A method and apparatus for masking screen information

Abstract

The application discloses a kind of screen information's screening method and device, it is related to computer technology field.The specific embodiment of the method includes: obtaining the front environment data and display content data corresponding to screen and the line-of-sight tracking data of authorized user;Information threat level is determined based on front environment data;Determine the privacy information area in display content data and the sensitivity level corresponding to privacy information area;According to line-of-sight tracking data, generate the fixation heat map corresponding to authorized user;Information screening strategy of screen is determined based on information threat level, the sensitivity level corresponding to privacy information area and fixation heat map, to carry out information screening processing to screen according to information screening strategy.This embodiment realizes the dynamic grading privacy screening of screen display content, both protect privacy security, different information screening strategies can be used for differential processing, also retains the peripheral visual experience of user, improves the reading fluency of user.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a method and apparatus for masking screen information. Background Technology

[0002] When users access private content through a single-screen device in various scenarios (such as offices, cafes, subways, airplanes, etc.), existing privacy protection technologies primarily employ traditional privacy screens (such as physical privacy films) or "spotlight" modes (such as AMD Privacy View) to obscure the private content in order to protect user privacy from being leaked. Traditional privacy screens can only globally restrict viewing angle obstruction and cannot provide differentiated processing; additionally, the "spotlight" mode only keeps the area the user is looking at clear, blurring the rest of the area, disrupting the user's peripheral vision and affecting reading fluency. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and apparatus for masking screen information. By integrating three dimensions—foreground environment detection, user gaze tracking, and content sensitivity level—dynamic hierarchical privacy masking of screen display content is achieved. This not only protects privacy and security but also allows for differentiated processing using different information masking strategies. At the same time, it preserves the user's surrounding visual experience and improves the user's reading fluency.

[0004] To achieve the above objectives, according to one aspect of the present invention, a method for masking screen information is provided, comprising: Acquire data on the foreground environment and displayed content corresponding to the screen, as well as eye-tracking data of authorized users; Determine the information threat level based on the foreground environmental data; determine the privacy information areas in the displayed content data and the corresponding sensitivity levels of the privacy information areas; generate gaze heatmaps for authorized users based on gaze tracking data; Based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, the information masking strategy of the screen is determined, so as to mask the information of the screen according to the information masking strategy.

[0005] Optionally, acquire the ambient data corresponding to the screen, including: The front-facing camera corresponding to the screen is invoked to collect environmental image data of the area in front of the screen in order to obtain the environmental data in front of the screen. Obtain eye-tracking data from authorized users, including: The system utilizes the front-facing camera or infrared gaze sensor on the screen to collect eye movement information from authorized users and generates gaze tracking data based on this information.

[0006] Optionally, the information threat level can be determined based on data from the surrounding environment, including: Based on the environmental data in front of the screen, determine the number of unauthorized personnel in the area in front of the screen, and determine the personnel risk result based on the number of unauthorized personnel. Based on the data of the surrounding environment, determine the line of sight of unauthorized personnel, and determine the risk of spying based on the line of sight information. Based on the environmental data, the recording equipment is tested to obtain the recording risk results; The information threat level is determined based on the risk results from personnel, spying, and recording.

[0007] Optionally, determine the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area, including: The displayed content data is analyzed and processed to obtain multiple display content areas; Each display content area is matched with a preset privacy information database, and the privacy information area on the screen and its corresponding privacy information type are determined based on the matching results. Determine the sensitivity level of the privacy information area based on the type of privacy information.

[0008] Optionally, a gaze heatmap for authorized users is generated based on gaze tracking data, including: Determine the current gaze area of ​​the authorized user based on eye-tracking data; The current gaze area is designated as the first central region; The surrounding adjacent area and visual edge area corresponding to the first central area are determined according to the preset distance conditions; A gaze heatmap is generated based on the first central region and its corresponding surrounding adjacent regions and visual edge regions.

[0009] Optionally, generating a gaze heatmap for authorized users based on gaze tracking data also includes: Based on the current gaze area, a preset gaze prediction algorithm is used to determine the target gaze area of ​​the authorized user within a preset time period in the future; The target gaze area is defined as the second central area; The surrounding adjacent area and visual edge area corresponding to the second central area are determined according to the preset distance conditions; The gaze heatmap is updated based on the second central region and its corresponding surrounding adjacent regions and visual edge regions.

[0010] Optionally, a screen information masking strategy is determined based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, including: The screen's masking strength is determined based on the information threat level. The information replacement mode for the privacy information area on the screen is determined based on the sensitivity level corresponding to the privacy information area. Determine the Gaussian blur gradient corresponding to the screen based on the gaze heatmap; An information occlusion strategy is generated based on the occlusion intensity, information replacement mode, and Gaussian blur gradient of the screen.

[0011] According to a second aspect of the present invention, a screen information masking device is provided, comprising: The acquisition module is used to acquire data on the foreground environment and displayed content corresponding to the screen, as well as eye tracking data of authorized users. The determination module is used to determine the information threat level based on the data of the foreground environment; determine the privacy information area in the displayed content data and the sensitivity level of the privacy information area; and generate a gaze heatmap for authorized users based on gaze tracking data. The masking module is used to determine the information masking strategy of the screen based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy.

[0012] According to a third aspect of the present invention, an electronic device is provided, comprising: One or more processors; Memory, used to store one or more programs. When one or more programs are executed by one or more processors, the one or more processors implement the methods of any of the above embodiments.

[0013] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method of any of the above embodiments.

[0014] According to a fifth aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0015] One embodiment of the above invention has the following advantages or beneficial effects: It acquires foreground environmental data, display content data, and authorized user gaze tracking data corresponding to the screen; determines the information threat level based on the foreground environmental data; determines the privacy information area and the corresponding sensitivity level of the privacy information area in the display content data; generates a gaze heatmap corresponding to the authorized user based on the gaze tracking data; and determines the screen's information masking strategy based on the information threat level, the sensitivity level of the privacy information area, and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy. By integrating three dimensions—foreground environmental detection, user gaze tracking, and content sensitivity level—dynamic hierarchical privacy masking of the screen display content is achieved, which not only protects privacy and security but also allows for differentiated processing using different information masking strategies, while preserving the user's surrounding visual experience and improving the user's reading fluency.

