Anti-peep processing method, device, equipment, storage medium and product

Abstract

The application discloses a kind of anti-spy processing method, device, equipment, storage medium and product, it is related to artificial intelligence technical field, including: in the process of displaying content based on browser, the current image of target detection area is acquired;When determining that target detection area exists unauthorized user according to current image, the current behavior intention of unauthorized user is determined according to the position information and action information of unauthorized user;When current behavior intention is preset intention, anti-spy processing is carried out to current display content;By the above-mentioned mode, when determining that target detection area exists unauthorized user, whether the current behavior intention of unauthorized user is preset intention is further judged, if yes, it indicates that unauthorized user is trying to spy current display content, at this time, anti-spy processing procedure is automatically triggered, reach the purpose of timely, accurately anti-spy processing to current display content, to prevent the privacy of user from being spied, and then improve the experience of user.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to methods, devices, equipment, storage media and products for preventing peeping. Background Technology

[0002] With the rapid development of internet technology, applications have become an important platform for enterprise operations and user interaction. However, application security issues are becoming increasingly prominent, especially illegal peeping. For example, when using applications in public places, users' private information is easily spied on by others, posing a risk of information leakage. Currently, common anti-peeping measures include privacy mode and external object blocking. However, these measures often rely on active user operation, and external object blocking can sometimes result in errors. Therefore, these measures cannot timely and accurately prevent peeping of displayed content.

[0003] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, device, storage medium, and product for preventing peeping, aiming to solve the technical problem that existing technologies cannot perform timely and accurate peeping protection on displayed content.

[0005] To achieve the above objectives, this application proposes an anti-peeping processing method, the method comprising:

[0006] During the process of displaying content based on the browser, the current image of the target detection area is obtained, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision;

[0007] When it is determined from the current image that an unauthorized user exists in the target detection area, the current behavioral intention of the unauthorized user is determined from the location information and action information of the unauthorized user.

[0008] When the current behavioral intention is the preset intention, anti-peeping processing is applied to the currently displayed content.

[0009] In one embodiment, before the step of determining the current behavioral intention of an unauthorized user based on the location information and action information of the unauthorized user, the method further includes:

[0010] Determine the set of facial feature points based on the current image;

[0011] The user's identity is obtained by performing identity recognition based on the set of facial feature points using a target user identity recognition model;

[0012] If at least one of the user authentications fails, it is determined that an unauthorized user exists in the target detection area.

[0013] In one embodiment, before the step of determining that an unauthorized user exists in the target detection area if at least one of the user authentications fails, the method further includes:

[0014] Access the database of authorized user identity features based on the security key;

[0015] The user's identity is subjected to feature extraction to obtain identity feature information;

[0016] Each of the aforementioned identity feature information is matched with the feature information in the authorized user identity feature database;

[0017] If at least one identity feature information fails to match in the matching results, then at least one of the user identity authentications is determined to have failed.

[0018] In one embodiment, the step of determining a set of facial feature points based on the current image includes:

[0019] Encrypt the current image;

[0020] Edge detection is performed on the encrypted current image based on the face recognition module;

[0021] The image edge detection results are segmented to obtain the face image;

[0022] Feature extraction is performed on the face image to obtain a set of face feature points.

[0023] In one embodiment, the step of determining the current behavioral intention of an unauthorized user based on the unauthorized user's location information and action information includes:

[0024] The location and action information of unauthorized users are cleaned separately.

[0025] The distance between the unauthorized user and the browser's terminal is determined based on the cleaned location information;

[0026] Determine the planar coordinates of the joints of various parts of the human body based on the motion information after cleaning;

[0027] The current behavioral intention of the unauthorized user is determined based on the distance and the planar coordinates of the key points.

[0028] In one embodiment, the step of determining the current behavioral intention of an unauthorized user based on the distance and the planar coordinates of the joints of various parts of the human body includes:

[0029] The relative direction between the unauthorized user and the terminal is determined based on the planar coordinates of the key points and the position coordinates of the terminal.

[0030] Determine the target extreme point based on different parts of the human body;

[0031] Based on the target pole, the planar coordinates of the joint point are transformed to obtain polar coordinates;

[0032] The current behavioral intention of an unauthorized user is determined using a behavioral intention recognition model based on the relative direction, the distance, and the polar coordinates.

[0033] In one embodiment, the step of determining the current behavioral intention of an unauthorized user based on the relative direction, the distance, and the polar coordinates using a behavioral intention recognition model includes:

[0034] The polar axis value and the target extreme value are calculated based on the polar coordinates using a preset extreme value algorithm.

[0035] Generate a joint behavior descriptor based on the polar axis value and the target extreme value;

[0036] The current behavioral intention of an unauthorized user is determined by the behavioral intention recognition model based on the relative direction, the distance, and the keypoint behavioral descriptor.

[0037] In one embodiment, the step of performing anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention includes:

[0038] When the current behavioral intention is a preset intention, determine the privacy level feature value of the currently displayed content;

[0039] When the privacy feature value is greater than or equal to a preset feature threshold, the screen of the terminal where the browser is located is turned off.

