborated here. Description of the Drawings

[0018] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Also, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 This is a flowchart of a method for controlling the display of an anti-photographing screen based on dynamic grating interference provided by an embodiment of the present invention.

[0019] Figure 2 This is a functional block diagram of a control system for an anti-photographing screen display based on dynamic grating interference provided by an embodiment of the present invention. Specific Embodiments

[0020] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. Hereinafter, the present invention will be described in detail with reference to the drawings and in conjunction with the embodiments.

[0021] In some embodiments of the present application, referring to Figure 1 as shown, a method for controlling the display of an anti-photographing screen based on dynamic grating interference includes: S100: Obtain display screen data, divide the display screen into N monitoring areas, and construct a dynamic grating interference pattern based on the display screen data.

[0022] S200: Based on the N monitoring areas, identify sensitive content areas. When a sensitive content area is detected, enhance the dynamic grating density for the sensitive content area and generate an aperiodic dynamic grating interference pattern.

[0023] S300: Obtain the ambient light parameters around the display screen and determine whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters.

[0024] S400: When it is determined to adjust the dynamic grating interference pattern, use the dynamic grating density and the display screen data as characteristic indices of the ambient light parameters, compare the characteristic indices with the historical adjustment schemes, and determine the adjustment coefficient according to the comparison result to adjust the dynamic grating interference pattern.

[0025] S500: Store the adjusted dynamic grating interference pattern and the characteristic indices into the historical adjustment schemes, and display the adjusted dynamic grating interference pattern on the display screen.

[0026] Specifically, the screen is divided into equal grid areas, and each area is analyzed independently. The display content (text, image, dynamic video) and pixel distribution characteristics (such as edge density, color histogram) of each area are captured in real time. The text is extracted by OCR, the keyword library (such as passwords, identity information) is matched, and sensitive paragraphs are identified by combining semantic analysis. At the same time, a lightweight object detection model (such as YOLOLite) can be used to locate sensitive elements such as faces, QR codes, and copyright marks. When a video stream window or a real-time transmission screen is recognized, it is automatically marked as a highly sensitive area. The non-periodic dynamic grating interference is generated based on the chaotic model (Logistic mapping) to generate random rotation angular velocity and scaling factor, breaking the time regularity, and then superimposing Perlin noise to achieve the deformation of the grating pattern, preventing the spatial frequency from being predicted. The high-frequency dense grating (such as 20% density) is used in the sensitive area, and the interference is reduced in frequency or turned off in the non-sensitive area. The ambient light intensity (Lux) and color temperature (Kelvin) are obtained in real time through the ambient light sensor. The light levels are divided as follows: Dim light (<50 Lux): Reduce the grating contrast to 15% and increase the transparency to 20%. Normal light (50 - 1000 Lux): Maintain the standard parameters. Strong light (>1000 Lux): Increase the contrast to 25% and reduce the transparency to 10%. When constructing the feature index, the grating density distribution, the proportion of sensitive areas, and the ambient light intensity are encoded into a multi-dimensional feature vector. The cosine similarity and Euclidean distance fusion algorithm are used to retrieve the TopK similar scenario solutions from the historical database, and the adjustment coefficients of the similar historical solutions are weighted and averaged. The weights are jointly determined by the matching similarity and the protection effect score. Only when the interference effect meets the standard (the moiré coverage rate > 80%, the readability score < 20%) is it stored in the historical database. If the effect of the new solution decreases after being applied continuously for 3 times, it automatically rolls back to the previous stable version. When applying this embodiment, a high refresh rate screen (≥120Hz), an ambient light sensor, and a GPU acceleration unit are deployed.

