Screen content dynamic fuzzy processing method based on user permission verification

Abstract

The invention relates to the technical field of electric data processing, and discloses a screen content dynamic fuzzy processing method based on user permission verification, which comprises the following steps of: acquiring original screen content of a screen sharing end, dividing the original screen content into regions, and distributing a target permission level according to the region content; obtaining a viewing end user permission level, comparing the viewing end user permission level with a layer target permission, and performing fuzzy processing on a layer with insufficient permission; determining a screen fixation point according to the definition of the user image and eye movement tracking, and adjusting the user permission; and finally, pushing the fuzzified screen content according to the adjusted permission. According to the method, protection of sensitive information is ensured through dynamic permission adjustment and fuzzy processing, and meanwhile user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical data processing, and more specifically, to a method for dynamically blurring screen content based on user permission verification. Background Art

[0002] Traditional permission management means such as password authentication and role assignment can control user access permissions, but in the case of multiple users sharing the same screen content, it is difficult to effectively protect the security of specific areas or parts of the data.

[0003] Existing screen content protection technologies mostly rely on static blurring or hiding processing, and have the following deficiencies: adopting a unified blurring strategy for all users, unable to dynamically adjust according to user permissions; static blurring processing may cause important information to be completely invisible, affecting the normal work process; lacking a real-time and intelligent permission verification mechanism. Summary of the Invention

[0004] In view of this, the present invention proposes a method for dynamically blurring screen content based on user permission verification to solve the problems in the prior art.

[0005] The method for dynamically blurring screen content based on user permission verification proposed by the present invention includes: Collect the original screen content of the screen sharing end, divide the original screen content into several regions, input each region into different layers, and assign a target permission level to each layer according to the original screen content in each region; Obtain the user permission levels of each user at the viewing end, compare the user permission levels with the target permission levels of each layer respectively, and blur the layers with user permission levels lower than the target permission levels; Overlay the blurred layers with the remaining unblurred layers to form blurred screen content, and push the blurred screen content; Collect the user images of the viewing end after receiving the blurred screen content according to the time series, determine the screen fixation points of the viewing end users based on eye tracking technology; calculate the trust degree of the screen fixation points according to the clarity of the user images; adjust the user permission levels according to the relationship between the screen fixation points and each layer to obtain the corrected user permissions; Collect the user portraits of the screen sharing end according to the time series, determine the screen fixation points according to the user images, and adjust the user permission levels according to the screen fixation points of the screen sharing end and the viewing end to obtain the final user permissions; Push the subsequent blurred screen content according to the final user permissions and the target permission levels.

[0006] Furthermore, when the original screen content is recognized and divided into a plurality of regions, it includes: The window borders in the original screen content are obtained based on Canny edge detection, the area enclosed by all the window borders is calculated, the window border with the smallest area is selected and input into a layer, and the content of the window border is removed from the original screen content, and the window border with the smallest area is selected again and input into another layer, and the selection is repeated until the original screen content is completely divided.

[0007] Further, when the target permission level is assigned to the layer according to the original screen content in each of the regions, it includes: Establishing a sensitive word library, the sensitive word library includes sensitive keywords and corresponding viewing permission levels; Performing OCR text recognition and application interface feature recognition on the original screen content in each layer to determine whether the layer contains sensitive keywords or a preset specific application program interface; When it is determined that the preset feature application interface is included, the maximum target permission level is assigned to the current layer; when it is determined that the sensitive keywords and the preset specific application interface are not included, the minimum target permission level is assigned to the current layer; When it is determined that only sensitive keywords are included, the position coordinates of the sensitive keywords in the current layer are obtained, and it is determined whether to re-divide the layer according to the position coordinates.

[0008] Furthermore, when there is no need to redivide the layers or the layers have been redivided, the viewing permission level corresponding to each sensitive keyword is obtained according to the sensitive word library, the highest viewing permission level is selected, and the highest viewing permission level is used as the target permission level of the current layer.

[0009] Further, when judging whether to re-divide the layers according to the position coordinates, it includes: Calculate the straight-line distance from each position coordinate to the same edge of the current layer and the interval distance from the edge to the opposite edge respectively, and when max(di)≤D / 3 is satisfied, re-divide the layer; Among them, di represents the straight-line distance from the position coordinate to the edge i in the current layer, di={x1, x2, x3, ..., xn}, i is a positive integer; the maximum value of i is the total number of edges in the current layer, xn represents the straight-line distance from the nth position coordinate to the same edge of the current layer, max(di) represents the maximum value in the set di, and D represents the interval distance.