[0040] In one embodiment, after the step of determining the privacy level feature value of the currently displayed content when the current behavioral intention is a preset intention, the method further includes:

[0041] When the privacy feature value is less than a preset feature threshold, the privacy portion of the currently displayed content is extracted;

[0042] The privacy-related content is privatized.

[0043] In one embodiment, the step of acquiring the current image of the target detection region during the process of displaying content based on the browser includes:

[0044] During the process of displaying content based on the browser, the current illumination intensity of the target detection area is obtained;

[0045] When the current light intensity is lower than a preset light intensity threshold, the light source component is turned on;

[0046] Occlusion detection is performed on the target detection area;

[0047] When the detection result indicates that there are no obstructions in the target detection area, the camera device is invoked to acquire the current image of the target detection area.

[0048] In one embodiment, the step of calling a camera device to acquire the current image of the target detection area when the detection result indicates that there is no occlusion in the target detection area includes:

[0049] When the detection result indicates that there are no obstructions in the target detection area, the current application of the displayed content is obtained;

[0050] When the current application type is a preset sensitivity type, the image acquisition angle is determined;

[0051] The current image of the target detection area is obtained by calling the camera device based on the image acquisition angle.

[0052] In one embodiment, after the step of performing anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention, the method further includes:

[0053] Obtain user feedback regarding privacy protection measures;

[0054] The objects to be optimized are determined based on the feedback information;

[0055] When the object to be optimized includes an identity recognition object, the target user identity recognition model is iteratively updated.

[0056] When the object to be optimized includes a behavioral intention recognition object, the behavioral intention recognition model is iteratively updated.

[0057] Furthermore, to achieve the above objectives, this application also proposes an anti-peeping processing device, which includes:

[0058] The acquisition module is used to acquire the current image of the target detection area during the process of displaying content based on the browser, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision.

[0059] The determination module is used to determine the current behavioral intention of the unauthorized user based on the location information and action information of the unauthorized user when it is determined from the current image that an unauthorized user exists in the target detection area.

[0060] The processing module is used to perform anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention.

[0061] In one embodiment, the determining module is further configured to determine a set of facial feature points based on the current image; perform identity recognition based on the set of facial feature points using a target user identity recognition model to obtain the user identity; and if at least one of the user identity authentications fails, determine that an unauthorized user exists in the target detection area.

[0062] In one embodiment, the determining module is further configured to: obtain an authorized user identity feature database based on a security key; extract features from the user identity to obtain identity feature information; match each of the identity feature information with the feature information in the authorized user identity feature database; and if at least one identity feature information fails to match in the matching result, determine that at least one of the user identity authentications has failed.

[0063] In one embodiment, the determining module is further configured to encrypt the current image; perform edge detection on the encrypted current image based on the face recognition module; segment the image edge detection results to obtain a face image; and extract features from the face image to obtain a set of face feature points.

[0064] In one embodiment, the determining module is further configured to clean the location information and action information of the unauthorized user respectively; determine the distance between the unauthorized user and the terminal where the browser is located based on the cleaned location information; determine the planar coordinates of the joints of various parts of the human body based on the cleaned action information; and determine the current behavioral intention of the unauthorized user based on the distance and the planar coordinates of the joints.

[0065] In addition, to achieve the above objectives, this application also proposes an anti-peeping processing device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the anti-peeping processing method as described above.

[0066] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the anti-peeping processing method described above.

[0067] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the anti-peeping processing method described above.

[0068] One or more technical solutions proposed in this application have at least the following technical effects: During the process of displaying content based on a browser, the current image of the target detection area is obtained, wherein the target detection area refers to the user's location area within the user's field of vision that includes the displayed content; when it is determined, based on the current image, that an unauthorized user exists in the target detection area, the current behavioral intention of the unauthorized user is determined based on the unauthorized user's location and action information; when the current behavioral intention is a preset intention, anti-spying processing is applied to the currently displayed content; through the above method, when it is determined that an unauthorized user exists in the target detection area, it is further determined whether the unauthorized user's current behavioral intention is a preset intention. If so, it indicates that the unauthorized user is attempting to spy on the currently displayed content, and the anti-spying processing flow is automatically triggered, achieving the purpose of timely and accurate anti-spying processing of the currently displayed content to prevent the user's privacy from being spied on, thereby improving the user experience. Attached Figure Description

[0069] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0070] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0071] Figure 1 This is a flowchart illustrating an embodiment of the anti-spyware processing method of this application.

[0072] Figure 2 This is a flowchart illustrating Embodiment 2 of the anti-peeping processing method of this application;

[0073] Figure 3 This is a schematic diagram of the module structure of the anti-peeping processing device according to an embodiment of this application;

[0074] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the anti-peeping processing method in the embodiments of this application.

[0075] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0076] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or anti-spyware processing device capable of performing the above functions. The following description uses an anti-spyware processing device as an example to illustrate this embodiment and the subsequent embodiments.

[0077] Based on this, the embodiments of this application provide an anti-peeping processing method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the anti-peeping processing method of this application.

[0078] In this embodiment, the anti-peeping processing method includes steps S10 to S30:

[0079] Step S10: During the process of displaying content based on the browser, the current image of the target detection area is obtained, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision.