[0027] Set the value of N according to the screen resolution (for example, when N = 8, a 1080P screen is divided into 64 areas of 135×135 pixels), , where W is the total width of the screen (number of pixels), H is the total height of the screen (number of pixels), and N is the number of partitions on one side (for example, N = 8 means the screen is divided into 8*8 = 64 areas), is the i-th monitoring area, indexed by row and column and It is uniquely determined that (x, y) is the position of the pixel point. Sensitive keywords, LOGO feature vectors, sensitive videos, etc. are preset. By storing sensitive content in the security database, it can be determined whether the content is sensitive by comparing with the security database when the content is detected. Each area independently runs OCR and object detection, outputs sensitive content markers, and then enhances the density of raster interference for the sensitive content area. At the same time, the data of the screen ambient light is obtained, and according to the different ambient lights, data such as the contrast and transparency of the raster are changed to ensure that the screen can still prevent shooting under different lighting conditions. When the raster on the screen (such as stripes, grids) is close to the spatial frequency of the pixel array of the camera sensor, the superposition of the two will generate Moiré patterns, resulting in blurred or distorted captured images. The dynamic raster breaks the camera's adaptation ability to a fixed frequency through periodic changes (such as rotation, scaling), making the Moiré pattern persist and unable to be repaired by algorithms. The persistence of vision of the human eye makes it insensitive to patterns with high-frequency changes (>60Hz), while the sampling frequency of the camera (usually 30 - 60fps) will capture the transient changes of the dynamic raster due to discrete sampling, resulting in stripes, flickering or blurring in the captured image. Furthermore, through the low-opacity superposition and sub-region control technology, the dynamic raster can seamlessly blend into the normal display content and achieve the protection function with almost no impact on the visual perception.

[0028] In some embodiments of the present application, when constructing a dynamic raster interference pattern based on the display screen data, it includes: The display screen data includes the screen resolution, screen brightness, and screen refresh rate. Synchronize the change frequency of the raster interference pattern based on the screen refresh rate, and the change frequency > 60Hz. Superimpose the raster interference pattern on the normal display content with low opacity based on the screen brightness, and determine the pixel density of the raster interference pattern based on the screen resolution.

[0029] Construct a security database based on the data of existing shooting devices.

[0030] The raster interference pattern includes stripe high-frequency patterns, dot matrix high-frequency patterns, and grid high-frequency patterns, and the pixel density of the raster interference pattern matches the pixel pitch in the security database.

[0031] It is understandable that through the dynamic synchronization of the screen refresh rate and the raster pattern change frequency, the interference frequency breaks through the threshold of the human eye's visual persistence effect, ensuring that the interference pattern cannot be detected by the naked eye while forming a dynamic optical interference barrier for the imaging device. High-frequency changing stripes, dot matrices and other multi-form patterns will produce moiré effects and pixel aliasing phenomena during imaging, destroying the complete acquisition of the screen content by the imaging device. The matching of pixel density and display resolution enables the interference pattern to correspond to the physical pixel arrangement characteristics of the screen, further exacerbating the distortion of the effective information in the captured image and increasing the difficulty of stealing screen information through optical imaging means. Based on the transparent superposition control of the screen brightness, the adjustment of the interference intensity and display quality is realized. On the premise of ensuring the readability of the basic display content, the low transparency superposition can not only maintain the normal visual experience, but also form an optical interference layer under the long exposure characteristics of the imaging device. It avoids the problem of screen brightness attenuation caused by traditional privacy screens, and at the same time solves the visual fatigue that may be caused by interference patterns of fixed intensity, establishing a dynamic balance between information protection and user experience. By driving the pixel density adjustment through the resolution parameter, the interference pattern can adapt to different specifications of display devices. For high-resolution screens, a fine pixel arrangement interference mode is adopted, while for low-resolution devices, large-size pattern units are automatically matched to ensure that the best interference effect can be obtained for all types of display terminals. The continuous update of the security database provides a basis for the dynamic optimization of interference strategies. By collecting and analyzing the imaging characteristic data of the imaging device, the frequency combination and spatial distribution parameters of the interference pattern can be adjusted specifically. Especially when dealing with advanced imaging technologies such as high-frame-rate imaging and multi-frame synthesis, targeted interference patterns can be quickly generated through database feature analysis, forming a continuously evolving dynamic defense ability.

[0032] In some embodiments of the present application, when identifying sensitive content areas based on N monitoring areas, it includes: Storing sensitive content in a security database, where the sensitive content includes text-sensitive content, image-sensitive content, and dynamic-content-sensitive content.