[0016] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0017] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of the main flow of the screen information masking method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the system architecture of a screen information masking system according to a preferred embodiment of the present invention; Figure 3 This is a schematic diagram of the main process of information threat level assessment according to a preferred embodiment of the present invention; Figure 4 This is a schematic diagram of the main process of content sensitivity classification according to a preferred embodiment of the present invention; Figure 5 This is a schematic diagram of the main process of screen visual partitioning and progressive occlusion rendering according to a preferred embodiment of the present invention; Figure 6 This is a timing diagram of line-of-sight prediction and pre-clarification processing according to a preferred embodiment of the present invention; Figure 7 This is a schematic diagram of the main modules of the screen information masking device according to an embodiment of the present invention; Figure 8 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 9 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0018] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0019] It should be noted that the acquisition, storage, and application of personal information involved in the embodiments of the present invention comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0020] When users access private content through a single-screen device in various scenarios (such as offices, cafes, subways, airplanes, etc.), existing privacy protection technologies primarily employ traditional privacy screens (such as physical privacy films) or "spotlight" modes (such as AMD Privacy View) to obscure the private content in order to protect user privacy from being leaked. Traditional privacy screens can only globally restrict viewing angle obstruction and cannot provide differentiated processing; additionally, the "spotlight" mode only keeps the area the user is looking at clear, blurring the rest of the area, disrupting the user's peripheral vision and affecting reading fluency.

[0021] In view of this, according to one aspect of the present invention, a method for masking screen information is provided.

[0022] Figure 1 This is a schematic diagram illustrating the main flow of a screen information masking method according to an embodiment of the present invention. Figure 1 As shown, the screen information masking method according to an embodiment of the present invention includes the following steps S101 to S103.

[0023] Step S101: Obtain the foreground environment data, display content data, and eye tracking data of the authorized user corresponding to the screen.

[0024] In this embodiment, the foreground environment data is used to characterize the state of the environment in front of the screen, including but not limited to environmental image information, personnel information, personnel location distribution information, personnel gaze direction information, and recording device related information. Display content data refers to the image data currently output to the screen for display, including but not limited to text content, image content, video content, interface elements, and application interface layout information. Authorized user gaze tracking data refers to data reflecting the authorized user's gaze movement state, including but not limited to eye feature information, gaze point coordinates, gaze direction information, and gaze movement trajectory information.

[0025] When acquiring foreground environmental data corresponding to the screen, a front-facing camera mounted on the screen can be used to continuously collect environmental image data of the area in front of the screen. The collected environmental image data can then be analyzed to obtain personnel information, personnel location distribution information, and recording device information, thereby generating foreground environmental data. Alternatively, a depth camera, millimeter-wave radar, or infrared sensor can be used to acquire depth information and target detection information of the area in front of the screen, and then fused with the environmental images for analysis, thereby improving the accuracy of acquiring foreground environmental data in complex environments.

[0026] When acquiring display content data, the display content data corresponding to the current display content can be obtained by extracting the display data from the graphics rendering pipeline, display buffer, or video stream output unit.

[0027] When acquiring eye tracking data of authorized users, the front-facing camera or infrared gaze sensor can be used to collect eye movement information of authorized users. Based on the pupil center position, eye movement state, and facial posture information, the coordinates of the gaze point and the direction of gaze of the authorized user can be determined, thereby generating eye tracking data of authorized users.

[0028] Step S102: Determine the information threat level based on the foreground environment data; determine the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area; generate a gaze heatmap corresponding to the authorized user based on the gaze tracking data.

[0029] In this embodiment, the information threat level refers to the level of risk information used to characterize the degree to which the current screen content is accessed by unauthorized personnel, such as low threat level, medium threat level, high threat level, or extreme threat level, etc. The privacy information area refers to the display area containing privacy information in the displayed content data, such as password input area, financial account information area, identity information area, chat history area, or email content area, etc. The sensitivity level corresponding to the privacy information area refers to the importance level of the privacy information, such as public level, low sensitivity level, medium sensitivity level, highest sensitivity level, etc. The gaze heatmap is used to characterize the distribution of authorized users' attention to various display areas on the screen.

[0030] When determining the information threat level based on the foreground environment data, face detection processing can be performed on the foreground environment data to identify authorized users and unauthorized personnel in front of the screen. The number, location, and direction of gaze of unauthorized personnel can be analyzed to determine the information threat level based on whether unauthorized personnel are engaging in spying behavior. Additionally, recording devices in the foreground environment can be detected, and the information threat level can be determined in conjunction with the detection results.

[0031] When determining the privacy information areas in the displayed content data and the corresponding sensitivity levels of the privacy information areas, preset privacy recognition rules can be used to identify privacy information areas such as password input boxes, bank card numbers, and ID card information, and the corresponding sensitivity levels can be determined according to the type of privacy information; alternatively, a pre-trained information recognition model can be used to identify privacy information areas and determine the corresponding sensitivity levels.

[0032] When generating a gaze heatmap for an authorized user based on gaze tracking data, the current gaze area can be determined based on the gaze tracking data, and a gaze heatmap can be generated based on the distance between each display area and the current gaze area; it can also predict the target gaze area by combining historical gaze trajectories, and dynamically generate a gaze heatmap based on the current gaze area and the target gaze area.

[0033] Step S103: Determine the information masking strategy for the screen based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy.

[0034] In this embodiment, the information masking strategy refers to a display control scheme generated based on the current information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap corresponding to the authorized user, which is used to determine the information protection method and protection strength corresponding to each display area; the above information masking strategy may include one or more of the following: clear display, progressive blurring display, content replacement display, watermark overlay display, content hiding display, or warning information display.