[0080] It should be noted that the browser in this embodiment can be an artificial intelligence (AI) browser that integrates artificial intelligence models, facial recognition modules, and data transmission encryption. This browser can also be responsible for user interface display and user interaction, such as providing a user-friendly interface and configuration options, which users can personalize according to their own needs to adapt to different application scenarios.

[0081] It should be understood that the current image refers to the image captured by the camera device within the target detection area. During the image capture process, if the user moves, the camera device can be controlled to track them in real time. Within the target detection area, the user can see all content displayed by the browser, such as text and images.

[0082] Understandably, the target detection region can be determined by fitting the user position critical points in various directions. For example, at user position point A, the user can see the displayed content, meaning the user's field of vision includes the displayed content. After moving one unit to the left, the user's field of vision no longer includes the displayed content. At this point, user position point A is the left critical point of the user position. Similarly, at user position point B, the user can see the displayed content, meaning the user's field of vision includes the displayed content. After moving one unit to the right, the user's field of vision no longer includes the displayed content. At this point, user position point B is the right critical point of the user position. To effectively improve the accuracy of determining the target detection region, multiple critical points can be added between user position points A and B. Following the above method, the user position critical points in each direction are determined, and then the target detection region is fitted.

[0083] Furthermore, in order to effectively improve the accuracy of acquiring the current image of the target detection area, the step of acquiring the current image of the target detection area during the process of displaying content based on the browser includes: acquiring the current illumination intensity of the target detection area during the process of displaying content based on the browser; turning on the light source component when the current illumination intensity is lower than a preset light intensity threshold; performing occlusion detection on the target detection area; and calling the camera device to acquire the current image of the target detection area when the detection result shows that there is no occlusion in the target detection area.

[0084] Understandably, after obtaining the current light intensity of the target detection area, it is determined whether the current light intensity is lower than the preset light intensity threshold. If so, it indicates that the light intensity of the target detection area is low, and the captured image is dark. At this time, the light source component is turned on to increase the light intensity. When the browser is running on a mobile terminal, the light source component can be a flashlight. When the browser is running on a computer, the light source component can be an extended light-emitting component, which is close to the camera.

[0085] It should be understood that, in order to prevent unauthorized users from peeping at the displayed content through obstructions, the target detection area also needs to perform obstruction detection. If there are no obstructions, the image acquisition process is automatically triggered, and the camera device is called to obtain the current image of the target detection area. If there are obstructions, the user's mobile terminal screen can be alerted to avoid obstructions in the target detection area.

[0086] Furthermore, in order to effectively improve the accuracy of acquiring the current image of the target detection area, the step of calling the camera device to acquire the current image of the target detection area when the detection result indicates that there is no occlusion in the target detection area includes: acquiring the current application of the displayed content when the detection result indicates that there is no occlusion in the target detection area; determining the image acquisition angle when the type of the current application is a preset sensitivity type; and calling the camera device to acquire the current image of the target detection area according to the image acquisition angle.

[0087] It should be understood that the current application refers to the application that the browser is running at the current moment. This current application can be a translation application, a search application, etc. After obtaining the current application of the displayed content, it is necessary to determine whether the type of the current application is a preset sensitive type. If so, it means that the current application is extremely sensitive. At this time, the image acquisition angle will be used to call the camera device to obtain the current image of the target detection area. The image acquisition angle can be the angle from which the user can see the displayed content.

[0088] Step S20: When it is determined from the current image that an unauthorized user exists in the target detection area, the current behavioral intention of the unauthorized user is determined from the location information and action information of the unauthorized user.

[0089] Understandably, unauthorized users refer to users who are not authorized to view the currently displayed content. Only authorized users can browse the currently displayed content normally. Other unauthorized users browsing the currently displayed content are considered to be spying, which poses a risk of privacy leakage. For example, after identifying three users in the current image, two of them are unauthorized users and one is an authorized user. At this time, it is determined that there are unauthorized users in the target detection area, and it is necessary to further determine the current behavioral intentions of the unauthorized users.

[0090] Furthermore, in order to effectively improve the efficiency of determining the current behavioral intention of an unauthorized user, the step of determining the current behavioral intention of an unauthorized user based on the location information and action information of the unauthorized user includes: cleaning the location information and action information of the unauthorized user respectively; determining the distance between the unauthorized user and the terminal where the browser is located based on the cleaned location information; determining the planar coordinates of the joints of various parts of the human body based on the cleaned action information; and determining the current behavioral intention of the unauthorized user based on the distance and the planar coordinates of the joints.

[0091] It should be understood that after obtaining the location and action information of unauthorized users, the location and action information of unauthorized users are cleaned to eliminate errors, anomalies and other information. Then, the distance between the unauthorized user and the browser terminal is determined based on the cleaned location information. The location information of both the unauthorized user and the browser terminal can be represented by coordinates.

[0092] Furthermore, to effectively improve the accuracy of determining the current behavioral intention of an unauthorized user, the step of determining the current behavioral intention of an unauthorized user based on the distance and the planar coordinates of the joint points of various parts of the human body includes: determining the relative direction between the unauthorized user and the terminal based on the planar coordinates of the joint points and the position coordinates of the terminal; determining the target pole based on various parts of the human body; performing coordinate transformation on the planar coordinates of the joint points based on the target pole to obtain polar coordinates; and determining the current behavioral intention of the unauthorized user based on the relative direction, the distance, and the polar coordinates through a behavioral intention recognition model.

