Data encryption processing method and device applied to AR scene and electronic equipment

Abstract

The invention provides a data encryption processing method and device applied to an AR scene and electronic equipment, and relates to the field of data processing. In the method, three-dimensional point cloud data of a target AR scene and fixation point data of a user in the target AR scene are acquired, and the user wears AR glasses for displaying the target AR scene; determining a privacy domain of the target AR scene according to the three-dimensional point cloud data and the fixation point data; obtaining sensitive data of the target AR scene; storing the sensitive data in a privacy domain to obtain to-be-encrypted data; and distributing a dynamic key for the to-be-encrypted data, and encrypting the to-be-encrypted data in combination with a preset encryption algorithm. By implementing the technical scheme provided by the invention, the data encryption processing efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a data encryption processing method, device and electronic device applied to AR scenarios. Background Art

[0002] With the rapid development of AR technology, AR applications have gradually penetrated into multiple fields, such as intelligent navigation, virtual meetings, personalized advertising, telemedicine, etc. However, the realization of this experience requires the processing of privacy data such as geographic location information, user behavior trajectories, facial recognition data, and environmental perception information. These data are not only highly sensitive, but also directly related to the privacy and security of users.

[0003] At present, the existing privacy data protection methods rely on traditional data encryption technology. However, in AR scenarios, multimodal data such as video, audio, and 3D point cloud need to be processed simultaneously. Traditional encryption methods are difficult to meet the diverse protection needs of multimodal data while ensuring high security, resulting in low data encryption processing efficiency.

[0004] Therefore, there is an urgent need for a data encryption processing method, device and electronic device applied to AR scenarios. Summary of the invention

[0005] The present application provides a data encryption processing method, device and electronic device applied to AR scenarios, which are convenient for improving the efficiency of data encryption processing.

[0006] In a first aspect of the present application, a data encryption processing method applied to an AR scene is provided, the method comprising: obtaining three-dimensional point cloud data of a target AR scene, and gaze point data of a user in the target AR scene, the user wearing AR glasses for displaying the target AR scene; determining a privacy domain of the target AR scene according to the three-dimensional point cloud data and the gaze point data; obtaining sensitive data of the target AR scene; storing the sensitive data in the privacy domain to obtain data to be encrypted; allocating a dynamic key to the data to be encrypted, and encrypting the data to be encrypted in combination with a preset encryption algorithm.

[0007] By adopting the above technical solution, the user's interest area and high-attention area in the target AR scene can be identified in real time through three-dimensional point cloud data and user's gaze point data, and these areas can be marked as privacy domains. This ensures that sensitive data is only associated with content that the user cares about, avoiding the waste of global protection resources. Based on the user's actual interactive behavior, the determination of the privacy domain is dynamic and personalized, adapting to the privacy protection needs of different users, and improving the accuracy of data protection. Combined with three-dimensional point cloud information, not only can the geometric structure of the scene be obtained, but also the location of virtual and real interactive content can be accurately located, providing spatial support for the division of privacy domains. The use of gaze point data reflects the user's real-time intention, and combining subjective interest areas with objective scene data helps to improve the rationality and credibility of privacy domain division. Aggregate storage of sensitive data in the privacy domain can reduce data redundancy, reduce the risk of sensitive data leakage, and provide convenience for subsequent encryption operations. Dynamically generating encryption keys based on real-time environment improves the flexibility and security of data protection, making the keys more difficult to predict and crack. Combined with different types of sensitive data, select a suitable data encryption algorithm, taking into account encryption strength and encryption efficiency. Therefore, it is easy to improve the efficiency of data encryption processing.

[0008] Optionally, the acquiring of the three-dimensional point cloud data of the target AR scene and the gaze point data of the user in the target AR scene specifically includes: receiving original scene image data of the target AR scene sent by a depth camera; analyzing the original scene image data using an environmental perception model to generate the three-dimensional point cloud data; receiving eye movement data for the user sent by an eye tracking sensor; and determining the gaze point data using a gaze point analysis algorithm based on the eye movement data.

[0009] By adopting the above technical solution, the original scene image data is captured by the depth camera, and the three-dimensional point cloud data is generated by the environmental perception model, which can fully reflect the geometric structure, object position and depth information of the target AR scene. The user's eye movement data is obtained by the eye tracking sensor, which can reflect the user's attention distribution and interaction intention in real time, and supplement the subjective interaction data missing in the scene information. Combining the three-dimensional point cloud data with the gaze point data not only provides objective information of the scene, but also integrates the user's subjective interest area, providing a more comprehensive and dynamic basis for the subsequent privacy domain division. The original image data is analyzed by the environmental perception model, which can intelligently identify the key elements and geometric relationships in the scene to generate high-quality three-dimensional point cloud data. This model has adaptive capabilities and can handle complex real-life scenes to ensure the accuracy and integrity of the data. The user's gaze point is extracted from the eye movement data by the gaze point analysis algorithm, which can quickly and accurately locate the specific location or target that the user is concerned about, and adapt to the real-time requirements of the AR scene. Based on the spatial information of the three-dimensional point cloud data and the interest area of ​​the gaze point data, the privacy domain can be dynamically divided to ensure that the scope of the privacy domain is highly consistent with the user's real-time interaction behavior, thereby accurately protecting the user's sensitive information. The introduction of gaze point data reflects the personalized needs of users. Different users may have different focus points in the same scene. By dynamically identifying the gaze point, a privacy domain division strategy that varies from person to person can be implemented. Through multimodal data fusion and intelligent analysis algorithms, privacy protection is precisely targeted at the key areas of user concern, avoiding indiscriminate processing of the entire scene data, thereby optimizing the efficiency and security of privacy protection. As the user's gaze point changes, the privacy domain can be updated in real time to ensure that sensitive data is always protected and reduce the possibility of privacy leakage.