[0035] Specifically, the system can first determine the central attention area, surrounding attention area, and edge attention area based on the gaze heatmap. Then, based on the sensitivity level of the privacy information area, the target protection level corresponding to each privacy information area can be determined. Finally, combined with the information threat level, the masking method and masking intensity corresponding to each display area can be determined to generate an information masking strategy. In addition, a strategy mapping relationship between information threat level, sensitivity level, and attention level can be established. By querying a preset strategy mapping table or calling a pre-trained strategy decision model, the corresponding information masking strategy can be directly output.

[0036] When performing information masking processing on the screen according to the determined information masking strategy, different intensity of Gaussian blur processing can be applied to different display areas, so that the displayed content is gradually blurred from the central area of ​​interest to the edge area; content replacement processing can also be performed on privacy information areas corresponding to high sensitivity levels, replacing the original content with preset placeholder content, and superimposing digital watermarks or interference patterns when a recording device is detected, thereby achieving dynamic information masking processing of the displayed content.

[0037] This embodiment acquires foreground environmental data, displayed content data, and authorized user gaze tracking data corresponding to the screen; determines the information threat level based on the foreground environmental data; identifies privacy information areas and their corresponding sensitivity levels within the displayed content data; generates a gaze heatmap for the authorized user based on the gaze tracking data; and determines a screen information masking strategy based on the information threat level, the sensitivity level of the privacy information areas, and the gaze heatmap, thereby masking the screen information accordingly. By integrating foreground environmental detection, user gaze tracking, and content sensitivity level, dynamic hierarchical privacy masking of the screen display content is achieved. This protects privacy and allows for differentiated processing using different information masking strategies, while also preserving the user's surrounding visual experience and improving reading fluency.

[0038] Optionally, obtaining the foreground environment data corresponding to the screen includes: calling the front-facing camera corresponding to the screen and using the front-facing camera to collect environmental image data of the area in front of the screen to obtain the foreground environment data corresponding to the screen; obtaining the eye tracking data of the authorized user includes: calling the front-facing camera or infrared eye-tracking sensor corresponding to the screen, collecting the eye movement information of the authorized user based on the front-facing camera or infrared eye-tracking sensor, and generating eye tracking data based on the eye movement information.

[0039] In this optional embodiment, when acquiring the foreground environmental data corresponding to the screen, the front-facing camera set on the screen is first invoked to continuously collect environmental image data of the area in front of the screen, and the environmental image data is preprocessed to eliminate the influence of factors such as lighting changes and image noise; then, personnel target features, position features, and environmental features are extracted from the preprocessed environmental image data to generate foreground environmental data that reflects the state of the environment in front of the screen. When acquiring the authorized user's gaze tracking data, the front-facing camera or infrared gaze sensor is invoked to collect the authorized user's eye movement information, and the eye movement information is processed by pupil positioning, eye movement analysis, and facial posture analysis to determine the authorized user's gaze point position, gaze direction, and gaze movement trajectory, thereby generating gaze tracking data. Environmental perception and gaze tracking can be completed using the existing hardware of the screen without the need for additional complex equipment, which can reduce system deployment costs and improve the real-time performance of environmental perception.

[0040] As another embodiment, when acquiring the foreground environment data corresponding to the screen, depth cameras, infrared cameras, or millimeter-wave radar can be used to obtain depth information, target distance information, and motion state information of the area in front of the screen. This information is then fused and analyzed with environmental image data to generate foreground environment data, thereby improving target detection accuracy in complex lighting environments, occluded environments, and multi-person scenarios. When acquiring the authorized user's gaze tracking data, multiple infrared emitters and receivers positioned at the screen edge can be used to construct an eye-tracking area. By analyzing the reflection characteristics of infrared light in the eye area, the pupil center position and eye movement state are determined. Combined with head posture information, the authorized user's gaze point position and gaze movement trajectory are calculated to generate gaze tracking data. This implementation reduces the impact of ambient light changes on gaze tracking accuracy and improves the stability and accuracy of gaze tracking data.

[0041] Optionally, determining the information threat level based on the foreground environmental data includes: determining the number of unauthorized personnel in the area in front of the screen based on the foreground environmental data, and determining the personnel risk result based on the number of unauthorized personnel; determining the gaze direction information corresponding to the unauthorized personnel based on the foreground environmental data, and determining the spying risk result based on the gaze direction information; detecting recording devices based on the foreground environmental data to obtain the recording risk result; and determining the information threat level based on the personnel risk result, the spying risk result, and the recording risk result.

[0042] In this embodiment, target detection and identity recognition are first performed on the foreground environmental data to identify unauthorized personnel and their numbers in the area in front of the screen. The personnel risk is determined based on the number of unauthorized personnel, their distance from the screen, and their duration of stay. Next, the facial and eye orientations of the unauthorized personnel are analyzed to determine their gaze direction. The spatial relationship between the gaze direction and the screen position is used to determine whether voyeurism is occurring, thus determining the voyeurism risk. Further, recording device detection is performed on the foreground environmental data. By identifying features such as camera lens reflections, device appearance, or infrared reflections, the recording risk is determined. Finally, the personnel risk, voyeurism risk, and recording risk are fused and analyzed. For example, a weighted calculation or rule-matching method is used to generate a comprehensive risk value, and the corresponding information threat level is determined based on this comprehensive risk value. By simultaneously considering personnel risk, voyeurism risk, and recording risk, the information leakage risk in the current environment can be more comprehensively reflected, improving the accuracy and reliability of the information threat level assessment results.

[0043] In another embodiment, an environmental risk assessment model can be constructed, using the surrounding environmental data as input. The pre-trained environmental risk assessment model directly outputs the corresponding information threat level. This implementation method can comprehensively utilize multi-dimensional environmental features to achieve dynamic risk assessment, improving the intelligence level and environmental adaptability of information threat level determination results in complex scenarios.

[0044] Optionally, determining the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area includes: performing content analysis processing on the displayed content data to obtain multiple displayed content areas; matching each displayed content area with a preset privacy information database, and determining the privacy information area on the screen and its corresponding privacy information type based on the matching result; and determining the sensitivity level corresponding to the privacy information area based on the privacy information type.