[0033] Performing word frequency statistics on text-sensitive content and constructing a text feature vector, extracting deep image features from image-sensitive content and constructing a sensitive image feature library, and performing sensitive marking on dynamic-content-sensitive content.

[0034] Obtaining the text content within the monitoring area and performing cosine similarity comparison based on the text feature vector.

[0035] When the text content matches the sensitive text, triggering a sensitive sub-region mark for the text content.

[0036] When the text content is fuzzy text, inferring its semantic risk and triggering a sensitive sub-region mark based on its semantic risk.

[0037] Obtain image - type sensitive content within the monitoring area, extract the feature vectors of the image - type sensitive content, compare the feature vectors of the image - type sensitive content with the sensitive image feature library, and trigger the marking of sensitive sub - regions based on the comparison result.

[0038] Obtain dynamic - content - type sensitive content within the monitoring area, perform continuous inter - frame difference analysis on the dynamic - content - type sensitive content data, and trigger the marking of sensitive sub - regions.

[0039] It can be understood that by storing sensitive content in a secure database, unified management of text - type, image - type, and dynamic - content - type sensitive content is achieved. This not only facilitates subsequent rapid retrieval and comparison but also enhances data security and prevents the leakage of sensitive information. At the same time, for different types of sensitive content, differential processing strategies are adopted to ensure the pertinence and effectiveness of detection. In text processing, by performing word - frequency statistics on sensitive text and constructing text feature vectors, a quantitative description of text content is achieved, enabling quick identification of content similar to sensitive text, thereby triggering the marking of sensitive sub - regions. In addition, for fuzzy text, by inferring its semantic risk, the accuracy of detection is further improved, avoiding missed reports or false alarms caused by vague text expressions. In image processing, by extracting deep - layer features of images and constructing a sensitive image feature library, in - depth analysis of image - type sensitive content is realized. This comparison method based on feature vectors can identify content similar to sensitive images, thereby triggering the marking of sensitive sub - regions. Compared with traditional image recognition methods, it pays more attention to the extraction and comparison of image features, improving the accuracy and efficiency of detection. In video - stream data processing, by performing continuous inter - frame difference analysis on video - stream data, real - time monitoring of dynamic content is achieved. Sensitive content in the video stream can be detected in a timely manner and marked and processed. Compared with static image processing, video - stream data processing is more complex, but through continuous inter - frame difference analysis, the real - time nature and accuracy of detection are ensured.

[0040] In some embodiments of the present application, when a sensitive content area is detected, when enhancing the dynamic grating density for the sensitive content area, it includes: Based on the detected discrete sensitive sub - regions, perform density clustering based on the Euclidean distance, merge adjacent or overlapping sensitive sub - regions, and perform edge smoothing processing on the merged adjacent or overlapping sensitive sub - regions.

[0041] Enhance the dynamic grating density based on the sensitive sub - regions, and at the junction of the sensitive sub - regions and non - sensitive sub - regions, transition the dynamic grating density based on linear interpolation.

[0042] Create independent grating layers based on N monitoring areas and generate a dynamic mask matrix for the N monitoring areas.

[0043] Based on the sensitive sub-regions and non-sensitive sub-regions detected by the dynamic mask matrix, the dynamic mask matrix is bound to the dynamic raster density through a shader.