[0010] Furthermore, when the layer is re-divided, it includes: When multiple max(di) are all less than or equal to D / 3, select the smallest max(di), and divide the current layer into two sub-layers, where one sub-layer contains all sensitive keywords.

[0011] Further, when calculating the trust degree of the screen fixation point according to the clarity of the user image, it includes: Convert the user image into a grayscale image, and the clarity satisfies the following relationship: ; Set the clarity threshold to 100. When the clarity is less than or equal to 100, it is judged as low trust degree. When the clarity is greater than 100, calculate the trust degree according to the normalization method, and the trust degree satisfies the following relationship: ; Among them, is the clarity, is the resolution of the image, which represents the product of the width and height of the image, is the pixel value at in the grayscale image, is the Laplacian value, is the average value of all Laplacian values; is the trust degree, is the clarity threshold, is the maximum clarity.

[0012] Further, according to the relationship between the screen fixation point and each layer, adjust the user permission level to obtain the corrected user permission, including: Obtain the layer where the screen fixation point is located, and calculate the stay time in the layer where it is located. When the preset time threshold is met, judge whether the layer where it is located contains sensitive keywords; if not, replace the user permission level with the corrected user permission; if so, perform the following steps: Obtain the screen fixation points of the other viewing terminals, denoted as reference fixation points, count the number of reference fixation points in the layer where it is located, and calculate the attention degree of the layer where it is located. The attention degree is the ratio of the number of reference fixation points in the layer where it is located to the total number of viewing terminals; when the ratio is less than the attention threshold, lower the user permission level of the viewing terminal corresponding to the screen fixation point by one level, and denote it as the corrected user permission; when the ratio is greater than or equal to the attention threshold, use the user permission level as the corrected user permission.

[0013] Further, when adjusting the user permission level according to the screen fixation points of the screen sharing terminal and the viewing terminals to obtain the final user permission, it includes: When the screen fixation points of the screen sharing end and the viewing end are on the same layer, the corrected user permission of the viewing end is taken as the final user permission; When the screen fixation points of the screen sharing end and the viewing end are not on the same layer, calculate the residence time. After the time threshold is met, downgrade the corrected user by one level to obtain the final user permission.

[0014] Furthermore, it also includes: When the user permission level changes, adjust the blur degree of the layer to the highest. Compared with the prior art, the beneficial effects of the present invention are as follows: By dividing the screen content into multiple layers and assigning target permission levels to each layer, differential permission control for different content areas is achieved. Compared with the unified blur strategy, this method can implement a higher level of protection for sensitive information areas and ensure visibility for non-sensitive areas, thus enhancing the balance between information security and user experience. By using eye-tracking technology to real-time obtain the screen fixation points of each viewing end and dynamically adjust the user permission level in combination with the layer content and fixation behavior, abnormal viewing behavior or unauthorized peeping behavior can be effectively identified, thereby enhancing the security control ability in multi-user sharing scenarios such as meetings and remote collaboration. The concept of "attention" is introduced. By referring to the group statistics of fixation points and user behavior, it is intelligently determined whether a certain area is a sensitive hotspot, and based on this information, the permission level of a single user is dynamically increased or decreased, thereby enhancing the adaptability of the system to user group behavior and the accuracy of sensitive area protection. Dynamic blur processing is used instead of static hiding. While ensuring that information cannot be recognized by unauthorized users, it avoids "excessive occlusion" of content and affects the normal usage process, thereby enhancing the flexibility and practicality of information protection. The credibility of user fixation points is evaluated through image clarity indicators, avoiding misjudgment caused by abnormal states such as blurred images and pose occlusion, and ensuring the reasonableness and robustness of permission adjustment. It supports collaborative adjustment of permissions between the screen sharing end and the viewing end fixation points. Taking the fixation point of the screen sharing end user as the reference basis for permission adjustment, a linkage judgment logic between the content creator and the viewer is formed, improving the context relevance and reasonableness of permission control decisions. Based on Canny edge detection and sensitive word position judgment, the system can re-divide the screen layer as needed to ensure that sensitive content is aggregated rather than dispersed, which helps to improve the logical clarity of the layer and the accuracy of permission control. By constructing a sensitive word library and combining OCR and interface feature recognition methods, it can flexibly adapt to various application scenarios (such as text, finance, medical, etc.), and has good scalability and adaptability. Description of the Drawings

[0015] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become apparent 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. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 This is a flowchart of the dynamic blurring processing method for screen content based on user permission verification provided by an embodiment of the present invention. Specific embodiments