[0045] In this embodiment, the displayed content data is first analyzed. The text content, image content, form controls, interface elements, and application windows in the current display screen are parsed, and the displayed content data is divided into multiple display content areas based on the content layout and interface structure. The text features, image features, and interface features in each display content area are matched against a preset privacy information database. This database may include features related to password information, bank card information, identity information, chat logs, emails, and confidential corporate information. Based on the matching results, the corresponding privacy information areas and their corresponding privacy information types are determined, and the corresponding sensitivity levels are determined according to the risk level rules corresponding to the privacy information types. For example, password information and financial account information correspond to a higher sensitivity level, chat logs and email content correspond to a medium sensitivity level, and ordinary web page content corresponds to a lower sensitivity level. By performing regional analysis and hierarchical identification of the displayed content, the privacy information areas that need protection can be accurately located, avoiding the uniform obscuring of all displayed content. This improves screen display effects and user experience while ensuring information security.

[0046] As another embodiment, a pre-trained privacy information recognition model can be used to analyze and process the displayed content data, extracting text semantic features, image semantic features, and interface context features from the displayed content data. Based on the extraction results, privacy information areas and their corresponding privacy information types are identified. Then, combined with a preset sensitivity assessment model, factors such as privacy information type, information quantity, information completeness, and application scenario are comprehensively considered to determine the corresponding sensitivity level. This implementation method can improve the accuracy of privacy information recognition and the intelligence level of sensitivity level assessment in complex display scenarios.

[0047] Optionally, generating a gaze heatmap corresponding to the authorized user based on gaze tracking data includes: determining the current gaze area corresponding to the authorized user based on gaze tracking data; determining the current gaze area as a first central area; determining the surrounding adjacent area and visual edge area corresponding to the first central area based on preset distance conditions; and generating a gaze heatmap based on the first central area and the surrounding adjacent area and visual edge area corresponding to the first central area.

[0048] In this embodiment, the gaze tracking data is first analyzed to determine the current gaze point position and corresponding gaze area of ​​the authorized user. The current gaze area can be determined based on the gaze point coordinates, gaze duration, and gaze stability. Then, the current gaze area is designated as the first central region, and a visual attention range model is established based on this first central region. Further, the distance relationship between each display area on the screen and the first central region is calculated according to preset distance conditions. Areas closer to the first central region are designated as surrounding adjacent areas, and areas farther from the first central region are designated as visual edge regions. Subsequently, a gaze heatmap is generated based on the attention distribution corresponding to the first central region, surrounding adjacent areas, and visual edge regions. The first central region corresponds to the highest attention level, the surrounding adjacent areas to the medium attention level, and the visual edge regions to the lowest attention level. The gaze heatmap generated in this way can realistically reflect the current visual attention state of the authorized user, providing a basis for subsequent differentiated information occlusion, ensuring that the centrally focused content is clearly displayed while also considering peripheral visual perception, thereby avoiding the visual disjointedness caused by traditional spotlight-style occlusion methods.

[0049] Optionally, generating a gaze heatmap corresponding to an authorized user based on gaze tracking data further includes: determining the target gaze area of ​​the authorized user within a preset time period based on the current gaze area using a preset gaze prediction algorithm; defining the target gaze area as a second central area; determining the surrounding adjacent area and visual edge area corresponding to the second central area based on preset distance conditions; and updating the gaze heatmap based on the second central area and the surrounding adjacent area and visual edge area corresponding to the second central area.

[0050] As another embodiment, the gaze movement trend can be determined by combining the authorized user's historical gaze trajectory information within a preset time period, and the target gaze area corresponding to the authorized user can be predicted. The current gaze area and the target gaze area are jointly regarded as high attention areas, and a dynamic attention distribution model is constructed based on their corresponding attention weights to generate a dynamically updated gaze heatmap. When the authorized user's gaze moves, the current gaze area and the target gaze area are dynamically updated, and the gaze heatmap is updated synchronously. This implementation can not only reflect the authorized user's current attention position, but also predict the display area that the authorized user may pay attention to in advance, thereby providing a basis for the pre-rendering, pre-caching, and pre-clarification processing of subsequent display content, reducing display latency during gaze switching, and improving the continuity of screen display and user experience.

[0051] In other embodiments, the gaze frequency and dwell time of each display area can be statistically analyzed based on historical gaze trajectory data within a preset time period, and an attention distribution model can be constructed based on the statistical results to generate a gaze heatmap corresponding to the authorized user, thereby reflecting the long-term visual attention characteristics of the authorized user.

[0052] Optionally, the information masking strategy for the screen is determined based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, including: determining the masking intensity corresponding to the screen based on the information threat level; determining the information replacement pattern of the privacy information area in the screen according to the sensitivity level corresponding to the privacy information area; determining the Gaussian blur gradient corresponding to the screen based on the gaze heatmap; and generating the information masking strategy according to the masking intensity, information replacement pattern, and Gaussian blur gradient corresponding to the screen.

[0053] In this embodiment, the corresponding masking strength is determined based on the information threat level. Higher threat levels correspond to greater masking strength; for example, high-threat-level areas receive deep protection, medium-threat-level areas receive moderate protection, and low-threat-level areas receive no masking. The information replacement mode is determined based on the sensitivity level of the privacy information area. For example, for privacy information areas corresponding to high sensitivity levels, methods such as placeholder content replacement, desensitized display, or hidden display can be used for protection; for privacy information areas corresponding to lower sensitivity levels, partial blurring or maintaining display can be used. Furthermore, the Gaussian blur gradient corresponding to the screen is determined based on the gaze heatmap. Different blur intensities are determined according to the attention level of each display area, ensuring the currently gazed area remains clearly displayed, while surrounding areas use lower blur intensities and visual edge areas use higher blur intensities. Finally, the masking strength, information replacement mode, and Gaussian blur gradient are fused to generate the corresponding information masking strategy. By simultaneously combining environmental risk, information sensitivity, and user visual attention status for joint decision-making, differentiated and dynamic information protection can be achieved, minimizing the impact on normal browsing experience while ensuring privacy security.