[0093] It is understandable that the relative direction refers to the direction between the unauthorized user and the terminal. This relative direction can be represented by angles; that is, after obtaining the plane coordinates of the joint point and the position coordinates of the terminal, the relative direction between the unauthorized user and the terminal is calculated using the cosine formula. The target pole can be the center point of the user's torso, and polar coordinates refer to the coordinates after coordinate transformation of the plane coordinates of the joint point. Then, the relative direction, distance, and polar coordinates are input into the behavior intention recognition model, which identifies and outputs the current behavior intention of the unauthorized user.

[0094] Furthermore, in order to effectively improve the accuracy of determining the current behavioral intention of an unauthorized user, the step of determining the current behavioral intention of an unauthorized user based on the relative direction, the distance, and the polar coordinates using a behavioral intention recognition model includes: calculating the polar axis value and the target extreme value based on the polar coordinates using a preset extreme value algorithm; generating a keypoint behavioral descriptor based on the polar axis value and the target extreme value; and determining the current behavioral intention of the unauthorized user based on the relative direction, the distance, and the keypoint behavioral descriptor using a behavioral intention recognition model.

[0095] It should be understood that the preset extreme value algorithm can be a minimax algorithm, in which case the calculated polar axis value can be the first polar axis value, the target extreme value can be the first minimum value, and then a joint behavior descriptor is generated based on the polar axis value and the target extreme value. At this time, the joint behavior descriptor has the characteristic of being invariant to translation, scaling and rotation transformations. Then, the current behavior intention of the unauthorized user is determined by combining the relative direction and distance.

[0096] Step S30: When the current behavioral intention is a preset intention, anti-peeping processing is performed on the currently displayed content.

[0097] It should be understood that a pre-set intention refers to the intention to spy on the currently displayed content. After obtaining the current behavioral intention, it is necessary to determine whether the current behavioral intention is a pre-set intention. If so, it indicates that an unauthorized user intends to spy on the currently displayed content. At this time, anti-spying processing is performed on the currently displayed content to protect the user's privacy information, so that the browser provides users with more layers of security.

[0098] It should be noted that, for the browser in this embodiment, after implementing anti-peeping measures, it will also perform security checks and vulnerability patching regularly to ensure operational security.

[0099] Furthermore, in order to protect the user's privacy information in a timely manner, step S30 includes: when the current behavioral intention is a preset intention, determining the privacy level feature value of the currently displayed content; when the privacy level feature value is greater than or equal to a preset feature threshold, turning off the screen of the terminal where the browser is located.

[0100] It is understandable that the privacy level feature value represents the proportion of private content in the currently displayed content. The larger the privacy level feature value, the more private content there is. When the privacy level feature value is greater than or equal to the preset feature threshold, it indicates that the proportion of private content is extremely large. At this time, the screen of the terminal where the browser is located is directly turned off, which protects the user's privacy information as quickly as possible.

[0101] Furthermore, in order to effectively improve the user experience, after the step of determining the privacy level feature value of the currently displayed content when the current behavioral intention is a preset intention, the method further includes: when the privacy level feature value is less than a preset feature threshold, extracting the privacy part of the currently displayed content; and performing privacy processing on the privacy part.

[0102] It should be understood that when the privacy feature value is less than the preset feature threshold, it indicates that the proportion of privacy content is small. In this case, directly closing the screen of the browser terminal will result in a poor user experience. Therefore, this embodiment uses a privacy processing method to process the privacy content in the currently displayed content. This privacy processing method includes, but is not limited to, automatic blurring processing and hiding sensitive information processing.

[0103] It should be noted that after privacy processing, both the content that does not require privacy processing and the content that has undergone privacy processing will be displayed. Authorized users can continue browsing at this time. In addition, an alarm message will be displayed on the screen to request re-verification of identity. Unauthorized users will leave the target detection area after seeing this alarm message. Similarly, authorized users will also be alerted. If an unauthorized user does not leave the detection area for an extended period of time, authorized users will also change their location, thereby achieving the purpose of protecting users' privacy information.

[0104] Furthermore, in order to effectively improve the user experience, after step S30, the method further includes: obtaining user feedback information regarding the anti-spyware processing; determining the object to be optimized based on the feedback information; iteratively updating the target user identity recognition model when the object to be optimized includes an identity recognition object; and iteratively updating the behavior intention recognition model when the object to be optimized includes a behavior intention recognition object.

[0105] Understandably, after privacy processing, feedback from users regarding the anti-spyware measures will be received. This feedback includes information on satisfaction and dissatisfaction with the anti-spyware measures. The objects to be optimized refer to those that need to be optimized, including but not limited to identity recognition objects and behavioral intention recognition objects. Specifically, this can involve iteratively updating the target user identity recognition model and the behavioral intention recognition model, continuously optimizing the algorithm and parameter configuration to improve intelligent analysis and decision-making capabilities.