[0044] Specifically, density clustering based on Euclidean distance: , where is the set of central coordinates of the detected sensitive sub-regions , is the neighborhood radius threshold (pixel distance), e.g., = 20, is the minimum number of neighborhood points, e.g., = 2, and finally the set of clustered sensitive regions is obtained. By traversing all sensitive sub-regions, the core points (number of points in the neighborhood ≥ ) are marked, and then the adjacent core points and their neighborhood points are merged to form a clustering cluster. Next, the circumscribed rectangle of each cluster is calculated , Edge smoothing processing: , where is the morphological dilation operation, using a structuring element SE (such as a 3*3 rectangular kernel), is the morphological erosion operation to eliminate the jagged edges, and finally the smoothed rectangular region is obtained. By dilating the circumscribed rectangle of each clustering cluster to fill the holes, and then eroding the dilated region to restore the approximate original size and smooth the edges. Next, the density of the sensitive region is enhanced: , where is the enhanced density of the sensitive region, is the basic raster density, is the enhancement coefficient, and then linear interpolation is used for the transition at the junction: , where is the closest distance (in pixels) from the pixel point (x, y) to the boundary of the sensitive region, is the width of the transition region (e.g., w = 10 pixels), and finally the raster density of the transition region (linearly decaying from to ) is obtained. By calculating the distance field of the sensitive region boundary , interpolation density is performed within the transition region , and then a sub-region raster layer is created: , where is the i-th monitoring region, is the raster density of the region , is the rotation angle of the region (generated by a chaotic model), is the region The scaling factor (driven by Perlin noise), by assigning independent raster parameters (density, rotation, scaling) to each monitoring area, enables the GPU instanced rendering technology to generate raster layers, dynamic mask matrix: , where is the dynamic mask matrix, 1 represents the sensitive area, and 0 represents the non-sensitive area. is the boundary of the smoothed sensitive area. The coordinates of the sensitive area after clustering and merging are mapped into a binary matrix to generate a mask in the GPU texture format (such as an 8-bit grayscale image). Finally, through shader binding and rendering, the composite image is output.

[0045] In some embodiments of the present application, when generating an aperiodic dynamic raster interference pattern, it includes: Generating a dynamic rotation pattern based on the sensitive sub-region and the non-sensitive sub-region through a pseudo-random number generator within a predetermined time.

[0046] Generating a non-repeating scaling pattern based on the sensitive sub-region and the non-sensitive sub-region.

[0047] Dividing the sensitive sub-region into sensitive sub-blocks, and independently running the dynamic rotation pattern or the non-repeating scaling pattern based on the sensitive sub-blocks.

[0048] Fusing the dynamic raster interference pattern with the content of the display screen based on Alpha blending, and re-randomizing the raster operation mode based on a preset time.

[0049] Specifically, the pseudo-random number generator: , where is the rotation angle (in radians) of the sensitive sub-region i at time t, is the base rotation angle, is the maximum rotational angular velocity (such as =π / 30 radians / frame), is the pseudo-random number generator based on time t and region seed . By assigning a unique seed to each sensitive sub-region, a new rotation angle is calculated for each frame to ensure that the rotation patterns of adjacent regions are not synchronized. The non-repeating scaling pattern: , where is the scaling factor of the sensitive sub-block j at time t, and are the lower and upper limits of the scaling factor, is the 64-bit hash value calculated after concatenating the timestamp t and the sub-block index j. Finally, the scaling factor is obtained. By dividing the sensitive sub-region into M*M sub-blocks, the hash-driven scaling factor is independently calculated for each sub-block, and then parameter allocation is performed on the sub-blocks: , where is the coordinate range of sub - blocks within the sensitive sub - region, and W, H are the width and height (in pixels) of the sensitive sub - region. , is the starting coordinate of the sub - block, determined by the position of the parent sensitive sub - region. M is the number of sub - blocks divided on each side. By evenly dividing each sensitive sub - region into M * M sub - blocks, a pattern (such as rotation or scaling) is randomly assigned to each sub - block with a probability of 50% for each, and then is applied for dynamic rotation, and is applied for non - repetitive scaling. Independent threads are assigned to each sub - block through the GPU Compute Shader. Finally, based on Alpha blending: , where is the final rendered pixel color, mixing the original content and raster interference. is the original screen pixel color (RGB value). is the dynamic raster interference value. is the global transparency. By using the fragment shader to calculate the mixed color in real - time, the sensitive area is increased to 0.2, and the non - sensitive area is reduced to 0.05. All sub - block seeds are regenerated periodically, and the rotation and scaling parameters are reset.

[0050] In some embodiments of the present application, when obtaining the ambient light parameters around the display screen and determining whether to adjust the contrast and transparency of the dynamic raster interference pattern, it includes: Obtaining the light intensity based on the ambient light parameters and dividing the light levels based on the light intensity.

[0051] The light levels are divided into strong light, dim light, and normal light.