[0054] As another embodiment, when determining the screen information masking strategy based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, a strategy decision model can also be constructed. This model takes the information threat level, sensitivity level, and gaze heatmap as input and outputs the corresponding information masking strategy through a pre-trained strategy decision model. The information masking strategy can include one or more of the following processing methods: blurred display, watermark overlay, content replacement, content hiding, and warning display, thereby improving the intelligence level and scene adaptability of the information masking strategy generation process.

[0055] In a preferred embodiment of the present invention, a screen privacy masking method is provided, applicable to display architectures where the screen device and core device are separated. The screen device is used for environmental perception and user gaze perception, while the core device is used for content analysis, privacy decision-making, and information masking processing. By constructing a four-layer collaborative architecture consisting of an environmental perception layer, a gaze tracking layer, a content analysis layer, and a hierarchical masking execution layer, dynamic privacy protection of displayed content is achieved, ensuring information security while also considering the user's normal visual experience.

[0056] In the environmental perception layer, the screen device uses a front-facing wide-angle camera positioned on the front of the screen to collect real-time environmental image data of the area in front of the screen, thus acquiring foreground environmental data. This data is then analyzed and processed using computer vision technology. Specifically, face detection is performed on the environmental image data. The face detection results or device binding information are used to distinguish authorized users from unauthorized personnel, and the number of unauthorized personnel is counted. Further, for unauthorized personnel, their facial and eye orientation information is analyzed to determine whether their gaze is directed towards the screen, thereby identifying any voyeuristic behavior. Simultaneously, recording device detection is performed on the environmental image data, using lens reflection characteristics, infrared reflection characteristics, device appearance characteristics, or pre-trained target recognition models to identify mobile phone cameras, hidden cameras, or other recording devices in the environment. The corresponding information threat level is determined based on the number of unauthorized personnel, voyeuristic behavior, and recording device detection results. Specifically, a low threat level is defined as follows: no unauthorized personnel are detected, or the detected unauthorized personnel are not looking at the screen; a medium threat level is defined as the presence of a small number of unauthorized personnel (e.g., 1 or 2, adjustable according to requirements) whose gaze is directed at the screen; and a high threat level is defined as the detection of multiple unauthorized personnel (e.g., more than 3, adjustable according to requirements) whose gaze is directed at the screen, unauthorized personnel continuously approaching the screen, or a recording device being detected. This method allows for a comprehensive assessment of the information leakage risk in the current scenario from multiple dimensions, including personnel risk, spying risk, and recording risk.

[0057] In the gaze tracking layer, the screen device uses a front-facing camera or infrared gaze sensor to collect the coordinates of the authorized user's gaze point in real time, determining the user's current gaze area. Simultaneously, combined with a pre-set gaze prediction algorithm, it predicts the target gaze area the authorized user might focus on within a preset timeframe. For example, when the authorized user is reading a document, the location of the next line or paragraph can be predicted based on the current reading position, reading direction, and page layout. A gaze heatmap is constructed based on the current gaze area and the target gaze area, where the current and target gaze areas correspond to high-attention areas, the surrounding adjacent areas correspond to medium-attention areas, and the visual edge areas correspond to low-attention areas. The gaze heatmap generated in this way not only reflects the authorized user's current visual focus position but also anticipates future visual attention trends, thus providing a basis for subsequent information occlusion processing.

[0058] In the content analysis layer, the core device acquires real-time display content data and performs content analysis processing. This core device can be a cloud service, a personal computer, an edge box, etc. Specifically, it identifies and parses text content, image content, interface elements, and application windows in the display content data to determine the privacy information areas and their corresponding privacy information types. Based on the privacy information type, these areas are divided into multiple sensitivity levels. S1 sensitivity level corresponds to the highest sensitivity information, including password input fields, bank card numbers, ID card photos, and confidential document titles; S2 sensitivity level corresponds to medium sensitivity information, including personal chat logs, email text, and contact lists; S3 sensitivity level corresponds to low sensitivity information, including ordinary web page content, media playback screens, and system interface elements; and S0 public level corresponds to information that does not require protection, including publicly displayed content such as wallpapers, clocks, and status bars. Simultaneously, the core device can also distinguish between dynamic and static content areas, such as identifying video playback windows, dynamic image areas, and ordinary text areas, thus supporting the subsequent use of differentiated information masking methods.

[0059] In the hierarchical masking execution layer, the core device generates an information masking strategy based on the overall information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap. It then performs dynamic information masking processing on the displayed content according to the generated strategy. When the information threat level is low, no information masking processing is performed, and all displayed content remains clear. When the information threat level is medium, the currently gazed area remains clear, the surrounding adjacent areas undergo slight blurring, the S1 sensitivity level area in the visual edge area undergoes information masking processing, and the remaining areas remain normally displayed. When the information threat level is high, the currently gazed area remains clear, the surrounding adjacent areas undergo moderate blurring, the visual edge area undergoes overall blurring, and content replacement processing is performed on the privacy information area corresponding to the S1 sensitivity level. When the information threat level is extreme, the currently gazed area remains clear and an invisible digital watermark is superimposed, the surrounding adjacent areas undergo high blurring and a digital watermark is superimposed, and the visual edge area undergoes black screen processing or is replaced with warning information. Furthermore, a progressive Gaussian blurring strategy can be used during the information masking process. Specifically, the Gaussian blur coefficient is determined based on the distance between the display area and the current gaze area, causing the displayed content to gradually increase in blur from the current gaze area towards the visual edge, thus creating a progressive blur effect that conforms to the human eye's visual attenuation law. Compared to traditional spotlight-style privacy protection schemes, this method preserves the peripheral visual perception ability of authorized users, allowing them to still observe interface changes, page structure, and contextual content using their peripheral vision, thereby significantly improving reading continuity and user comfort. Furthermore, for privacy information areas corresponding to the S1 sensitivity level, when unauthorized personnel are detected peeping, content replacement can be used instead of traditional blurring methods. For example, the original content can be replaced with preset placeholder content, desensitized content, or sensitive information prompts. Through content replacement, even if unauthorized personnel observe the corresponding area, they cannot infer the original information content from the blurred outline, thereby further improving the protection capability of highly sensitive information. Furthermore, when a recording device is detected, anti-recording protection processing can also be performed. For example, embedding invisible digital watermarks in the video stream corresponding to the displayed content, or overlaying interference patterns that are difficult for the human eye to perceive but can be captured by camera equipment on the screen display content, thereby reducing the usability of the recorded content and preventing the displayed content from being illegally photographed, recorded or disseminated.