[0106] This embodiment acquires the current image of the target detection area during the browser content display process. The target detection area refers to the user's location area, which includes the displayed content, within the user's field of vision. When it is determined that an unauthorized user exists in the target detection area based on the current image, the unauthorized user's current behavioral intention is determined based on the unauthorized user's location and action information. If the current behavioral intention is a preset intention, anti-spying processing is applied to the currently displayed content. Through the above method, when it is determined that an unauthorized user exists in the target detection area, it is further determined whether the unauthorized user's current behavioral intention is a preset intention. If so, it indicates that the unauthorized user is attempting to spy on the currently displayed content, and the anti-spying processing flow is automatically triggered. This achieves the purpose of timely and accurate anti-spying processing of the currently displayed content to prevent the user's privacy from being spied on, thereby improving the user experience.

[0107] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 Before step S20, steps S101 to S103 are also included:

[0108] Step S101: Determine the set of facial feature points based on the current image.

[0109] It should be understood that a facial feature point set refers to the set of feature points used to identify a human face image. This set of facial feature points includes, but is not limited to, eye feature points, nose feature points, mouth feature points, and ear feature points.

[0110] Furthermore, in order to effectively improve the accuracy of obtaining the facial feature point set, step S101 includes: encrypting the current image; performing edge detection on the encrypted current image based on the face recognition module; segmenting the image edge detection result to obtain a face image; and extracting features from the face image to obtain a facial feature point set.

[0111] Understandably, to ensure data transmission security, after acquiring the current image of the target detection area, a data transmission encryption strategy is used to encrypt the current image. For the face recognition module, after obtaining the encrypted current image, it needs to be decrypted, and then a target edge detection algorithm is used to perform edge detection on the decrypted current image. To effectively improve the accuracy of edge detection, this target edge detection algorithm can be an algorithm that combines the advantages of the Prewitt edge detection algorithm and the Laplacian of Gaussian edge detection algorithm.

[0112] It should be understood that after edge detection, the image edge detection results may include images of other objects besides the face image, such as windows and walls. In this case, the image edge detection results are segmented and the face image is extracted.

[0113] Step S102: The user identity is obtained by performing identity recognition based on the set of facial feature points using the target user identity recognition model.

[0114] It should be understood that after obtaining the set of facial feature points, the set of facial feature points is input into the pre-trained target user identity recognition model. At this time, the parameters output by the target user identity recognition model are the user identity corresponding to the set of facial feature points. This user identity can be an authorized user or an unauthorized user.

[0115] Step S103: If at least one of the user authentications fails, it is determined that an unauthorized user exists in the target detection area.

[0116] Furthermore, in order to effectively improve the efficiency of user identity authentication, before step S103, the method further includes: obtaining an authorized user identity feature database based on a security key; extracting features from the user identity to obtain identity feature information; matching each of the identity feature information with the feature information in the authorized user identity feature database; and determining that at least one of the user identity authentications has failed if at least one of the matching results is a failed match.

[0117] It should be understood that identity feature information refers to the feature information used to identify different identities. This identity feature information can be an ID card number. In order to effectively improve the security of data transmission, it is necessary to obtain the authorized user identity feature database through a security key, and after the matching is completed, it is necessary to directly destroy the authorized user identity feature database.

[0118] Understandably, in order to effectively improve the efficiency of matching feature information, after obtaining the authorized user identity feature database, the identity feature information can be matched with the feature information in the authorized user identity feature database at both ends simultaneously. When all the identity feature information in the matching results is successfully matched, it indicates that all user identities have been successfully authenticated, further confirming that there are no unauthorized users in the target detection area. At this time, the browser continues to display the current content. If there is at least one unmatched identity feature information in the matching results, it is determined that at least one user identity authentication has failed, further confirming that there are unauthorized users in the target detection area.

[0119] This embodiment determines a set of facial feature points based on the current image; it then uses a target user identity recognition model to identify the user based on the set of facial feature points, thus obtaining the user's identity; if at least one of the user identity authentications fails, it is determined that an unauthorized user exists in the target detection area. Through this method, after obtaining the current image, a set of facial feature points is obtained through a series of processing methods such as edge detection, segmentation, and feature extraction. The user identity identified by the target user identity recognition model is then used to determine whether there is a user identity authentication failure. If so, it is determined that an unauthorized user exists in the target detection area, thereby effectively improving the efficiency of determining whether an unauthorized user exists.

[0120] This application also provides an anti-peeping processing device, please refer to... Figure 3 The privacy protection device includes:

[0121] The acquisition module 10 is used to acquire the current image of the target detection area during the process of displaying content based on the browser, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision.

[0122] The determination module 20 is used to determine the current behavioral intention of the unauthorized user based on the location information and action information of the unauthorized user when it is determined from the current image that an unauthorized user exists in the target detection area.

[0123] Processing module 30 is used to perform anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention.

[0124] This embodiment acquires the current image of the target detection area during the browser content display process. The target detection area refers to the user's location area, which includes the displayed content, within the user's field of vision. When it is determined that an unauthorized user exists in the target detection area based on the current image, the unauthorized user's current behavioral intention is determined based on the unauthorized user's location and action information. If the current behavioral intention is a preset intention, anti-spying processing is applied to the currently displayed content. Through the above method, when it is determined that an unauthorized user exists in the target detection area, it is further determined whether the unauthorized user's current behavioral intention is a preset intention. If so, it indicates that the unauthorized user is attempting to spy on the currently displayed content, and the anti-spying processing flow is automatically triggered. This achieves the purpose of timely and accurate anti-spying processing of the currently displayed content to prevent the user's privacy from being spied on, thereby improving the user experience.