[0016] The exemplary embodiments disclosed in the present application will be described in more detail below 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 fully 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. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0017] Refer to Figure 1 As shown, this embodiment provides a dynamic blurring processing method for screen content based on user permission verification, including: S1: Collect the original screen content of the screen sharing end, divide the original screen content into several regions, input each region into different layers, and assign a target permission level to the layers according to the original screen content in each region; S2: Obtain the user permission levels of each user at the viewing end, compare the user permission levels with the target permission levels of each layer respectively, and blur the layers with user permission levels lower than the target permission levels; S3: Superimpose the blurred layers with the remaining unblurred layers to form blurred screen content, and push the blurred screen content; S4: Collect the user images at the viewing end after receiving the blurred screen content according to the time series, determine the screen fixation points of the viewing end users based on eye tracking technology; calculate the confidence of the screen fixation points according to the clarity of the user images; adjust the user permission levels according to the relationship between the screen fixation points and each layer to obtain the corrected user permissions; S5: Collect the user portraits of the screen sharing end according to the time series, determine the screen fixation points according to the user images, and adjust the user permission levels according to the screen fixation points of the screen sharing end and the viewing end to obtain the final user permissions; S6: Push the subsequent blurred screen content according to the final user permissions and the target permission levels.

[0018] Specifically, after obtaining the user image, any means of processing the image so that it can participate in subsequent operations belongs to the prior art. To more clearly introduce the technical solution of this embodiment, the above "any means" may be: increasing the resolution and frame rate of the viewing-end camera, adjusting the light source conditions when acquiring the image; image sharpening processing; and image super-resolution processing, etc.

[0019] It should be noted that by using the dynamic blur processing technology to adjust the visibility of the screen content according to the user's permission level, sensitive information can be effectively protected. For example, when some users have insufficient permissions, the system will automatically blur the areas that do not match their permissions, thus preventing users from viewing or obtaining content that they should not access. Such a method not only ensures the confidentiality of data, but also avoids human errors or leaks, improving the overall information security.

[0020] The system dynamically adjusts permissions according to the user's real-time behaviors (such as screen fixation points, image clarity, etc.), making the permission management more flexible and adaptive. For example, if the area where the user fixates on the screen is blurred and the clarity of the fixation point is high enough, the system will correct the user's permissions according to the trust level of the fixation point. This dynamic adjustment mechanism based on user behavior enables the system to respond to user needs and behaviors in real time, ensuring the accuracy and personalization of information display.

[0021] The dynamic blur processing can display content according to the permissions of different users, thus providing a personalized screen content experience. For example, high-permission users can see the complete content, while low-permission users can only see the blurred part. This method not only meets the security requirements, but also can flexibly adjust the content display according to the user's permissions and behaviors, avoiding interference from irrelevant content, thereby improving the user experience.

[0022] Through the eye movement tracking technology, the system can accurately obtain the user's fixation points, and thus perform more precise permission control based on the user's behaviors. If the user's fixation points are close to sensitive areas, the system can calculate the trust level based on the clarity of the user image, and then adjust the user's permissions in real time, improving the accuracy and flexibility of permission control to ensure that only users who meet the permission requirements can access high-permission content.

[0023] The dynamic blur technology not only makes a preliminary screening according to the preset permissions, but also further calibrates and adjusts the permissions according to time series, user behaviors and eye movement tracking information. This mechanism avoids the problem of information leakage caused by incorrect initial permission allocation, ensures that the system can always make the most accurate permission adjustment based on real-time data, and effectively prevents the risk of information leakage.

[0024] This method supports real-time interaction and collaboration between multiple users, and is particularly suitable for scenarios that require screen sharing and collaborative work. In a multi-user environment, the system can dynamically adjust the visible area of ​​each user based on their permissions and behavior. For viewing users, the system uses eye tracking technology and image clarity calculations to determine changes in permissions in real time, ensuring that each user can only access appropriate content during the collaboration process, enhancing the smoothness and security of the workflow.

[0025] The system is able to automatically adjust permissions based on the real-time behavior of viewing users without manual intervention or manual review. This automated process not only improves the efficiency of the system, but also reduces deviations and errors caused by manual intervention, reducing labor costs and potential operational errors.

[0026] In the scenario of multi-user permission management, user permissions and behaviors will change. The system can flexibly adjust and modify permissions based on real-time data, making the entire process highly adaptable and fault-tolerant. Even if user behavior or permission settings change, the system can still respond effectively to ensure a balance between information security and user experience.

[0027] This method is applicable to various scenarios where screen content needs to be displayed according to user permissions, such as remote meetings, online education, corporate shared files, and viewing of sensitive information. Especially in scenarios with high information security requirements, the efficiency and accuracy of data protection and access control can be greatly improved by dynamically adjusting permissions and blurring screen content.