[0010] Optionally, determining the privacy domain of the target AR scene based on the three-dimensional point cloud data and the gaze point data specifically includes: determining a virtual element on which the user's line of sight is focused from the three-dimensional point cloud data and the gaze point data; determining the virtual element as a high privacy domain; determining environmental objects of the target AR scene from the three-dimensional point cloud data and the gaze point data; determining the environmental objects as a medium privacy domain; determining a scene background of the target AR scene from the three-dimensional point cloud data and the gaze point data; and determining the scene background as a low privacy domain.

[0011] By adopting the above technical solution, through the combination of three-dimensional point cloud data and gaze point data, it is possible to dynamically capture the virtual elements where the user's sight is focused, accurately define the content that the user pays close attention to as a high privacy domain, and ensure accurate protection of sensitive data. The scene is divided into high privacy domain, medium privacy domain and low privacy domain, and hierarchical protection is implemented according to the importance of the area and the sensitivity of the data, effectively avoiding resource waste and meeting the security requirements of different data. As the user's gaze point moves, the high privacy domain, medium privacy domain and low privacy domain can be updated in real time, so that privacy protection dynamically adapts to the user's interactive behavior, improving the flexibility and real-time nature of protection. By differentially processing privacy domains, over-protection of low-sensitivity data is reduced, and encryption resources are concentrated on data protection in high privacy domains, significantly improving the operating efficiency and resource utilization of the system. The three-dimensional point cloud data is used to provide the structural information of the scene, and the gaze point data is used to reflect the user's focus. The combination of the two realizes efficient identification of key privacy areas in the scene. By classifying virtual elements, environmental objects and scene backgrounds, all components of the AR scene are covered to ensure the comprehensiveness of privacy protection. The division and dynamic adjustment of privacy domains are transparent to users and do not interfere with their normal operations and experience, thus enhancing the immersion and interaction fluency of AR applications. Based on the user's gaze point, the system can automatically adapt to the user's focus content, implement privacy protection strategies that vary from person to person, and improve user satisfaction and trust.

[0012] Optionally, storing the sensitive data in the privacy domain to obtain the data to be encrypted specifically includes: using a secret sharing algorithm to split the sensitive data into multiple binary data segments; if it is determined that the target binary data segment belongs to the core fragment of the sensitive data, using texture mapping technology to determine the target texture of the virtual element; according to the value of the target binary data segment, adjusting the value corresponding to the target texture to obtain first data to be embedded; embedding the first data to be embedded into the high privacy domain to obtain the data to be encrypted.

[0013] By adopting the above technical solution, sensitive data is split into multiple binary data segments through a secret sharing algorithm. Even if an attacker obtains part of the data segments, the complete sensitive data cannot be restored, which fundamentally improves the security of the data. This method cannot crack the data even if it is stolen because there is no complete key information, thereby effectively reducing the risk of leakage. By determining which data segments belong to the core part of the sensitive data, these key data can be specially protected, so that the core data is strengthened and protected, further improving the overall security. By using texture mapping technology to embed the core data into the target texture of the virtual element, the encrypted data can be hidden in a visually imperceptible texture, making the data embedding process invisible to both users and attackers, and enhancing the concealment of data protection. By adjusting the value of the target texture and embedding the encrypted data, the embedding of sensitive information will not change the visual appearance of the scene, and the attacker cannot detect the change of the data through conventional analysis methods, thereby avoiding being discovered by malicious attackers or monitoring systems. By splitting the data into multiple binary data segments and encrypting and protecting them according to their importance, a more fine-grained encryption strategy can be implemented, and different encryption strengths can be applied to different data segments, thereby improving the efficiency and security of the overall encryption process. Storing the encrypted data in a specific privacy domain not only improves the security of the data, but also reduces the potential risk of data leakage. This hierarchical storage method ensures that sensitive data only exists in the high-privacy area, and other low-privacy areas do not contain sensitive data, reducing the attack surface.

[0014] Optionally, the method also includes: if it is determined that the target binary data segment belongs to a redundant fragment of the sensitive data, encoding the target binary data segment into a decimal form to obtain encoded data; using a baseline transparency value as a default value, and embedding the encoded data into a small offset of transparency to obtain second data to be embedded; embedding the second data to be embedded into the low privacy domain to obtain the data to be encrypted.

[0015] By adopting the above technical solution, by encoding redundant slices into decimal form and embedding them into a small offset of transparency, the embedding of data hardly changes the visual effect. It is difficult for attackers to identify or extract embedded data through conventional means, thereby improving the concealment of data protection. The offset amplitude of the transparency value is very small, and the impact on the visual performance of the target AR scene can be ignored, ensuring that users cannot perceive the existence of data embedding, while avoiding destroying the user's immersive experience. Encoding the redundant slices of sensitive data into decimal form greatly reduces the storage occupancy of redundant data and optimizes the embedding efficiency. Using the transparency channel of the virtual object in the AR scene to embed data does not require additional storage space, fully utilizes the existing rendering resources, and saves system resources. Redundant slices are embedded in the low privacy domain and lightweight protection is performed through transparency offset. The low privacy domain does not contain sensitive content that users are highly concerned about, so this method can reduce the computational complexity while meeting the basic privacy protection requirements. According to the importance of the privacy domain, different encryption and embedding methods are used for the core slices and redundant slices to achieve hierarchical privacy protection, ensuring the centralized protection of highly sensitive data under limited resources. The data is split into core shards and redundant shards through a secret sharing algorithm. Even if part of the data segment is lost or attacked, the original data can still be restored as long as there are enough redundant shards. This design enhances the robustness and anti-corruption ability of the data protection scheme. Even if the embedded data in the low-privacy domain is stolen, since the encoded data in the transparency offset is a redundant shard, the attacker cannot reconstruct the complete sensitive data by parsing these shards alone, thereby further reducing the risk of data leakage.