[0125] The anti-peeping processing device provided in this application, employing the anti-peeping processing method in the above embodiments, can solve the technical problem that the prior art cannot perform timely and accurate anti-peeping processing on the displayed content. Compared with the prior art, the beneficial effects of the anti-peeping processing device provided in this application are the same as the beneficial effects of the anti-peeping processing method provided in the above embodiments, and other technical features in the anti-peeping processing device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0126] In one embodiment, the acquisition module 10 is further configured to acquire the current light intensity of the target detection area during the process of displaying content based on the browser; turn on the light source component when the current light intensity is lower than a preset light intensity threshold; perform occlusion detection on the target detection area; and call the camera device to acquire the current image of the target detection area when the detection result shows that there is no occlusion in the target detection area.

[0127] In one embodiment, the acquisition module 10 is further configured to acquire the current application of the displayed content when the detection result indicates that there is no obstruction in the target detection area; determine the image acquisition angle when the type of the current application is a preset sensitive type; and call the camera device to acquire the current image of the target detection area according to the image acquisition angle.

[0128] In one embodiment, the determining module 20 is further configured to determine a set of facial feature points based on the current image; perform identity recognition based on the set of facial feature points using a target user identity recognition model to obtain the user identity; and if at least one of the user identity authentications fails, determine that an unauthorized user exists in the target detection area.

[0129] In one embodiment, the determining module 20 is further configured to: obtain an authorized user identity feature database based on a security key; extract features from the user identity to obtain identity feature information; match each of the identity feature information with the feature information in the authorized user identity feature database; and if at least one identity feature information fails to match in the matching result, determine that at least one of the user identity authentications has failed.

[0130] In one embodiment, the determining module 20 is further configured to encrypt the current image;

[0131] The face recognition module performs edge detection on the encrypted current image; the edge detection results are segmented to obtain a face image; and features are extracted from the face image to obtain a set of face feature points.

[0132] In one embodiment, the determining module 20 is further configured to clean the location information and action information of the unauthorized user respectively; determine the distance between the unauthorized user and the terminal where the browser is located based on the cleaned location information; determine the planar coordinates of the joints of various parts of the human body based on the cleaned action information; and determine the current behavioral intention of the unauthorized user based on the distance and the planar coordinates of the joints.

[0133] In one embodiment, the determining module 20 is further configured to determine the relative direction between the unauthorized user and the terminal based on the planar coordinates of the joint point and the position coordinates of the terminal; determine the target pole based on various parts of the human body; perform coordinate transformation on the planar coordinates of the joint point based on the target pole to obtain polar coordinates; and determine the current behavioral intention of the unauthorized user based on the relative direction, the distance, and the polar coordinates through a behavioral intention recognition model.

[0134] In one embodiment, the determining module 20 is further configured to calculate the polar axis value and the target extreme value based on the polar coordinates using a preset extreme value algorithm; generate a joint behavior descriptor based on the polar axis value and the target extreme value; and determine the current behavior intention of the unauthorized user based on the relative direction, the distance, and the joint behavior descriptor using a behavior intention recognition model.

[0135] In one embodiment, the processing module 30 is further configured to determine the privacy level feature value of the currently displayed content when the current behavioral intention is a preset intention; and to turn off the screen of the terminal where the browser is located when the privacy level feature value is greater than or equal to a preset feature threshold.

[0136] In one embodiment, the processing module 30 is further configured to extract the privacy portion of the currently displayed content when the privacy feature value is less than a preset feature threshold, and to perform privacy processing on the privacy portion.

[0137] In one embodiment, the processing module 30 is further configured to acquire user feedback information regarding anti-peeping processing; determine the object to be optimized based on the feedback information; when the object to be optimized includes an identity recognition object, iteratively update the target user identity recognition model; and when the object to be optimized includes a behavioral intention recognition object, iteratively update the behavioral intention recognition model.

[0138] This application provides an anti-peeping processing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the anti-peeping processing method in the above embodiment 1.

[0139] The following is for reference. Figure 4The diagram illustrates a structural schematic of an anti-spyware processing device suitable for implementing embodiments of this application. The anti-spyware processing device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The privacy protection device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application.

[0140] like Figure 4 As shown, the privacy protection processing device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the privacy protection processing device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the privacy processing device to communicate wirelessly or wiredly with other devices to exchange data. While privacy processing devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0141] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application 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 a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0142] The anti-peeping processing device provided in this application, employing the anti-peeping processing method in the above embodiments, can solve the technical problem that the prior art cannot perform timely and accurate anti-peeping processing on the displayed content. Compared with the prior art, the beneficial effects of the anti-peeping processing device provided in this application are the same as the beneficial effects of the anti-peeping processing method provided in the above embodiments, and other technical features in the anti-peeping processing device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0143] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0144] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0145] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the anti-peeping processing method in the above embodiments.

[0146] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0147] The aforementioned computer-readable storage medium may be included in the privacy protection device; or it may exist independently and not assembled into the privacy protection device.

[0148] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0149] 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 this application. 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 the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can 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.