[0060] The above technical solutions can achieve a balance between information security and visual experience, effectively preventing human eye peeping and device recording while preserving the normal visual perception ability of authorized users; they can implement differentiated protection according to different sensitivity levels, avoiding uniformly obscuring all displayed content and affecting normal use; they can perceive environmental threats from multiple dimensions such as personnel risk, peeping risk, and recording risk, adapting to complex and ever-changing privacy protection scenarios; and they can adapt to system architectures that separate screen devices from core devices, enabling the coordinated operation of environmental perception and content processing.

[0061] Figure 2 This is a schematic diagram of the system architecture of a screen information masking system according to a preferred embodiment of the present invention. Figure 2 As shown, the system in this embodiment adopts a distributed architecture in which core devices, the cloud, and screen devices work together. The core devices include four levels of business processing units: a content analysis module, a sensitivity grading module, a masking execution engine, and a video stream encoding module. The cloud model service deploys four AI inference models: a content classification model, a face detection model, a gaze analysis model, and a recording device detection model. The screen devices are equipped with two types of acquisition hardware: an environmental perception camera and a gaze tracking sensor. During operation, the screen devices acquire images through the environmental perception camera and output gaze point coordinates through the gaze tracking sensor. These two data streams are sent to the local privacy threat assessment module for preliminary feature extraction and then uploaded to the cloud to call the corresponding AI model for feature analysis. The cloud outputs content classification results and face / peeping / recording device detection results, which are then sent back to the core devices. The core devices then perform content analysis, sensitivity grading, masking execution, and video stream encoding at each level, finally outputting a privacy-protected video stream and pushing it back to the screen devices for display.

[0062] Figure 3 This is a schematic diagram of the main process of information threat level assessment according to a preferred embodiment of the present invention. Figure 3As shown, environmental image data of the area in front of the screen is first acquired and preprocessed, such as through noise reduction, brightness correction, and target enhancement, to obtain a preprocessed image suitable for target recognition. Then, parallel detection processing is performed on the preprocessed image. Specifically, a face detection module identifies personnel targets in the environment and counts the number of unauthorized personnel to generate an unauthorized personnel quantity factor; a gaze direction analysis module analyzes the facial and eye orientation of unauthorized personnel to determine if there is any peeping behavior, generating a peeping gaze factor; and a recording device detection module identifies recording devices such as mobile phone cameras and hidden cameras to generate a recording device factor. Finally, the unauthorized personnel quantity factor, peeping gaze factor, and recording device factor are input into a multi-factor fusion module for comprehensive analysis, and a threat level determination is performed based on the fusion results. When no unauthorized personnel (no one else) or recording devices are present, the threat level is determined to be low; when unauthorized personnel are watching the screen, the threat level is determined to be medium; when multiple people are watching (which can be understood as multiple unauthorized personnel spying on the screen) or when strangers (which can be understood as unauthorized personnel) are continuously approaching, the threat level is determined to be high; when a recording device is detected, the threat level is determined to be extreme. By integrating personnel risk, spying risk, and recording risk, an accurate assessment of the environmental security status is achieved, improving the reliability and comprehensiveness of information threat level determination.

[0063] Figure 4 This is a schematic diagram of the main process of content sensitivity classification according to a preferred embodiment of the present invention. Figure 4As shown, the core device performs content analysis on the screen display and determines the corresponding sensitivity level based on the content type. Specifically, it first identifies multiple display content areas, such as password input boxes, bank card number areas, chat log areas, email body areas, ordinary webpage text areas, video playback window areas, status bar areas, and wallpaper background areas. For information areas involving account security and financial security, such as password input boxes and bank card numbers, it is determined to be at the highest sensitivity level (S1); for information areas involving personal communication content, such as chat logs and email body areas, it is determined to be at the medium sensitivity level (S2); for information areas with high public visibility, such as ordinary webpage text and video playback windows, it is determined to be at the low sensitivity level (S3); and for information areas that do not require protection, such as status bar icons and wallpaper backgrounds, it is determined to be at the public level (S0). Then, a corresponding sensitivity classification result is generated based on the different sensitivity levels, where the highest sensitivity level (S1) is marked in red, the medium sensitivity level (S2) is marked in orange, the low sensitivity level (S3) is marked in yellow, and the public level (S0) is marked in green. By identifying and managing the displayed content by region, the privacy risk level of different content can be accurately distinguished, providing a basis for subsequent differentiated information masking and avoiding uniform masking of all displayed content. This ensures privacy and security while improving the user experience.

[0064] Figure 5 This is a schematic diagram illustrating the main process of screen visual partitioning and progressive occlusion rendering according to a preferred embodiment of the present invention. Figure 5 As shown, this embodiment uses progressive Gaussian blur as the basic occlusion algorithm. The blur radius increases linearly with the spatial distance between the pixel and the user's gaze point. The screen is divided into four visual zones based on visual distance, each corresponding to a different occlusion intensity. The gaze area is completely clear and receives no blurring, ensuring normal browsing operation for the user. Peripheral region 1, a secondary region closer to the gaze point, undergoes slight blurring, retaining only the image outline and not affecting overall interface recognition. Peripheral region 2, a medium-distance outer region, undergoes moderate blurring, allowing only color to be distinguished. The edge region, the farthest outer region of the screen, undergoes high blurring. If content with the highest sensitivity level (S1) is detected in this region, blurring is no longer used; instead, a placeholder is directly replaced for desensitized display. For example, the bank card number "1234 5678 9012 3456" will be uniformly replaced with "[Sensitive Content]". "Formatting completely eliminates the risk of digital leakage. Non-highest level sensitive content is only weakened in terms of privacy through high blurring, without text replacement."