[0016] Optionally, the method of assigning a dynamic key to the data to be encrypted and encrypting the data to be encrypted in combination with a preset encryption algorithm specifically includes: monitoring risk factors for the data to be encrypted through an edge computing device, the risk factors including data interception and network fluctuations; if it is determined that the risk factors indicate that there is no data interception and network fluctuations, obtaining the user's eye movement pattern; generating a random number based on the eye movement pattern using a pseudo-random number generation algorithm; and randomly generating the dynamic key using the random number.

[0017] By adopting the above technical solution, the user's eye movement pattern is a highly personalized and difficult-to-copy biological behavior data. Combined with the pseudo-random number generation algorithm, a unique and highly random dynamic key can be generated, effectively avoiding the security vulnerabilities in the traditional key generation method. The dynamic key relies on the random number generated in real time and does not need to be stored in the system for a long time, which fundamentally reduces the risk of key theft and enhances the security of the overall data encryption. With the help of edge computing devices to monitor risk factors such as data interception and network fluctuations in real time, the security of the current environment can be quickly judged to ensure that key generation and data encryption are carried out in a safe environment, and the dynamic response capability of the system is improved. If potential risks are monitored, such as network fluctuations or interception behaviors, the key generation or encryption process can be suspended to avoid performing sensitive operations in a high-risk environment, further reducing security risks. The dynamic key is generated according to the user's eye movement pattern and bound to the user's real-time behavior data to ensure that the key used for each encryption is unique, effectively avoiding security issues such as replay attacks. The user does not need to perform additional operations. The system can automatically collect data and generate dynamic keys through the eye tracking device, which is highly concealed and will not disturb the user's normal AR experience.

[0018] Optionally, the method also includes: if it is determined that the privacy domain is the high privacy domain, then using an encryption algorithm based on lattice cipher to assign the dynamic key to the high privacy domain; if it is determined that the privacy domain is the medium privacy domain, then using a medium-strength AES encryption algorithm to assign the dynamic key to the medium privacy domain; if it is determined that the privacy domain is the low privacy domain, then using a lightweight symmetric encryption algorithm to assign the dynamic key to the low privacy domain.

[0019] By adopting the above technical solutions, according to the importance of the privacy domain, different encryption algorithms of different strengths are dynamically selected to avoid traditional encryption methods and provide adaptive protection measures for different types of data, which is both safe and efficient. The high privacy domain uses a stronger encryption algorithm, such as an algorithm based on lattice cryptography, to ensure the security of highly sensitive data; while the low privacy domain uses a lightweight symmetric encryption algorithm to reduce resource usage and ensure the efficiency of system operation.

[0020] In a second aspect of the present application, a data encryption processing device applied to an AR scene is provided, the data encryption processing device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire three-dimensional point cloud data of a target AR scene and gaze point data of a user in the target AR scene, the user wearing AR glasses for displaying the target AR scene; the processing module is used to determine a privacy domain of the target AR scene based on the three-dimensional point cloud data and the gaze point data; the acquisition module is also used to acquire sensitive data of the target AR scene; the processing module is also used to store the sensitive data in the privacy domain to obtain data to be encrypted; the processing module is also used to assign a dynamic key to the data to be encrypted, and encrypt the data to be encrypted in combination with a preset encryption algorithm.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: Through the three-dimensional point cloud data and the user's gaze point data, the user's interest area and high-attention area in the target AR scene can be identified in real time, and these areas can be marked as privacy domains. This ensures that sensitive data is only associated with content that the user cares about, avoiding the waste of global protection resources. Based on the user's actual interactive behavior, the determination of the privacy domain is dynamic and personalized, adapting to the privacy protection needs of different users, and improving the accuracy of data protection. Combined with the three-dimensional point cloud information, not only can the geometric structure of the scene be obtained, but also the location of the virtual and real interactive content can be accurately located, providing spatial support for the division of privacy domains. The use of gaze point data reflects the user's real-time intention. Combining subjective interest areas with objective scene data helps to improve the rationality and credibility of privacy domain division. Aggregate storage of sensitive data in the privacy domain can reduce data redundancy, reduce the risk of sensitive data leakage, and provide convenience for subsequent encryption operations. Dynamically generating encryption keys based on real-time environment improves the flexibility and security of data protection, making the keys more difficult to predict and crack. Combined with different types of sensitive data, select a suitable data encryption algorithm to balance encryption strength and encryption efficiency. Therefore, it is easy to improve the efficiency of data encryption processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a data encryption processing method applied to an AR scenario provided in an embodiment of the present application; Figure 2 Another schematic diagram of a data encryption processing method applied to an AR scenario provided in an embodiment of the present application; Figure 3 A schematic diagram of a module of a data encryption processing device applied to an AR scenario provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0026] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] With the rapid development of augmented reality technology, its application has been widely used in many fields such as intelligent navigation, virtual meetings, personalized advertising and telemedicine. The realization of these immersive experiences requires the processing of a variety of private data including geographic location information, user behavior trajectories, facial recognition data and environmental perception information. These data are not only highly sensitive, but also directly related to user privacy and data security.