[0150] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0151] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described anti-peeping processing method, thereby solving the technical problem that the prior art cannot perform timely and accurate anti-peeping processing on displayed content. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the anti-peeping processing method provided in the above embodiments, and will not be repeated here.

[0152] This invention discloses A1. A method for preventing peeping, the method comprising:

[0153] During the process of displaying content based on the browser, the current image of the target detection area is obtained, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision;

[0154] When it is determined from the current image that an unauthorized user exists in the target detection area, the current behavioral intention of the unauthorized user is determined from the location information and action information of the unauthorized user.

[0155] When the current behavioral intention is the preset intention, anti-peeping processing is applied to the currently displayed content.

[0156] A2. The method as described in A1, prior to the step of determining the current behavioral intention of the unauthorized user based on the location information and action information of the unauthorized user, further includes:

[0157] Determine the set of facial feature points based on the current image;

[0158] The user's identity is obtained by performing identity recognition based on the set of facial feature points using a target user identity recognition model;

[0159] If at least one of the user authentications fails, it is determined that an unauthorized user exists in the target detection area.

[0160] A3. The method as described in A2, prior to the step of determining the presence of an unauthorized user in the target detection area if at least one of the user authentications fails, further comprising:

[0161] Access the database of authorized user identity features based on the security key;

[0162] The user's identity is subjected to feature extraction to obtain identity feature information;

[0163] Each of the aforementioned identity feature information is matched with the feature information in the authorized user identity feature database;

[0164] If at least one identity feature information fails to match in the matching results, then at least one of the user identity authentications is determined to have failed.

[0165] A4. As described in A2, the step of determining the set of facial feature points based on the current image includes:

[0166] Encrypt the current image;

[0167] Edge detection is performed on the encrypted current image based on the face recognition module;

[0168] The image edge detection results are segmented to obtain the face image;

[0169] Feature extraction is performed on the face image to obtain a set of face feature points.

[0170] A5. The method as described in A1, wherein the step of determining the current behavioral intention of the unauthorized user based on the location information and action information of the unauthorized user includes:

[0171] The location and action information of unauthorized users are cleaned separately.

[0172] The distance between the unauthorized user and the browser's terminal is determined based on the cleaned location information;

[0173] Determine the planar coordinates of the joints of various parts of the human body based on the motion information after cleaning;

[0174] The current behavioral intention of the unauthorized user is determined based on the distance and the planar coordinates of the key points.

[0175] A6. As described in A5, the step of determining the current behavioral intention of the unauthorized user based on the distance and the planar coordinates of the joints of various parts of the human body includes:

[0176] The relative direction between the unauthorized user and the terminal is determined based on the planar coordinates of the key points and the position coordinates of the terminal.

[0177] Determine the target extreme point based on different parts of the human body;

[0178] Based on the target pole, the planar coordinates of the joint point are transformed to obtain polar coordinates;

[0179] The behavioral intention recognition model determines the current behavioral intention of an unauthorized user based on the relative direction, the distance, and the polar coordinates.

[0180] A7. The method as described in A6, wherein the step of determining the current behavioral intention of the unauthorized user based on the relative direction, the distance, and the polar coordinates using a behavioral intention recognition model includes:

[0181] The polar axis value and the target extreme value are calculated based on the polar coordinates using a preset extreme value algorithm.

[0182] Generate a joint behavior descriptor based on the polar axis value and the target extreme value;

[0183] The current behavioral intention of an unauthorized user is determined by the behavioral intention recognition model based on the relative direction, the distance, and the keypoint behavioral descriptor.

[0184] A8. The method as described in A1, wherein the step of performing anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention includes:

[0185] When the current behavioral intention is a preset intention, determine the privacy level feature value of the currently displayed content;

[0186] When the privacy feature value is greater than or equal to a preset feature threshold, the screen of the terminal where the browser is located is turned off.

[0187] A9. The method as described in A8, after the step of determining the privacy level feature value of the currently displayed content when the current behavioral intention is a preset intention, further includes:

[0188] When the privacy feature value is less than a preset feature threshold, the privacy portion of the currently displayed content is extracted;

[0189] The privacy-related content is privatized.

[0190] A10. The method as described in A1, wherein the step of acquiring the current image of the target detection region during the process of displaying content based on the browser includes:

[0191] During the process of displaying content based on the browser, the current illumination intensity of the target detection area is obtained;

[0192] When the current light intensity is lower than a preset light intensity threshold, the light source component is turned on;

[0193] Occlusion detection is performed on the target detection area;

[0194] When the detection result indicates that there are no obstructions in the target detection area, the camera device is invoked to acquire the current image of the target detection area.

[0195] A11. The method as described in A10, wherein the step of calling a camera device to acquire the current image of the target detection area when the detection result indicates that there is no occlusion in the target detection area includes:

[0196] When the detection result indicates that there are no obstructions in the target detection area, the current application of the displayed content is obtained;

[0197] When the current application type is a preset sensitivity type, the image acquisition angle is determined;

[0198] The current image of the target detection area is obtained by calling the camera device based on the image acquisition angle.

[0199] A12. The method as described in any one of A1 to A11, further comprising, after the step of performing anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention:

[0200] Obtain user feedback regarding privacy protection measures;

[0201] The objects to be optimized are determined based on the feedback information;

[0202] When the object to be optimized includes an identity recognition object, the target user identity recognition model is iteratively updated.