[0065] Figure 6This is a timing diagram of line-of-sight prediction and pre-clarification processing according to a preferred embodiment of the present invention. Figure 6 As shown, this embodiment incorporates a gaze prediction mechanism to eliminate image blurring delays when the user moves their gaze. The complete business sequence is as follows: Initially, the user's gaze point remains on screen area A. The screen device's gaze tracking sensor collects the gaze point coordinates in real time and reports them to the core device. The core device continuously outputs a fully clear rendering command to area A, ensuring that area A remains unblurred. Simultaneously, the gaze movement prediction process is initiated. The screen device continuously uploads real-time gaze coordinates to the cloud-based gaze analysis model. The model, combining historical gaze trajectories and screen content layout, predicts that the user's next gaze point will move to area B. The cloud sends a pre-clarification command to the core device. Upon receiving the pre-clarification command, the core device preprocesses the clear image of area B and sends a confirmation signal back to the screen device. When the user's gaze actually moves from area A to area B, the screen device continuously reports the updated gaze coordinates in real time. As soon as the gaze point enters the boundary of area B, the core device pushes the clear image of area B. After the user's gaze stabilizes in area B, the global current gaze point is updated to B, and the tracking and prediction process is executed cyclically. This embodiment relies on the prediction of the eye trajectory to render the target area in advance, so the user cannot perceive the delay caused by the blurry screen switching throughout the process, thus balancing privacy protection and browsing experience.

[0066] According to a second aspect of the present invention, a screen information masking device is provided.

[0067] Figure 7 This is a schematic diagram of the main modules of a screen information masking device according to an embodiment of the present invention. Figure 7 As shown, the screen information masking device 700 includes: The acquisition module 701 is used to acquire the foreground environment data and display content data corresponding to the screen, as well as the eye tracking data of the authorized user; The determination module 702 is used to determine the information threat level based on the data of the foreground environment; determine the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area; and generate a gaze heatmap corresponding to the authorized user based on the gaze tracking data. The masking module 703 is used to determine the information masking strategy of the screen based on the information threat level, the sensitivity level corresponding to the privacy information area and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy.

[0068] Optionally, the acquisition module 701 is also used for: The front-facing camera corresponding to the screen is invoked to collect environmental image data of the area in front of the screen in order to obtain the environmental data in front of the screen. The acquisition module 701 is also used for: The system utilizes the front-facing camera or infrared gaze sensor on the screen to collect eye movement information from authorized users and generates gaze tracking data based on this information.

[0069] Optionally, the determining module 702 is also used for: Based on the environmental data in front of the screen, determine the number of unauthorized personnel in the area in front of the screen, and determine the personnel risk result based on the number of unauthorized personnel. Based on the data of the surrounding environment, determine the line of sight of unauthorized personnel, and determine the risk of spying based on the line of sight information. Based on the environmental data, the recording equipment is tested to obtain the recording risk results; The information threat level is determined based on the risk results from personnel, spying, and recording.

[0070] Optionally, the determining module 702 is also used for: The displayed content data is analyzed and processed to obtain multiple display content areas; Each display content area is matched with a preset privacy information database, and the privacy information area on the screen and its corresponding privacy information type are determined based on the matching results. Determine the sensitivity level of the privacy information area based on the type of privacy information.

[0071] Optionally, the determining module 702 is also used for: Determine the current gaze area of ​​the authorized user based on eye-tracking data; The current gaze area is designated as the first central region; The surrounding adjacent area and visual edge area corresponding to the first central area are determined according to the preset distance conditions; A gaze heatmap is generated based on the first central region and its corresponding surrounding adjacent regions and visual edge regions.

[0072] Optionally, the determining module 702 is also used for: Based on the current gaze area, a preset gaze prediction algorithm is used to determine the target gaze area of ​​the authorized user within a preset time period in the future; The target gaze area is defined as the second central area; The surrounding adjacent area and visual edge area corresponding to the second central area are determined according to the preset distance conditions; The gaze heatmap is updated based on the second central region and its corresponding surrounding adjacent regions and visual edge regions.

[0073] Optionally, the masking module 703 is also used for: The screen's masking strength is determined based on the information threat level. The information replacement mode for the privacy information area on the screen is determined based on the sensitivity level corresponding to the privacy information area. Determine the Gaussian blur gradient corresponding to the screen based on the gaze heatmap; An information occlusion strategy is generated based on the occlusion intensity, information replacement mode, and Gaussian blur gradient of the screen.

[0074] It should be noted that the specific implementation of the screen information covering device of the present invention has been described in detail in the screen information covering method above, so the content will not be repeated here.

[0075] According to a third aspect of the present invention, an electronic device is provided, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the present invention.

[0076] According to a fourth aspect of the present invention, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0077] According to a fifth aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided in the first aspect of the present invention.

[0078] Figure 8 An exemplary system architecture 800 is shown in which the screen information masking method or screen information masking device of the present invention can be applied.

[0079] like Figure 8 As shown, system architecture 800 may include terminal devices 801, 802, and 803, a network 804, and a server 805. Network 804 serves as the medium for providing communication links between terminal devices 801, 802, and 803 and server 805. Network 804 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0080] Users can use terminal devices 801, 802, and 803 to interact with server 805 via network 804 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 801, 802, and 803, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0081] Terminal devices 801, 802, and 803 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0082] Server 805 can be a server providing various services, such as a backend management server supporting shopping websites browsed by users using terminal devices 801, 802, and 803 (for example only). The backend management server can analyze and process data such as received screen information masking requests, and feed back the processing results (screen information masking results - for example only) to the terminal devices.

[0083] It should be noted that the screen information masking method provided in the embodiments of the present invention is generally executed by server 805, and correspondingly, the screen information masking device is generally disposed in server 805. The screen information masking method provided in the embodiments of the present invention can also be executed by terminal devices 801, 802, and 803, and correspondingly, the screen information masking device can be disposed in terminal devices 801, 802, and 803.