[0030] Current privacy protection technologies mainly rely on traditional data encryption methods. However, in AR scenarios, applications need to process multimodal data such as video, audio, and 3D point clouds at the same time. Since these data are complex and interrelated, traditional encryption methods cannot meet the diverse protection needs of multimodal data while ensuring high security, which often leads to low encryption processing efficiency and makes it difficult to meet the high requirements of AR scenarios for real-time performance and flexibility.

[0031] In order to solve the above technical problems, the present application provides a data encryption processing method applied to AR scenarios, referring to Figure 1 , Figure 1 This is a flow chart of a data encryption processing method applied to an AR scene provided in an embodiment of the present application. The method is applied to a server and includes steps S110 to S150, which are as follows: S110, obtaining three-dimensional point cloud data of a target AR scene and gaze point data of a user in the target AR scene, wherein the user wears AR glasses for displaying the target AR scene.

[0032] Specifically, as the core computing device, the server is responsible for processing and storing the data uploaded from the AR glasses. Its main task is to obtain and analyze the three-dimensional point cloud data of the target scene and the user's gaze point data. These data provide the basis for subsequent scene understanding and personalized interaction. The three-dimensional point cloud data is collected by sensors such as the depth camera or lidar on the AR glasses, and can accurately describe the three-dimensional spatial structure of objects and environments in the target AR scene. The point cloud data is represented in the form of a series of point coordinates and is used to reconstruct the three-dimensional model of the scene. The gaze point data is collected by the eye tracking sensor built into the AR glasses. The eye sensor tracks the user's eye movement and determines the user's specific focus area in the target scene. The role of the gaze point data is to capture the user's points of interest, thereby providing a basis for the dynamic processing of data in the scene and the division of privacy domains. Among them, AR glasses, as the main interactive device, are not only used to display the target AR scene, but also responsible for capturing the user's line of sight and scene information in real time, and transmitting the data to the server for calculation and storage. It is a bridge between data collection and display.

[0033] In a possible implementation, obtaining three-dimensional point cloud data of a target AR scene and gaze point data of a user in the target AR scene specifically includes: receiving original scene image data of the target AR scene sent by a depth camera; analyzing the original scene image data using an environmental perception model to generate three-dimensional point cloud data; receiving eye movement data for the user sent by an eye tracking sensor; and determining the gaze point data using a gaze point analysis algorithm based on the eye movement data.

[0034] Specifically, the depth camera is used to capture the depth information in the AR scene. The depth information can describe the distance between each object in the scene and the camera, forming the basic data of the three-dimensional scene. The eye tracking sensor tracks the user's eye movement in real time, collects the user's gaze direction and points of interest, and is used to determine the specific location or target that the user is paying attention to. After the depth camera shoots the target scene, the generated raw image data includes a two-dimensional color image and depth information. These data are transmitted to the server or computing device as the basic input for subsequent analysis. The raw image data is analyzed and processed through an environmental perception model, such as an algorithm based on machine learning or computer vision, and the two-dimensional image data and depth information are converted into three-dimensional point cloud data. The point cloud data represents the three-dimensional coordinates of each object in the scene in the form of discrete points, which is used to construct a three-dimensional structural model of the entire scene. The eye tracking sensor monitors the user's eye movements and captures the user's line of sight and gaze focus. Based on the eye movement data, a specific gaze point analysis algorithm, such as geometric mapping, heat map generation, etc., is used to calculate the corresponding position of the user's gaze point in the three-dimensional scene. These gaze point data can reflect the user's focus area or point of interest.

[0035] S120: Determine a privacy domain of the target AR scene based on the three-dimensional point cloud data and the gaze point data.

[0036] Specifically, the high privacy domain is the area where the user's sight is frequently focused or continuously stayed. For example, the virtual object that the user is looking at, the personal information display area, etc. The medium privacy domain is the environmental object that the user may indirectly pay attention to. For example, the furniture or environmental objects around the user. The low privacy domain is the background part of the scene or the area that does not involve privacy, such as the distant scenery or background wall.

[0037] For example, the server analysis found that the user's gaze was mainly focused on the virtual memo area, so it was marked as a high privacy domain. This area may contain the user's private information, such as meeting minutes, to-do items, etc. The conference table that the user occasionally pays attention to is marked as a medium privacy domain because it may contain sensitive content such as documents and items. The company logo on the background wall and other unfocused areas are marked as low privacy domains because they do not involve the user's personal privacy.

[0038] In a possible implementation, the privacy domain of the target AR scene is determined based on the three-dimensional point cloud data and the gaze point data, specifically including: determining the virtual elements on which the user's line of sight is focused from the three-dimensional point cloud data and the gaze point data; determining the virtual elements as the high privacy domain; determining the environmental objects of the target AR scene from the three-dimensional point cloud data and the gaze point data; determining the environmental objects as the medium privacy domain; determining the scene background of the target AR scene from the three-dimensional point cloud data and the gaze point data; and determining the scene background as the low privacy domain.

[0039] Specifically, the main focus of the user's line of sight is determined through gaze point data. These virtual elements may be content that the user interacts directly with or areas containing sensitive information. For example: personal information on the virtual screen, sensitive virtual objects, or content that needs to be strictly protected. Perform high-level privacy protection on these areas, such as strong encryption and access control. The medium privacy domain is the environmental objects extracted from the three-dimensional point cloud data, which are areas that the user may indirectly focus on. For example, objects around the user, furniture, or some objects that are not related to the operation but are related to the scene. These areas have lower privacy requirements and can adopt medium-intensity protection strategies. The low privacy domain includes the scene background that the user does not actively pay attention to and does not contain sensitive information, such as distant scenery, blank walls, or other insignificant scene information. Take basic protection measures for these areas or ignore special protection directly.