[0052] When it is determined to be dim light, reduce the contrast of the dynamic raster interference pattern and increase the transparency of the dynamic raster interference pattern.

[0053] When it is determined to be normal light, maintain the current contrast and transparency of the dynamic raster interference pattern.

[0054] When it is determined to be strong light, increase the contrast of the dynamic raster interference pattern and reduce the transparency of the dynamic raster interference pattern.

[0055] Specifically, in a dim - light environment, the contrast is reduced by 20%, and the transparency is increased to 18% (not exceeding 25%); in a normal - light environment, there is no change; in a strong - light environment, the contrast is increased by 30% (not exceeding 1.5 times), and the transparency is reduced to 10.5% (not less than 5%).

[0056] In some embodiments of the present application, when comparing the feature index with the historical adjustment scheme and determining the adjustment coefficient to adjust the dynamic grating interference pattern according to the comparison result, it includes: The historical adjustment scheme includes a historical feature index and a historical adjustment coefficient.

[0057] Calculate the similarity between the feature index and each historical feature index, and determine the adjustment coefficient to adjust the dynamic grating interference pattern according to the similarity comparison result.

[0058] When there is data in the historical adjustment scheme whose similarity with the feature index is greater than the similarity threshold, adjust the dynamic grating interference pattern according to the historical adjustment coefficient corresponding to the maximum similarity.

[0059] When there is no data in the historical adjustment scheme whose similarity with the feature index is greater than the similarity threshold, determine the similarity set and select the historical feature index corresponding to the maximum similarity in the similarity set as the initial value, and adjust the initial value according to the remaining historical adjustment coefficients in the similarity set to obtain the adjustment coefficient to adjust the dynamic grating interference pattern.

[0060] Specifically, the feature index vector: , where is the feature index vector, is the ambient light intensity, is the proportion of the sensitive area, is the average density of the dynamic grating, and the historical adjustment scheme: , where is the historical feature index vector, , is the historical adjustment coefficient (contrast coefficient , transparency coefficient ), and then calculate the feature similarity: , where is the current feature and the similarity with the historical scheme j, is the weight of the adjustment coefficient difference to prevent mis-matching when the coefficient difference is too large, is the current grating parameter. When the threshold exceeds 0.8, it is regarded as an effective match. If there is a matching historical scheme, select the optimal historical coefficient. If there is no matching historical scheme, generate a similarity candidate set and select the one with the maximum similarity as the initial value, and then adjust this initial value to finally obtain the adjustment coefficient to adjust the dynamic grating interference pattern.

[0061] In some embodiments of the present application, when determining the similarity set and selecting the historical feature index corresponding to the maximum similarity in the similarity set as the initial value and adjusting the initial value according to the remaining historical adjustment coefficients in the similarity set, it includes: Evaluate the moiré coverage rate and readability score for all historical feature indices, and based on the moiré coverage rate and readability score, perform sorting to select the historical feature index with the highest moiré coverage rate and the lowest readability score as a candidate.

[0062] Based on the candidate historical feature index, perform univariate iteration on the grating density, transparency, and dynamic speed respectively.

[0063] When the difference in coverage rate between two adjacent iterations is less than 5%, stop the iteration.

[0064] Based on the historical feature index after stopping the iteration, perform rule solidification, and based on the historical feature index after rule solidification, determine the adjustment coefficient to adjust the dynamic grating interference pattern.

[0065] In some embodiments of the present application, rule solidification includes: Take the mean of the grating density interval and round it to a 5% step size.

[0066] Limit the transparency adjustment range to ≤ ±15%.

[0067] Limit the dynamic speed ≤ 15 revolutions per second.