[0028] In some embodiments of the present application, when the original screen content is recognized and divided into a plurality of regions, it includes: The window borders in the original screen content are obtained based on Canny edge detection, the area enclosed by all window borders is calculated, the window border with the smallest area is selected and input into a layer, and the content of the window border is removed from the original screen content, and the window border with the smallest area is selected again and input into another layer, and the selection is repeated until the original screen content is completely divided.

[0029] It should be noted that Canny edge detection is a classic edge detection algorithm that can effectively identify edge information in screen content, especially for extracting window borders. Through this method, the system can accurately identify the boundaries of different areas (such as windows) and perform content segmentation based on the boundaries. This segmentation method can divide the screen content into multiple independent areas, which is convenient for subsequent blur processing, permission verification and content display.

[0030] The area enclosed by each window border is divided according to its area size, enabling the system to prioritize the processing of smaller window areas. This division method can effectively avoid the chaos in processing complex screen layouts, allowing each area to be processed individually according to a certain logic and priority. By adopting the strategy of preferentially selecting the window with the smallest area, the system can ensure that the smallest area is processed first during the blurring process, gradually covering the entire screen to avoid omission and duplication.

[0031] By removing the processed areas (window border content) and continuing the division based on the remaining areas, the integrity of the original screen content is ensured not to be lost. Each time the window with the smallest area is selected and its content is removed, it can effectively avoid the situation of omitting or duplicating areas during the division process, ensuring that all content can be reasonably and completely divided into different layers, thus providing complete basic data for subsequent blurring processing and permission control.

[0032] Using Canny edge detection to extract window borders can achieve high-precision content recognition through the clear extraction of edge information. For complex screen layouts (such as multiple windows, application interfaces, etc.), this method can effectively distinguish the boundaries of each window, making the content division result more accurate, avoiding the errors that may occur during manual division, and enhancing the stability of the division process.

[0033] In different screen layouts, the area, shape, and number of windows may vary. By gradually processing the window with the smallest area, the system can adaptively handle different screen layouts. Regardless of how the window size changes, the system will automatically process them from smallest to largest in terms of area, ensuring that the processing of each area meets the priority requirements. This method has strong flexibility and can adapt to different types and complexities of screen layouts.

[0034] By placing each divided area into different layers for permission allocation and blurring processing, it can ensure that each area is processed independently, avoiding interference between areas. This division method enables the system to more precisely control the permission level of each area in subsequent steps and dynamically adjust the displayed content for users with different permissions. Through this refined area processing, the processing efficiency of the system is greatly improved, especially when dealing with complex screen content.

[0035] Assigning each area to different layers and performing blurring processing based on the permission level of each area makes this method very suitable for scenarios that require dynamic permission control. For example, when some users have lower permissions, the system can blur the areas they need to view, while users with higher permissions can see clear content. Through precise area division, the system can better apply blurring processing to different areas, enhancing security and the personalized experience.

[0036] Under various different screen layouts and content structures, the segmentation method based on edge detection can ensure that the system still maintains a good segmentation effect when facing screens with different layouts. Especially in some complex scenarios of screen sharing (such as multi-window and multi-program interaction), the system can effectively identify each window and perform correct segmentation, enhancing the adaptability and fault tolerance of the system.

[0037] In a multi-user scenario (such as video conferencing, online collaboration, etc.), each user may have different permission levels. Through refined segmentation and permission control, different degrees of blurred content can be presented to each user according to their permission levels. This flexible processing method can support the permission management requirements in multi-device collaboration scenarios, ensuring that each user can only access information that matches their permissions.

[0038] In some embodiments of the present application, when assigning target permission levels to layers according to the original screen content in each region, it includes: Establish a sensitive word library, which includes sensitive keywords and corresponding viewing permission levels; Perform OCR text recognition and application interface feature recognition on the original screen content in each layer to determine whether the layer contains sensitive keywords or a preset specific application program interface; Specifically, the preset specific application programs include but are not limited to WeChat, QQ, Alipay, etc. Since these application programs are logged in through private accounts, privacy protection needs to be carried out for the above application programs.

[0039] When it is determined that the preset feature application program interface is included, assign the maximum target permission level to the current layer; when it is determined that neither sensitive keywords nor the preset specific application program interface is included, assign the minimum target permission level to the current layer; When it is determined that only sensitive keywords are included, obtain the position coordinates of the sensitive keywords in the current layer, and determine whether to re-divide the layer according to the position coordinates.

[0040] It should be noted that by establishing a sensitive word library and combining OCR technology to identify sensitive keywords in the layer content, sensitive information on the screen can be dynamically identified. This provides precise guarantee for realizing privacy protection, especially when dealing with private information. Combining the feature recognition of specific application programs (such as WeChat, QQ, Alipay, etc.), the system can identify and protect the application program interfaces with high privacy and security requirements, preventing unauthorized users from accessing sensitive information.