[0040] S130: Acquire sensitive data of the target AR scene.

[0041] Specifically, in AR scenarios, sensitive data refers to specific data types related to user privacy, personal information, or key content, such as: user personal identity information, such as name, avatar, account information; user activity data, such as gaze point, behavior trajectory; content data in interaction, such as virtual items or interaction records; private data in the environment, such as home layout, room structure. The server collects raw data of the target AR scene through cameras, sensors, and AR glasses. The server extracts information related to user interaction from these raw data. Identify which data is sensitive data through preset rules or models.

[0042] S140: Store the sensitive data in the privacy domain to obtain the data to be encrypted.

[0043] Specifically, the data to be encrypted is the data stored in the privacy domain and marked as data that needs to be encrypted. According to its privacy level, select the appropriate encryption strength and algorithm. After the server collects sensitive data, it classifies the data into different privacy domains based on the privacy domain division model. Record which data needs to be encrypted and select the corresponding encryption algorithm according to the privacy level.

[0044] In one possible implementation, sensitive data is stored in a privacy domain to obtain data to be encrypted, specifically including: using a secret sharing algorithm to split the sensitive data into multiple binary data segments; if it is determined that the target binary data segment belongs to the core fragment of the sensitive data, then using texture mapping technology to determine the target texture of the virtual element; according to the value of the target binary data segment, adjusting the value corresponding to the target texture to obtain first data to be embedded; embedding the first data to be embedded into a high privacy domain to obtain data to be encrypted.

[0045] Specifically, the secret sharing algorithm is an encryption technology that divides sensitive data into multiple binary data segments and distributes these data segments to different storage locations or objects. This prevents attackers from obtaining the complete sensitive data even if part of the data is leaked, thereby increasing security. For example, suppose there is a data block containing sensitive information (such as a payment password). The secret sharing algorithm will divide this data block into multiple shards, each of which contains only part of the data. Each shard itself is meaningless, and only by recombining these shards can the complete sensitive data be restored. The core shard refers to the key part of the sensitive data, which is the most important part of the data and must be protected at the highest level.

[0046] In augmented reality applications, virtual elements refer to visual objects (such as virtual objects or markers) in the AR scene. Texture mapping technology embeds data into the appearance (i.e., texture) of these virtual elements, making sensitive data visually "invisible" but still protected at the technical level. For example, assuming there is a virtual product (such as a virtual shoe), sensitive data can be embedded in the surface pattern of the shoe through texture mapping, so that the appearance of the shoe is associated with the data, but the outside world cannot directly see the data. For the target data of the core shard, the color, details and other attributes of the texture can be adjusted according to the value of the data. This adjustment not only ensures that the data is embedded in the virtual object, but also makes the embedded data information hidden in the virtual scene and can only be extracted through specific decryption technology. For example, if the shard data is "1101", the color or transparency of the texture may change accordingly, such as becoming slightly transparent or changing the hue to covertly represent the data.

[0047] High privacy domains refer to those areas that require extremely high user privacy protection (such as user identity, passwords and other sensitive information). Sensitive data stored in these areas require the strongest encryption protection. The adjusted embedded data (i.e., the first data to be embedded) is stored in this high privacy domain to ensure that the data in this area is protected at the highest level. For example, the texture of a virtual object (such as a virtual shoe) is adjusted and embedded with sensitive data (such as a password) and stored in the high privacy domain of the AR application. This ensures that only authorized users or systems can access the sensitive data.

[0048] For example, assume that the target AR scene is sensitive data protection in AR virtual shopping. Users enter the virtual shopping scene through AR glasses, browse virtual goods and make payments. In this process, the system needs to protect the user's payment password, shopping records and other sensitive data. The user's payment password is split into multiple binary data segments by the secret sharing algorithm, such as "1101", "0110", "1001", etc. These data segments are stored in the textures of different virtual goods, and each data segment is embedded in the texture mapping of a specific virtual element (such as virtual shoes, virtual clothes). Among them, a key virtual product (such as a pair of shoes) is selected as the target texture of the high privacy domain. The surface texture of the shoe is adjusted according to the core slice of the payment password (such as "1101"), so that its color and transparency change, but these changes are invisible to ordinary users. For example, the color of the texture may change from standard blue to reddish, or its transparency may change slightly. These changes are only to hide data, not to change the appearance of the object. Finally, these adjusted textures (first data to be embedded) are stored in the high privacy domain, that is, the area where the user's payment information and account information are located. In this way, only authorized systems or devices can access the textures of these virtual objects, decrypt and recover the user's sensitive data.

[0049] Through the above steps, the server can use elements in the virtual scene, such as texture, transparency, etc. to covertly store and protect sensitive data. The combination of encryption and steganography can not only effectively protect user privacy, but also ensure the security of sensitive information in augmented reality scenes. This method improves user experience while ensuring data privacy and security.

[0050] In one possible implementation, if it is determined that the target binary data segment belongs to a redundant fragment of sensitive data, the target binary data segment is encoded into a decimal form to obtain encoded data; the baseline transparency value is used as a default value, and the encoded data is embedded into a small offset of the transparency to obtain second data to be embedded; the second data to be embedded is embedded into a low privacy domain to obtain data to be encrypted.