[0203] When the object to be optimized includes a behavioral intention recognition object, the behavioral intention recognition model is iteratively updated.

[0204] The present invention also discloses B13. An anti-peeping processing device, the device comprising:

[0205] The acquisition module is used to acquire the current image of the target detection area during the process of displaying content based on the browser, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision.

[0206] The determination module is used to determine the current behavioral intention of the unauthorized user based on the location information and action information of the unauthorized user when it is determined from the current image that an unauthorized user exists in the target detection area.

[0207] The processing module is used to perform anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention.

[0208] B14. The apparatus as described in B13, wherein the determining module is further configured to determine a set of facial feature points based on the current image; perform identity recognition based on the set of facial feature points using a target user identity recognition model to obtain a user identity; and if at least one of the user identity authentications fails, determine that an unauthorized user exists in the target detection area.

[0209] B15. The apparatus as described in B14, wherein the determining module is further configured to: obtain an authorized user identity feature database based on a security key; extract features from the user identity to obtain identity feature information; match each of the identity feature information with the feature information in the authorized user identity feature database; and if at least one identity feature information fails to match in the matching result, determine that at least one of the user identity authentications has failed.

[0210] B16. The apparatus as described in B14, wherein the determining module is further configured to encrypt the current image; perform edge detection on the encrypted current image based on the face recognition module; segment the image edge detection result to obtain a face image; and extract features from the face image to obtain a set of face feature points.

[0211] B17. The apparatus as described in B13, wherein the determining module is further configured to clean the location information and action information of the unauthorized user respectively; determine the distance between the unauthorized user and the terminal where the browser is located based on the cleaned location information; determine the planar coordinates of the joints of various parts of the human body based on the cleaned action information; and determine the current behavioral intention of the unauthorized user based on the distance and the planar coordinates of the joints.

[0212] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the anti-peeping processing method described above.

[0213] The computer program product provided in this application can solve the technical problem that the prior art cannot perform timely and accurate anti-peeping processing on the displayed content. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the anti-peeping processing method provided in the above embodiments, and will not be repeated here.

[0214] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for preventing peeping, characterized in that, The method includes: During the process of displaying content based on the browser, the current image of the target detection area is obtained, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision; When it is determined from the current image that an unauthorized user exists in the target detection area, the current behavioral intention of the unauthorized user is determined from the location information and action information of the unauthorized user. When the current behavioral intention is the preset intention, anti-peeping processing is applied to the currently displayed content.

2. The method as described in claim 1, characterized in that, Before the step of determining the current behavioral intention of an unauthorized user based on the location and action information of the unauthorized user, the method further includes: Determine the set of facial feature points based on the current image; The user's identity is obtained by performing identity recognition based on the set of facial feature points using a target user identity recognition model; If at least one of the user authentications fails, it is determined that an unauthorized user exists in the target detection area.

3. The method as described in claim 2, characterized in that, Before the step of determining that an unauthorized user exists in the target detection area if at least one of the user authentications fails, the method further includes: Access the database of authorized user identity features based on the security key; The user's identity is subjected to feature extraction to obtain identity feature information; Each of the aforementioned identity feature information is matched with the feature information in the authorized user identity feature database; If at least one identity feature information fails to match in the matching results, then at least one of the user identity authentications is determined to have failed.

4. The method as described in claim 1, characterized in that, The step of determining the current behavioral intention of an unauthorized user based on the unauthorized user's location and action information includes: The location and action information of unauthorized users are cleaned separately. The distance between the unauthorized user and the browser's terminal is determined based on the cleaned location information; Determine the planar coordinates of the joints of various parts of the human body based on the motion information after cleaning; The current behavioral intention of the unauthorized user is determined based on the distance and the planar coordinates of the key points.

5. The method as described in claim 1, characterized in that, The step of performing anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention includes: When the current behavioral intention is a preset intention, determine the privacy level feature value of the currently displayed content; When the privacy feature value is greater than or equal to a preset feature threshold, the screen of the terminal where the browser is located is turned off.

6. The method as described in claim 1, characterized in that, The step of acquiring the current image of the target detection region during the process of displaying content based on the browser includes: During the process of displaying content based on the browser, the current illumination intensity of the target detection area is obtained; When the current light intensity is lower than a preset light intensity threshold, the light source component is turned on; Occlusion detection is performed on the target detection area; When the detection result indicates that there are no obstructions in the target detection area, the camera device is invoked to acquire the current image of the target detection area.

7. A privacy protection device, characterized in that, The device includes: The acquisition module is used to acquire the current image of the target detection area during the process of displaying content based on the browser, wherein the target detection area refers to the user's position area that includes the displayed content within the user's field of vision. The determination module is used to determine the current behavioral intention of the unauthorized user based on the location information and action information of the unauthorized user when it is determined from the current image that an unauthorized user exists in the target detection area. The processing module is used to perform anti-peeping processing on the currently displayed content when the current behavioral intention is a preset intention.

8. A privacy protection device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the anti-peeping processing method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the anti-peeping processing method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the anti-peeping processing method as described in any one of claims 1 to 6.

Images