[0084] It should be understood that Figure 8 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0085] The following is for reference. Figure 9 It shows a schematic diagram of the structure of a computer system 900 suitable for implementing a terminal device of the present invention. Figure 9 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0086] like Figure 9 As shown, the computer system 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 902 or programs loaded from storage section 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the system 900. The CPU 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0087] The following components are connected to I / O interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to I / O interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 910 as needed so that computer programs read from it can be installed into storage section 908 as needed.

[0088] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 909, and / or installed from removable medium 911. When the computer program is executed by central processing unit (CPU) 901, it performs the functions defined above in the system of this invention.

[0089] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor. For example, a processor can be described as including an acquisition module, a determination module, and an occlusion module. The names of these modules do not necessarily limit the module itself. For instance, the acquisition module can also be described as "a module for acquiring foreground environmental data, display content data, and eye-tracking data of authorized users corresponding to the screen."

[0092] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, implement the following method: acquiring foreground environment data and display content data corresponding to the screen, as well as eye-tracking data of an authorized user; determining an information threat level based on the foreground environment data; determining a privacy information area in the display content data and the sensitivity level corresponding to the privacy information area; generating a gaze heatmap corresponding to the authorized user based on the eye-tracking data; determining an information masking strategy for the screen based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy.

[0093] The computer program product provided in this embodiment of the invention includes a computer program that, when executed by a processor, implements the screen information masking method in this embodiment of the invention.

[0094] The technical solution of this invention has the following advantages or beneficial effects: It acquires foreground environmental data, display content data, and authorized user eye-tracking data corresponding to the screen; determines the information threat level based on the foreground environmental data; determines the privacy information area and the sensitivity level corresponding to the privacy information area in the display content data; generates a gaze heatmap corresponding to the authorized user based on the eye-tracking data; and determines the screen's information masking strategy based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy. By integrating three dimensions—foreground environmental detection, user eye tracking, and content sensitivity level—dynamic hierarchical privacy masking of the screen display content is achieved, which not only protects privacy and security but also allows for differentiated processing using different information masking strategies, while preserving the user's surrounding visual experience and improving the user's reading fluency.

[0095] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0096] It should be noted that the acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

Claims

1. A method for masking screen information, characterized in that, include: Acquire data on the foreground environment and displayed content corresponding to the screen, as well as eye-tracking data of authorized users; The information threat level is determined based on the aforementioned frontal environmental data; Determine the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area; generate a gaze heatmap corresponding to the authorized user based on the gaze tracking data; Based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, an information masking strategy for the screen is determined, and the screen is processed for information masking according to the information masking strategy.

2. The method according to claim 1, characterized in that, Obtain the ambient data corresponding to the screen, including: The front-facing camera corresponding to the screen is invoked, and environmental image data of the area in front of the screen is collected using the front-facing camera to obtain the environmental data in front of the screen. Obtain eye-tracking data from authorized users, including: The system invokes the front-facing camera or infrared gaze sensor corresponding to the screen, collects the eye movement information of the authorized user based on the front-facing camera or infrared gaze sensor, and generates gaze tracking data based on the eye movement information.

3. The method according to claim 1, characterized in that, Determining the information threat level based on the aforementioned frontal environment data includes: Based on the aforementioned environmental data, determine the number of unauthorized personnel in the area in front of the screen, and determine the personnel risk result based on the number of unauthorized personnel. Based on the aforementioned environmental data, determine the gaze direction information corresponding to the unauthorized personnel, and based on the gaze direction information, determine the spying risk result. Based on the aforementioned environmental data, the recording device is detected to obtain a recording risk result; The information threat level is determined based on the personnel risk results, the spying risk results, and the recording risk results.

4. The method according to claim 1, characterized in that, Determining the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area includes: The displayed content data is analyzed and processed to obtain multiple display content areas; Each of the displayed content areas is matched with a preset privacy information database, and the privacy information area and its corresponding privacy information type in the screen are determined based on the matching results. Based on the type of privacy information, determine the sensitivity level corresponding to the privacy information area.

5. The method according to claim 1, characterized in that, Generate a gaze heatmap for the authorized user based on the gaze tracking data, including: The current gaze area of ​​the authorized user is determined based on the gaze tracking data. The current gaze region is defined as the first central region; The surrounding adjacent area and visual edge area corresponding to the first central area are determined according to preset distance conditions; The gaze heatmap is generated based on the first central region and the surrounding adjacent regions and visual edge regions corresponding to the first central region.

6. The method according to claim 5, characterized in that, Generating a gaze heatmap for the authorized user based on the gaze tracking data further includes: Based on the current gaze area, a preset gaze prediction algorithm is used to determine the target gaze area of ​​the authorized user within a preset time period in the future; The target gaze region is defined as the second central region; The surrounding adjacent area and visual edge area corresponding to the second central area are determined according to preset distance conditions; The gaze heatmap is updated based on the second central region and the corresponding surrounding adjacent region and visual edge region.

7. The method according to claim 1, characterized in that, Based on the information threat level, the sensitivity level corresponding to the privacy information area, and the gaze heatmap, the information masking strategy for the screen is determined, including: The screen's shielding strength is determined based on the information threat level. The information replacement mode of the privacy information area on the screen is determined based on the sensitivity level corresponding to the privacy information area; The Gaussian blur gradient corresponding to the screen is determined based on the gaze heatmap; The information masking strategy is generated based on the masking intensity, information replacement mode, and Gaussian blur gradient corresponding to the screen.

8. A screen information shielding device, characterized in that, include: The acquisition module is used to acquire data on the foreground environment and displayed content corresponding to the screen, as well as eye tracking data of authorized users. The determination module is used to determine the information threat level based on the aforementioned frontal environment data; Determine the privacy information area in the displayed content data and the sensitivity level corresponding to the privacy information area; generate a gaze heatmap corresponding to the authorized user based on the gaze tracking data; The masking module is used to determine the information masking strategy of the screen based on the information threat level, the sensitivity level corresponding to the privacy information area and the gaze heatmap, so as to perform information masking processing on the screen according to the information masking strategy.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-7.

Images