[0051] Specifically, during the encryption of sensitive data, some data may not be critical data but redundant. Redundant slices are backup data used to recover data. A single redundant slice is not sufficient to recover sensitive information, but in a complete slice, they play a role of protection and redundancy. The data of these redundant slices are encoded in decimal form in order to store the data in a more concealed manner to prevent it from being directly identified or extracted. This encoding method can make the data look more "fuzzy", thereby increasing the difficulty of data protection. For example, if the redundant slice is binary data "1101", it may be converted into a decimal "2.75", which is more difficult to directly understand and extract than the original binary data. The transparency value is used to describe the transparency of the surface of an object. The larger the value, the more opaque the object, and the smaller the value, the more transparent the object. The baseline transparency value here is used as the default value, that is, the initial transparency, representing the standard display state of the virtual element. For example, assuming that the baseline transparency value is 0.8, this means that the transparency of the virtual object is 80%, that is, only 20% of the part is transparent.

[0052] Among them, redundant data is stored covertly in the texture of the virtual object by slightly adjusting the transparency value, and these adjustments are imperceptible to the naked eye. For example, if the encoded data is "2.75", it may correspond to a slight change in the transparency value (for example, from 0.8 to 0.802), which is small enough to be directly perceived by the user's vision, but it can store data covertly. Low privacy domain refers to areas with low data protection requirements. The data in these areas does not involve very sensitive user information and may be some public or shareable data. In AR scenarios, this may be some background information or environmental data that is not closely related to user privacy. For example, the background and environmental scenery of virtual objects can be used as low privacy domains, and these data are not critical to protecting user privacy. By embedding the second data to be embedded (i.e., the adjusted transparency data) into the virtual elements (such as background texture) in the low privacy domain, redundant data can be stored covertly without affecting the user experience. For example, the transparency is adjusted on the background texture of the virtual scene, so that it "invisibly" carries redundant data. What the user sees is still a normal virtual scene, but the data has been encrypted and hidden behind it. In this process, redundant data has been successfully embedded into virtual elements in low-privacy domains by fine-tuning transparency, and the data is invisible. In this way, the data to be encrypted is ready and can be further encrypted when needed to ensure data security. For example, the background texture of the virtual object has been adjusted to hide the redundant shard data and wait for subsequent encryption operations.

[0053] For example, assume that the target AR scenario is sensitive data protection in AR games. Users experience games in the virtual game world through AR glasses. The game involves sensitive data of users, such as account information, game records, etc., but some data is redundant and does not directly affect the game. The user's game data (such as "combat power points") is split into multiple data slices, one of which is redundant data. This redundant data may be "1101", which is encoded into "2.75" for further concealment. On the texture of the virtual game background, the baseline transparency value is set to 0.8. In order to embed the redundant data "2.75", the transparency value is slightly adjusted to 0.802, and this change is almost imperceptible to the user. These fine-tuned transparency data are embedded in the background texture (low privacy domain) of the virtual game. The transparency values ​​of background objects (such as the sky, the ground, etc.) are slightly adjusted to ensure that the redundant data is stored in them covertly. Although the transparency of the background texture has changed slightly and the user cannot detect it, the redundant part of the sensitive data has been hidden in the virtual environment and can be encrypted at any time to ensure data security.

[0054] S150: Allocate a dynamic key to the data to be encrypted, and encrypt the data to be encrypted in combination with a preset encryption algorithm.

[0055] Specifically, in the encryption process, the key is a key factor in protecting data security. A dynamic key refers to a new, temporary key that is generated each time encryption is performed. Unlike a static key, a dynamic key is different each time, which effectively increases the difficulty of data cracking. Dynamic keys are generated through some random algorithms, user behavior data, or external factors. This key generation method not only increases the security of the encryption process, but also prevents attackers from obtaining the content of multiple data by cracking static keys. Assuming that a user is using AR glasses to browse virtual content, the server will generate a new dynamic key through a pseudo-random number generation algorithm based on the real-time environment, the user's interactive behavior (such as eye movement data), and other information. Each time encryption is performed, this new key is used to encrypt the data.

[0056] Among them, the encryption algorithm is a specific technical solution used to encrypt data. The preset encryption algorithm refers to an encryption algorithm that has been selected and fixed during the design, such as a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA). When encryption is combined with a dynamic key, the selected encryption algorithm will use the key to process the encrypted data, so that the original data is converted into unrecognizable encrypted data, and only those who have the corresponding key can decrypt and restore it. The encryption algorithm can choose an encryption method that adapts to different security requirements. For example, some applications may require higher-intensity encryption, such as an encryption algorithm based on a lattice cipher, or a lighter-weight encryption algorithm, such as the AES encryption algorithm.

[0057] In one possible implementation, a dynamic key is assigned to the data to be encrypted, and the data to be encrypted is encrypted in combination with a preset encryption algorithm, specifically including: monitoring risk factors for the data to be encrypted through an edge computing device, the risk factors including data interception and network fluctuations; if it is determined that the risk factors indicate that there is no data interception and network fluctuations, obtaining the user's eye movement pattern; generating a random number based on the eye movement pattern using a pseudo-random number generation algorithm; and randomly generating a dynamic key using the random number.

[0058] Specifically, edge computing devices refer to computing devices or servers deployed at the edge of the network, close to the data source. Edge computing devices can process data from user devices in real time and respond quickly. Risk factors include factors that may threaten data security, such as data interception and network fluctuations. Data interception refers to malicious attackers intercepting data during transmission, while network fluctuations may affect the stability of data transmission. Edge computing devices monitor these risk factors in real time. If the server detects the risk of data interception or large network fluctuations, it will take measures to prevent data leakage or loss. Assuming that the user is browsing virtual reality content through AR glasses, the edge computing device can detect in real time whether the user's network environment is stable. If it is found that the network fluctuations are large or the risk of data interception is high, the server will automatically respond to protect data security.