[0041] When sensitive information or application interfaces are recognized, the system can assign the highest permission level to that layer to ensure that authorized users can access the complete content, while other users cannot view it. Through this permission control mechanism, the system can effectively manage access permissions in a multi-user environment, preventing users with insufficient permissions from accessing sensitive or private data, thereby enhancing overall security.

[0042] After matching the sensitive word library and identifying the application interface for the layer content, more flexible permission control can be achieved. When the layer does not contain sensitive keywords and specific application interfaces, the minimum permission level can be assigned to it to ensure that unnecessary information is not exposed to unauthorized users. When the layer contains sensitive information, the system will automatically adjust the permission level according to the position, type of sensitive words, and characteristics of the application, thereby achieving a more refined permission division and avoiding the leakage of user privacy.

[0043] OCR text recognition and specific application feature recognition can automatically determine whether the screen content contains sensitive information or privacy applications without manual intervention. This automated processing improves efficiency and can respond in real time to user behavior and changes in screen content, enabling the system to adjust the screen display content in real time according to specific situations when facing different shared content, ensuring the intelligence and efficiency of privacy protection.

[0044] When it is determined that there are sensitive keywords in the layer, the system not only assigns permissions but also further determines whether the layer needs to be re-divided by obtaining the position coordinates of the sensitive words in the layer. This approach can accurately distinguish sensitive content from non-sensitive content and make reasonable layer assignments and adjustments according to factors such as the importance, position, and sensitivity of the content, thereby preventing unnecessary information leakage.

[0045] In a multi-user screen sharing or collaboration scenario, each user may require different access permissions. For example, some users may need to view the complete screen content, while some users can only view blurred or partial content. By combining sensitive words, application interface recognition, and position judgment, the system can provide personalized permission control according to each user's permission level and the sensitivity of the screen content. This fine-grained permission management not only meets the security requirements but also enhances the user experience.

[0046] By recognizing the interface characteristics of specific applications (such as WeChat, QQ, Alipay, etc.), the system can effectively identify and protect the application interfaces involving sensitive content such as private accounts and transaction information. This cross-application permission management ensures security in different application scenarios, and appropriate permission protection can be obtained for both chat applications, payment platforms, and other applications with high privacy.

[0047] By comprehensively utilizing the sensitive word library, application identification, and coordinate position judgment, the system can achieve multi-level permission control. It dynamically adjusts the content in different regions, not only considering the sensitivity of the content itself, but also making refined processing based on the location of the content, the specific user permission level, and the environment. In this way, the flexibility and adaptability of the system are greatly enhanced, enabling it to handle various complex scenarios and security requirements.

[0048] In a multi-user environment, considering the group behavior differences and the possible risk of accidental triggering, this method can avoid information leakage caused by misoperation or improper permission settings, and improve the fault tolerance and stability of the system through precise layer division, sensitive information identification, and dynamic permission adjustment. In addition, the preset application feature recognition helps to avoid excessive obfuscation and prevent users from being unable to correctly access the required shared content due to too low permissions.

[0049] In some embodiments of the present application, when there is no need to re-divide the layer or after the layer is re-divided, the viewing permission level corresponding to each sensitive keyword is obtained according to the sensitive word library, the highest viewing permission level is selected, and the highest viewing permission level is used as the target permission level of the current layer.

[0050] It should be noted that by identifying sensitive words in each layer and determining the corresponding viewing permission level based on the sensitive word library, the system can ensure that any part of the layer involving sensitive content is properly protected. If a layer contains sensitive words, the system will automatically raise the permission level of the layer to ensure that only users with the corresponding permissions can access the sensitive content, thereby preventing unauthorized users from accessing sensitive information.

[0051] When multiple sensitive words appear in the same layer, selecting the highest permission level as the target permission level of the current layer can avoid permission conflicts between different sensitive information, and uniformly manage and allocate access permissions. This approach simplifies the permission management process, ensures the unity and rationality of content access permissions, and improves the management efficiency of the system.

[0052] In a multi-user environment, some layers may contain multiple sensitive keywords. Selecting the highest permission level to protect these layers and preventing low-permission users from seeing high-risk content can effectively improve the security of the system. In this way, the system can promptly lock and protect highly sensitive areas, prevent inappropriate access and information leakage, and reduce potential risks.

[0053] By automatically adjusting the permission level based on a sensitive word library, the system can intelligently identify the sensitivity of the layer content and elevate the permission level as needed. This automated permission adjustment not only enhances security but also ensures a smooth user experience. Users can obtain appropriate content display according to their needs without losing access to critical information due to misoperations or permission errors.