[0068] Specifically, by obtaining the moiré coverage rate and readability score (the readability score is an index that quantifies the degree to which the original sensitive content can be recognized in the screen image obtained by an attacker through a photographing device (such as a mobile phone, camera)), by selecting a scheme with a high moiré coverage rate and a low readability score, ensure the maximization of the interference effect, and then obtain the comprehensive score ranking, select the highest historical scheme, and determine its adjustment coefficient. Through the golden section method for univariate iteration, first control the iteration variable range. The initial range of the grating density: , with a step size of 0.05, transparency: , with a step size of 0.02, dynamic speed: (revolutions per second), with a step size of 0.5, where is the historical adjustment coefficient of the grating density, is the historical adjustment coefficient of the transparency, is the historical adjustment coefficient of the dynamic speed. Taking the grating density as an example: Define the search interval: , and then calculate the trial point: , and then evaluate the objective function: , by maximizing (the higher the moiré coverage rate and the lower the readability score, the better), and then narrow the interval. If > , then retain the interval , otherwise, retain , when the interval length When it is less than 0.05, stop the iteration and output the optimal value. Perform univariate iteration on the grating density, transparency, and dynamic speed in sequence. Each time, only adjust one parameter, and keep the other parameters at the initial values of the candidate solutions. Finally, obtain the adjustment coefficient and transfer it to the GPU shader to adjust the grating parameters in real time.

[0069] In summary, the beneficial effects of the present invention are as follows: Through regional dynamic monitoring and differential interference, the protection of sensitive content is realized. The dynamic grating density enhancement based on real-time content recognition can impose high-intensity interference on the core sensitive areas, improving the active defense ability against secretly taking pictures. The non-periodic grating generation algorithm breaks the time and space regularity of the traditional static interference mode, increasing the difficulty for the shooting device to crack. The real-time matching of the dynamic grating parameters with the screen content and ambient light forms a multi-level optical interference barrier, making it difficult for illegal shooting devices to avoid protection through conventional parameter adjustment. The transparent overlay and regional control method minimize the impact on normal viewing while ensuring the protection effect. By positioning the sensitive areas and weakening the interference in the non-sensitive areas, visual fatigue caused by full-screen unified interference is avoided. The environmental adaptive adjustment of the grating transparency and contrast ensures the visibility of the content under different lighting conditions. The fusion analysis of the ambient light parameters enables the grating interference effect to change dynamically with the lighting conditions. The interference contrast is enhanced in strong light environments, and the grating visibility is reduced in low light scenarios, ensuring the protection stability in different lighting scenarios. Based on the feature matching and parameter adjustment of historical data, combined with the random perturbation of the non-periodic grating pattern, it resists cracking attempts based on algorithms such as multi-frame synthesis and deep learning. The synchronization mechanism of the dynamic parameters and the screen refresh rate eliminates the protection loopholes caused by timing misalignment.

[0070] In another preferred embodiment based on the above embodiments, refer to Figure 2 As shown, this embodiment provides an anti-shooting screen display control system based on dynamic grating interference, which is used to apply the above anti-shooting screen display control method based on dynamic grating interference, and includes: An acquisition module, configured to obtain the display screen data, and the acquisition module is also configured to obtain the ambient light parameters around the display screen.

[0071] A judgment module, configured to identify the sensitive content area. When the sensitive content area is detected, enhance the dynamic grating density for the sensitive content area and generate a non-periodic dynamic grating interference pattern. The judgment module is also configured to judge whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters.

[0072] A storage module, configured to store the adjusted dynamic grating interference pattern and the feature index into the historical adjustment scheme.

[0073] An adjustment module is configured to use the dynamic grating density and the display screen data as characteristic indices of the ambient light parameters, compare the characteristic indices with historical adjustment schemes, and determine an adjustment coefficient according to the comparison result to adjust the dynamic grating interference pattern.

[0074] Specifically, the acquisition module obtains screen data and ambient light parameters, the judgment module identifies sensitive content areas, and then enhances the density of the dynamic grating for the sensitive content areas. At the same time, by obtaining the ambient light parameters, it further determines whether to adjust the contrast and transparency. The historical schemes are stored in the storage module for subsequent judgment of whether there are similar adjustment schemes, and similar adjustment schemes can be applied. The adjustment module then determines an adjustment coefficient according to the comparison result to adjust the dynamic grating interference pattern.