[0059] When the monitoring data is not intercepted and the network is stable, the server will further analyze the user's behavior pattern. The eye movement pattern here refers to the movement trajectory and gaze point of the user's eyes, such as the object the user is looking at in the AR scene and the viewing time. Eye movement data can provide valuable information about where the user's attention is focused and what content they are paying attention to in the AR application. The server can generate a random value related to the user's behavior based on this data. Suppose a user is looking at a car in an AR scene, the server will capture the user's eye movement data to determine whether the user is looking at the car continuously. If the user's eye movement pattern indicates that he has been looking at an element (such as a virtual object) for a long time, the server may generate an encryption key based on this behavior.

[0060] Once the user's eye movement pattern is obtained, the server uses a pseudo-random number generation algorithm (PRNG) to generate a random number based on the eye movement data. The pseudo-random number generation algorithm generates values ​​that appear random but are actually predictable through a specific mathematical formula. In this step, the pseudo-random number generation algorithm generates a random number based on the characteristics of the eye movement pattern, such as the speed of the eye movement, the duration of the gaze, the type of object being focused, etc., as the basis for the subsequent generation of a dynamic key.

[0061] In one possible implementation, refer to Figure 2 , Figure 2 Another flow chart of a data encryption processing method applied to an AR scene provided by an embodiment of the present application. It includes steps S210 to S230, and the above steps are as follows: S210, if the privacy domain is determined to be a high privacy domain, a lattice-based encryption algorithm is used to allocate dynamic keys to the high privacy domain; S220, if the privacy domain is determined to be a medium privacy domain, a medium-strength AES encryption algorithm is used to allocate dynamic keys to the medium privacy domain; S230, if the privacy domain is determined to be a low privacy domain, a lightweight symmetric encryption algorithm is used to allocate dynamic keys to the low privacy domain.

[0062] Specifically, lattice cryptography is a new encryption algorithm that is resistant to quantum computing attacks. It is currently recognized as one of the encryption schemes designed for future quantum computing environments. The advantage of lattice cryptography is that even quantum computers find it difficult to crack encryption based on lattice problems. Data in high-privacy domains contain extremely sensitive personal information of users, such as facial recognition data, medical records, financial information, etc. Once leaked, this information will seriously threaten the privacy and security of users. Suppose in a medical AR application, the user's health data (such as genetic information, medical records, etc.) needs to be encrypted and stored. These data belong to the high-privacy domain, so an encryption algorithm based on lattice cryptography will be chosen to ensure the extremely high security of the data to prevent leakage or cracking.

[0063] The AES algorithm is a widely used symmetric encryption algorithm with high security and low computational complexity, and is suitable for most application scenarios. The security of AES is one of the strongest encryption algorithms known to date, especially for data with medium-strength security requirements. Data in the medium privacy domain may include user behavior data, communication records, etc., which also need to be protected in some cases, but their sensitivity is lower than that of data in the high privacy domain. In an AR-based smart navigation application, the user's geographic location data belongs to the medium privacy domain, because the leakage of this data may affect the user's privacy, but the impact is not as serious as facial recognition data. In this case, the AES encryption algorithm can be used to encrypt the location data to ensure the security of data transmission.

[0064] Lightweight symmetric encryption algorithms, such as XTEA and RC4, are simpler and faster encryption methods than AES and lattice-based encryption algorithms, and are mainly used for devices with limited resources (such as IoT devices, embedded devices, etc.). These encryption algorithms are suitable for data transmission or storage scenarios with high performance requirements, but their security is lower than that of AES, etc. Data in the low-privacy domain refers to non-sensitive or public content, such as environmental data, scene background information, etc. Even if these data are leaked, they have little impact on the user's privacy, so lightweight encryption algorithms can be used. In an AR advertising application, the advertising content or background image data in the scene may belong to the low-privacy domain. The user's interactive behavior with the advertisement, the display data of the advertisement, etc. do not involve personal privacy, so lightweight encryption algorithms, such as RC4, can be used to quickly encrypt these data to improve application performance while maintaining a certain degree of security.

[0065] This application also provides a data encryption processing device applied to AR scenarios, referring to Figure 3 , Figure 3 A module schematic diagram of a data encryption processing device applied to an AR scene provided in an embodiment of the present application. The data encryption processing device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the three-dimensional point cloud data of the target AR scene and the gaze point data of the user in the target AR scene, and the user wears AR glasses for displaying the target AR scene; the processing module 32 determines the privacy domain of the target AR scene according to the three-dimensional point cloud data and the gaze point data; the acquisition module 31 acquires the sensitive data of the target AR scene; the processing module 32 stores the sensitive data in the privacy domain to obtain the data to be encrypted; the processing module 32 allocates a dynamic key to the data to be encrypted, and encrypts the data to be encrypted in combination with a preset encryption algorithm.

[0066] In a possible implementation, the acquisition module 31 acquires three-dimensional point cloud data of the target AR scene and the gaze point data of the user in the target AR scene, specifically including: the acquisition module 31 receives the original scene image data of the target AR scene sent by the depth camera; the processing module 32 uses the environmental perception model to analyze the original scene image data to generate three-dimensional point cloud data; the acquisition module 31 receives the eye movement data of the user sent by the eye tracking sensor; the processing module 32 determines the gaze point data based on the eye movement data using a gaze point analysis algorithm.

[0067] In a possible implementation, the processing module 32 determines the privacy domain of the target AR scene based on the three-dimensional point cloud data and the gaze point data, specifically including: the processing module 32 determines the virtual elements on which the user's line of sight is focused from the three-dimensional point cloud data and the gaze point data; the processing module 32 determines the virtual elements as a high privacy domain; the processing module 32 determines the environmental objects of the target AR scene from the three-dimensional point cloud data and the gaze point data; the processing module 32 determines the environmental objects as a medium privacy domain; the processing module 32 determines the scene background of the target AR scene from the three-dimensional point cloud data and the gaze point data; the processing module 32 determines the scene background as a low privacy domain.