[0054] The application of the sensitive word library provides a dynamic and flexible mechanism for privacy protection. The system can update and identify new sensitive information in real time and adjust the permission control of the displayed content based on this information. Through this mechanism, the system can better adapt to the changing privacy protection requirements and ensure the protection of sensitive data without affecting the normal user experience.

[0055] By selecting the highest permission level in the layer as the target permission level instead of assigning permissions to each keyword individually, the problem of inconsistent permissions between multiple keywords can be effectively avoided, reducing the risk of accidental triggering or misassignment of permissions. For example, some sensitive information may be described by multiple words, and using the highest permission level ensures comprehensive protection of the layer and avoids missing some sensitive information.

[0056] In some embodiments of the present application, when determining whether to re-divide the layer according to the position coordinates, it includes: Calculating the straight-line distance from each position coordinate to the same edge of the current layer and the interval distance from this edge to the opposite edge respectively. When max(di) ≤ D / 3 is satisfied, the layer is re-divided; where di represents the straight-line distance from the position coordinate to the edge i in the current layer, di = {x1, x2, x3,..., xn}, i is a positive integer; the maximum value of i is the total number of edges of the current layer, xn represents the straight-line distance from the nth position coordinate to the same edge of the current layer, max(di) represents the maximum value in the set di, and D represents the interval distance.

[0057] It should be noted that by calculating the distance from each position coordinate to the layer edge and comparing it with the edge interval distance, it is possible to intelligently determine whether the boundary of the layer needs to be adjusted. This method ensures more accurate layer division, especially when there are subtle differences in the content or critical positions.

[0058] This method dynamically adjusts the layer structure based on the distance relationship between the position coordinates and the layer edge, enabling the system to adapt to the changing content distribution. This enhances the system's adaptability to complex interfaces and avoids improper layer division caused by fixed boundaries.

[0059] When the distance between the position coordinates and the layer edge is small, by re-dividing the layer, it is possible to avoid wrongly including the content that should be assigned to other layers in the current layer, thus ensuring that the content division of the layer is more in line with the actual requirements and avoiding information omission or incorrect display.

[0060] By setting the distance threshold D / 3, the system can flexibly adjust the sensitivity of layer division. When the distance is small and the condition is met, re-division is performed to avoid unnecessary division and effectively improve the accuracy of layer division. In this way, the system can process content more efficiently, thereby enhancing the overall response speed and effect of the system.

[0061] Through precise layer division, corresponding permission levels can be more accurately assigned to each layer, ensuring that the content in each area can be protected according to the actual sensitivity. Precise division also helps to optimize the dynamic adjustment of user permissions and improve the system's adaptability to different user permissions.

[0062] By re-dividing the layer and ensuring that each area has a reasonable permission setting, chaos and leakage of content during display are avoided. After each area is correctly divided, different permissions can be managed according to its sensitivity, ensuring the security and consistency of information.

[0063] It should be noted that by selecting the maximum value among the minimum values of multiple edge distances, the sensitive area is divided at the minimum cost, ensuring that sensitive keywords are concentrated in the newly generated sub-layers, which is convenient for subsequent permission and blurring processing. The direction with the smallest division cost is preferentially selected for cutting to avoid unnecessary complex layer reconstruction and improve the real-time processing performance of the system. Through refined re-division means, sensitive information is confined to the smallest necessary area, effectively retaining more original clear content and enhancing the viewing experience of users at the viewing end. This method can automatically determine the optimal cutting boundary according to the distribution of sensitive words, enhancing the intelligence and content adaptability of layer division and being applicable to various complex sharing scenarios.

[0064] In some embodiments of the present application, when calculating the trust degree of the screen fixation point according to the clarity of the user image, it includes: Converting the user image into a grayscale image, and the clarity satisfies the following relationship: ; Set the clarity threshold to 100. When the clarity is less than or equal to 100, it is judged as low trust degree. When the clarity is greater than 100, the trust degree is calculated according to the normalization method, and the trust degree satisfies the following relationship: ; Among them, is the clarity, is the resolution of the image, which represents the product of the width and height of the image. is the pixel value at in the grayscale image, is the Laplacian value, is the average of all Laplacian values; is the confidence level, is the sharpness threshold, is the maximum sharpness.