[0075] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0077] These computer program instructions can also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable storage medium generate a manufactured product including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to generate a computer-implemented process, thereby providing instructions for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for the functions specified in one block or a plurality of blocks.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for controlling screen display against shooting based on dynamic grating interference, characterized in that: include: Acquire display screen data, divide the display screen into N monitoring areas, and construct a dynamic grating interference pattern based on the display screen data; Based on the N monitoring areas, a sensitive content area is identified, and when a sensitive content area is detected, the dynamic grating density is enhanced for the sensitive content area, and a non-periodic dynamic grating interference pattern is generated; Acquiring ambient light parameters around the display screen, and determining whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters; When it is determined that the dynamic grating interference pattern is to be adjusted, the dynamic grating density and the display screen data are used as characteristic indexes of the ambient light parameters, the characteristic indexes are compared with historical adjustment schemes, and an adjustment coefficient is determined according to the comparison result to adjust the dynamic grating interference pattern; The adjusted dynamic grating interference pattern and the characteristic index are stored in the historical adjustment scheme, and the adjusted dynamic grating interference pattern is displayed on the display screen.

2. The anti-shooting screen display control method based on dynamic grating interference according to claim 1 is characterized in that: When constructing a dynamic grating interference pattern based on the display screen data, it includes: The display screen data includes screen resolution, screen brightness and screen refresh rate, the change frequency of the grating interference pattern is synchronized based on the screen refresh rate, and the change frequency is greater than 60 Hz, the grating interference pattern is superimposed on the normal display content with low transparency based on the screen brightness, and the pixel density of the grating interference pattern is determined based on the screen resolution; Build a security database based on existing camera data; The grating interference pattern includes a stripe high-frequency pattern, a dot matrix high-frequency pattern and a grid high-frequency pattern, and the pixel density of the grating interference pattern matches the pixel spacing in the security database.

3. The anti-shooting screen display control method based on dynamic grating interference according to claim 2 is characterized in that: Based on N monitoring areas, when identifying sensitive content areas, it includes: Storing sensitive content in the security database, the sensitive content includes text-type sensitive content, image-type sensitive content, and dynamic content-type sensitive content; Perform word frequency statistics on the text-based sensitive content and construct a text feature vector, extract deep image features from the image-based sensitive content and construct a sensitive image feature library, and perform sensitive marking on the dynamic content-based sensitive content; Obtain the text content in the monitoring area and perform cosine similarity comparison based on the text feature vector; When the text content matches the sensitive text, triggering a sensitive sub-region mark for the text content; When the text content is ambiguous text, inferring its semantic risk, and triggering sensitive sub-region marking based on its semantic risk; Acquire image-type sensitive content in the monitoring area, extract feature vectors of the image-type sensitive content, compare the feature vectors of the image-type sensitive content with a sensitive image feature library, and trigger a sensitive sub-area tag based on the comparison result; Acquire dynamic content-type sensitive content in the monitoring area, perform continuous inter-frame difference analysis on the dynamic content-type sensitive content data, and trigger sensitive sub-area marking.

4. The anti-shooting screen display control method based on dynamic grating interference according to claim 3 is characterized in that: When a sensitive content area is detected, the dynamic grating density is enhanced for the sensitive content area, including: Based on the detected discrete sensitive sub-regions, density clustering based on Euclidean distance is performed to merge adjacent or overlapping sensitive sub-regions, and edge smoothing is performed on the merged adjacent or overlapping sensitive sub-regions; Enhancing the dynamic grating density based on the sensitive sub-region, and transitioning the dynamic grating density based on linear interpolation at the boundary between the sensitive sub-region and the non-sensitive sub-region; Creating an independent raster layer based on the N monitoring areas, and generating a dynamic mask matrix for the N monitoring areas; The detected sensitive sub-region and non-sensitive sub-region are marked based on the dynamic mask matrix, and the dynamic mask matrix is ​​bound to the dynamic raster density through a shader.

5. The anti-shooting screen display control method based on dynamic grating interference according to claim 4 is characterized in that: When the non-periodic dynamic grating interference pattern is generated, it includes: Generate a dynamic rotation pattern within a predetermined time by a pseudo-random number generator based on the sensitive sub-area and the non-sensitive sub-area; generating a non-repeating zoom pattern based on the sensitive sub-region and the non-sensitive sub-region; Dividing the sensitive sub-areas into sensitive sub-blocks, and independently running the dynamic rotation mode or the non-repetitive scaling mode based on the sensitive sub-blocks; The dynamic grating interference pattern is merged with the content of the display screen based on Alpha blending, and the grating operation mode is re-randomized based on a preset time.