[0065] It should be noted that calculating the image sharpness through the grayscale image + Laplacian operator can effectively identify whether the image is blurred, indirectly reflecting whether the user's line of sight is truly focused on the screen, and helping to filter out pseudo-gaze data caused by head tilting, blinking, or camera occlusion. Introducing the sharpness threshold and the normalized scoring mechanism does not simply make a binary judgment on the validity of the gaze, but assigns the confidence level according to the continuity of the image quality, making the subsequent permission adjustment smoother and more fault-tolerant. This method only depends on the image grayscale and edge sharpness, has low requirements for device conditions such as camera resolution, has strong adaptability, and can work stably in different device and network environments. Linking the user image sharpness with the gaze point confidence level provides a quantitative basis for permission adjustment, improving the decision-making rationality and security of the system in "fuzzy control" and "sensitive area access".

[0066] In some embodiments of the present application, according to the relationship between the screen gaze point and each layer, the user permission level is adjusted to obtain the corrected user permission, including: Obtain the layer where the screen gaze point is located, and calculate the residence time staying in the layer where it is located. When the preset time threshold is met, determine whether the layer where it is located contains sensitive keywords; if not, replace the user permission level with the corrected user permission; if so, perform the following steps: Obtain the screen gaze points of the remaining viewing ends, denoted as reference gaze points, count the number of reference gaze points in the layer where it is located, and calculate the attention degree of the layer where it is located. The attention degree is the ratio of the number of reference gaze points in the layer where it is located to the total number of viewing ends; when the ratio is less than the attention threshold, lower the user permission level of the viewing end corresponding to the screen gaze point by one level, and denote it as the corrected user permission; when the ratio is greater than or equal to the attention threshold, use the user permission level as the corrected user permission.

[0067] It should be noted that for the value of the attention threshold, the optimal value range can be obtained through repeated experiments. By monitoring the fixation duration of the user in a certain area (layer), the permission detection is triggered only when the duration meets the predetermined threshold, thus avoiding misjudgment due to momentary accidental fixation and ensuring the real-time and stability of permission adjustment. When the layer contains sensitive keywords, the system further obtains the fixation data of other viewer users, counts the number of reference fixation points and calculates the attention degree. This mechanism ensures that the permission of the corresponding user is downgraded by one level only when there is an abnormal concentration and low attention degree in this area, so as to achieve more strict control of sensitive content. By obtaining the reference fixation points of other viewer users and using the ratio of the number of reference fixation points to the total number of viewers as the attention degree index, the system can "draw on" group behavior to judge whether an individual user has abnormal behavior of attempting to peep at highly sensitive information, and then dynamically adjust their permissions. This method fully considers individual operations and also takes into account the overall security strategy. When the layer does not contain sensitive keywords, the user permission is directly replaced with the corrected permission, avoiding excessive blurring of irrelevant content, thus improving the overall readability and user experience of screen content sharing. This method forms a closed-loop feedback mechanism by collecting and analyzing user fixation behavior data in real time: the user's fixation behavior affects permission adjustment, and the permission adjustment further affects the blurred presentation of screen content, ensuring that the system can adapt to changing user behaviors and scenario requirements and provide continuous and effective security protection.

[0068] In some embodiments of the present application, when adjusting the user permission level according to the screen fixation points of the screen sharing end and the viewing end to obtain the final user permission, it includes: When the screen fixation points of the screen sharing end and the viewing end are in the same layer, the corrected user permission of the viewing end is used as the final user permission; When the screen fixation points of the screen sharing end and the viewing end are not in the same layer, calculate the fixation duration, and when the time threshold is met, downgrade the corrected user by one level to obtain the final user permission.

[0069] In addition, when the user permission level changes, adjust the blur degree of the layer to the highest.

[0070] 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, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for dynamically blurring screen content based on user permission verification, characterized in that, include: Collecting the original screen content of the screen sharing terminal, dividing the original screen content into a plurality of regions, inputting each of the regions into a different layer, and assigning a target permission level to the layer according to the original screen content in each of the regions; Obtaining the user authority level of each user at the viewing end, comparing the user authority level with the target authority level of each layer, and performing fuzzy processing on the layers whose user authority level is lower than the target authority level; The blurred layer is superimposed with the remaining unblurred layer to form blurred screen content, and the blurred screen content is pushed; Collecting user images of the viewing end after receiving the blurred screen content according to the time series, determining the screen gaze point of the viewing end user based on the eye tracking technology; calculating the trustworthiness of the screen gaze point according to the clarity of the user image; According to the relationship between the screen gaze point and each of the layers, the user authority level is adjusted to obtain a modified user authority; Collecting a user portrait of the screen sharing terminal according to the time series, determining the screen gaze point according to the user image, and adjusting the user authority level according to the screen gaze points of the screen sharing terminal and the viewing terminal to obtain the final user authority; Subsequent blurred screen content is pushed according to the end-user permissions and the target permission level.

2. The method for dynamically blurring screen content based on user permission verification according to claim 1, wherein When the original screen content is recognized and divided into several areas, including: The window borders in the original screen content are obtained based on Canny edge detection, the area enclosed by all the window borders is calculated, the window border with the smallest area is selected and input into a layer, and the content of the window border is removed from the original screen content, and the window border with the smallest area is selected again and input into another layer, and the selection is repeated until the original screen content is completely divided.

3. The method for dynamically blurring screen content based on user permission verification according to claim 2, wherein When assigning a target permission level to the layer according to the original screen content in each of the regions, including: Establishing a sensitive word library, the sensitive word library includes sensitive keywords and corresponding viewing permission levels; Performing OCR text recognition and application interface feature recognition on the original screen content in each layer to determine whether the layer contains sensitive keywords or a preset specific application program interface; When it is determined that the preset feature application interface is included, the maximum target permission level is assigned to the current layer; when it is determined that the sensitive keywords and the preset specific application interface are not included, the minimum target permission level is assigned to the current layer; When it is determined that only sensitive keywords are included, the position coordinates of the sensitive keywords in the current layer are obtained, and it is determined whether to re-divide the layer according to the position coordinates.

4. The method for dynamically blurring screen content based on user permission verification according to claim 3, wherein When there is no need to redivide the layers or the layers have been redivided, the viewing permission level corresponding to each sensitive keyword is obtained according to the sensitive word library, the highest viewing permission level is selected, and the highest viewing permission level is used as the target permission level of the current layer.

5. The method for dynamically blurring screen content based on user permission verification according to claim 4, characterized in that, When determining whether to re-divide the layers according to the position coordinates, it includes: Calculate the straight-line distance from each of the position coordinates to the same edge of the current layer and the interval distance from this edge to the opposite edge. When max(di) ≤ D / 3 is satisfied, re-partition the layer; where di represents the straight-line distance from the position coordinate to edge i in the current layer, di = {x1, x2, x3,..., xn}, i is a positive integer; the maximum value of i is the total number of edges of the current layer, xn represents the straight-line distance from the nth position coordinate to the same edge of the current layer, and max(di) represents the maximum value in the set di, and D represents the interval distance.

6. The method for dynamically blurring screen content based on user permission verification according to claim 5, wherein, When re-partitioning the layer, it includes: When multiple max(di) are all less than or equal to D / 3, select the smallest max(di), and divide the current layer into two sub-layers, where one sub-layer contains all sensitive keywords.

7. The method for dynamically blurring screen content based on user permission verification according to claim 6, wherein, When calculating the trust level of the screen fixation point based on the clarity of the user image, it includes: Convert the user image into a grayscale image, and the clarity satisfies the following relationship: ； Set the clarity threshold to 100. When the clarity is less than or equal to 100, it is judged as low trust level. When the clarity is greater than 100, calculate the trust level according to the normalization method, and the trust level satisfies the following relationship: ； Among them, For clarity, is the resolution of the image, which represents the product of the width and height of the image, in the grayscale image is the pixel value at, is the Laplacian value, is the average value of all Laplacian values; is the confidence level, is the clarity threshold, is the maximum clarity.

8. The method for dynamically blurring screen content based on user permission verification according to claim 7, characterized in that Adjust the user permission level according to the relationship between the screen fixation point and each layer to obtain the corrected user permission, including: Obtain the layer where the screen fixation point is located, and calculate the stay time in the layer where it is located. When the preset time threshold is satisfied, judge whether the layer where it is located contains sensitive keywords; if not, replace the user permission level with the corrected user permission; if so, perform the following steps: Obtain the screen fixation points of the other viewing ends, denoted as reference fixation points, count the number of reference fixation points in the layer where it is located, and calculate the attention degree of the layer where it is located. The attention degree is the ratio of the number of reference fixation points in the layer where it is located to the total number of viewing ends; when the ratio is less than the attention threshold, lower the user permission level of the viewing end corresponding to the screen fixation point by one level, and denote it as the corrected user permission; when the ratio is greater than or equal to the attention threshold, use the user permission level as the corrected user permission.

9. The method for dynamically blurring screen content based on user permission verification according to claim 8, wherein, When adjusting the user permission level based on the screen fixation points of the screen sharing end and the viewing ends to obtain the final user permission, it includes: When the screen fixation points of the screen sharing end and the viewing ends are in the same layer, use the corrected user permission of the viewing end as the final user permission; When the screen fixation points of the screen sharing end and the viewing ends are not in the same layer, calculate the stay time. After the time threshold is satisfied, lower the corrected user by one level to obtain the final user permission.

10. The method for dynamically blurring screen content based on user permission verification according to claim 9, wherein, It also includes: When the user permission level changes, adjust the blur degree of the layer to the highest.

Images