6. The anti-shooting screen display control method based on dynamic grating interference according to claim 5 is characterized in that: Acquiring ambient light parameters around the display screen and determining whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameters includes: Acquire light intensity based on the ambient light parameter, and divide light levels based on the light intensity; The light levels are divided into strong light, dim light and normal light; When it is determined to be dark light, the contrast of the dynamic grating interference pattern is reduced, and the transparency of the dynamic grating interference pattern is increased; When it is determined to be normal light, the contrast and transparency of the current dynamic grating interference pattern are maintained; When it is determined to be strong light, the contrast of the dynamic grating interference pattern is increased, and the transparency of the dynamic grating interference pattern is reduced.

7. The anti-shooting screen display control method based on dynamic grating interference according to claim 6 is characterized in that: The characteristic index is compared with the historical adjustment scheme, and the adjustment coefficient is determined according to the comparison result to adjust the dynamic grating interference pattern, including: The historical adjustment plan includes a historical characteristic index and a historical adjustment coefficient; Calculating the similarity between the characteristic index and each of the historical characteristic indexes, and determining an adjustment coefficient according to the similarity comparison result to adjust the dynamic grating interference pattern; When there is data in the historical adjustment scheme whose similarity with the characteristic index is greater than a similarity threshold, adjusting the dynamic grating interference pattern according to a historical adjustment coefficient corresponding to a maximum similarity value; When there is no data in the historical adjustment scheme whose similarity with the characteristic index is greater than the similarity threshold, a similarity set is determined and the historical characteristic index corresponding to the maximum similarity in the similarity set is selected as the initial value, and the initial value is adjusted according to the remaining historical adjustment coefficients in the similarity set to obtain the adjustment coefficient to adjust the dynamic grating interference pattern.

8. The anti-shooting screen display control method based on dynamic grating interference according to claim 7 is characterized in that: Determining a similarity set and selecting a historical characteristic index corresponding to a maximum similarity value in the similarity set as an initial value, and adjusting the initial value according to other historical adjustment coefficients in the similarity set, including: Performing moiré coverage and readability score evaluation on all the historical feature indices, and sorting them based on the moiré coverage and the readability score, to select the historical feature index with the highest moiré coverage and the lowest readability score as a candidate; Based on the candidate historical characteristic index, univariate iteration is performed on grating density, transparency and dynamic speed respectively; When the coverage difference between two consecutive iterations is less than 5%, the iteration is stopped; The rule is solidified based on the historical characteristic index after the iteration is stopped, and the adjustment coefficient is determined based on the historical characteristic index after the rule is solidified, and the dynamic grating interference pattern is adjusted.

9. The anti-shooting screen display control method based on dynamic grating interference according to claim 8 is characterized in that: The rule solidification includes: Take the mean of the grating density interval and round it to 5% step size; Limit the transparency adjustment range to ≤±15%; The dynamic speed is limited to ≤15 rpm.

10. A screen display control system for preventing shooting based on dynamic grating interference, applied to the screen display control method for preventing shooting based on dynamic grating interference as claimed in any one of claims 1 to 9, characterized in that: include: A collection module is configured to obtain display screen data, and the collection module is further configured to obtain ambient light parameters around the display screen; a determination module configured to identify a sensitive content area, and when a sensitive content area is detected, to enhance the dynamic grating density for the sensitive content area and generate a non-periodic dynamic grating interference pattern, and the determination module is further configured to determine whether to adjust the contrast and transparency of the dynamic grating interference pattern based on the ambient light parameter; A storage module, configured to store the adjusted dynamic grating interference pattern and characteristic index into a historical adjustment scheme; The adjustment module is configured to use the dynamic grating density and the display screen data as characteristic indexes of the ambient light parameters, compare the characteristic indexes with historical adjustment schemes, and determine an adjustment coefficient according to the comparison result to adjust the dynamic grating interference pattern.

Images