[0068] In one possible implementation, the processing module 32 stores the sensitive data in a privacy domain to obtain data to be encrypted, specifically including: the processing module 32 uses a secret sharing algorithm to split the sensitive data into multiple binary data segments; if the processing module 32 determines that the target binary data segment belongs to the core fragment of the sensitive data, the texture mapping technology is used to determine the target texture of the virtual element; the processing module 32 adjusts the value corresponding to the target texture according to the value of the target binary data segment to obtain the first data to be embedded; the processing module 32 embeds the first data to be embedded into the high privacy domain to obtain the data to be encrypted.

[0069] In one possible implementation, if the processing module 32 determines that the target binary data segment belongs to a redundant fragment of sensitive data, the target binary data segment is encoded into a decimal form to obtain encoded data; the processing module 32 uses the baseline transparency value as a default value, and embeds the encoded data into a small offset of the transparency to obtain second data to be embedded; the processing module 32 embeds the second data to be embedded into the low privacy domain to obtain data to be encrypted.

[0070] In one possible implementation, the processing module 32 assigns a dynamic key to the data to be encrypted, and encrypts the data to be encrypted in combination with a preset encryption algorithm, specifically including: the processing module 32 monitors the risk factors for the data to be encrypted through an edge computing device, the risk factors including data interception and network fluctuations; if the processing module 32 determines that the risk factors indicate that there is no data interception and network fluctuations, the user's eye movement pattern is obtained; the processing module 32 generates a random number based on the eye movement pattern using a pseudo-random number generation algorithm; the processing module 32 uses the random number to randomly generate a dynamic key.

[0071] In one possible implementation, if the processing module 32 determines that the privacy domain is a high privacy domain, a lattice-based encryption algorithm is used to assign dynamic keys to the high privacy domain; if the processing module 32 determines that the privacy domain is a medium privacy domain, a medium-strength AES encryption algorithm is used to assign dynamic keys to the medium privacy domain; if the processing module 32 determines that the privacy domain is a low privacy domain, a lightweight symmetric encryption algorithm is used to assign dynamic keys to the low privacy domain.

[0072] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0073] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0074] The communication bus 42 is used to realize the connection and communication between these components.

[0075] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0076] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0077] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0078] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for a data encryption processing method applied to an AR scenario.

[0079] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application stored in the memory 45 for a data encryption processing method applied to an AR scenario. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0080] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0081] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0082] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0086] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0087] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A data encryption processing method applied to AR scenarios, characterized in that: The method comprises: Acquire three-dimensional point cloud data of a target AR scene and gaze point data of a user in the target AR scene, wherein the user wears AR glasses for displaying the target AR scene; Determining a privacy domain of the target AR scene according to the three-dimensional point cloud data and the gaze point data; Acquire sensitive data of the target AR scene; Storing the sensitive data in the privacy domain to obtain data to be encrypted; A dynamic key is allocated to the data to be encrypted, and the data to be encrypted is encrypted in combination with a preset encryption algorithm.

2. The data encryption processing method applied to AR scenarios according to claim 1 is characterized in that: The acquiring of the three-dimensional point cloud data of the target AR scene and the gaze point data of the user in the target AR scene specifically includes: Receiving original scene image data of the target AR scene sent by the depth camera; Analyzing the original scene image data using an environmental perception model to generate the three-dimensional point cloud data; receiving eye movement data of the user sent by an eye tracking sensor; The gaze point data is determined by using a gaze point analysis algorithm according to the eye movement data.

3. The data encryption processing method applied to AR scenarios according to claim 1 is characterized in that: The determining, according to the three-dimensional point cloud data and the gaze point data, a privacy domain of the target AR scene specifically includes: Determining a virtual element where the user's line of sight is focused from the three-dimensional point cloud data and the gaze point data; determining the virtual element as a high privacy domain; Determining an environmental object of the target AR scene from the three-dimensional point cloud data and the gaze point data; Determining the environmental object as a medium privacy domain; Determining a scene background of the target AR scene from the three-dimensional point cloud data and the gaze point data; The scene background is determined as a low privacy domain.

4. The data encryption processing method applied to AR scenarios according to claim 3 is characterized in that: The storing the sensitive data in the privacy domain to obtain the data to be encrypted specifically includes: Splitting the sensitive data into multiple binary data segments using a secret sharing algorithm; If it is determined that the target binary data segment belongs to the core slice of the sensitive data, a texture mapping technique is used to determine the target texture of the virtual element; According to the value of the target binary data segment, adjusting the value corresponding to the target texture to obtain first data to be embedded; The first data to be embedded is embedded into the high privacy domain to obtain the data to be encrypted.

5. The data encryption processing method applied to AR scenarios according to claim 4 is characterized in that: The method further comprises: If it is determined that the target binary data segment belongs to a redundant fragment of the sensitive data, encoding the target binary data segment into a decimal form to obtain encoded data; Using a reference transparency value as a default value, and embedding the encoded data into a small offset of the transparency to obtain second data to be embedded; The second data to be embedded is embedded into the low privacy domain to obtain the data to be encrypted.

6. The data encryption processing method applied to AR scenarios according to claim 3 is characterized in that: The step of allocating a dynamic key to the data to be encrypted and encrypting the data to be encrypted in combination with a preset encryption algorithm specifically includes: Monitoring risk factors for the data to be encrypted by an edge computing device, wherein the risk factors include data interception and network fluctuations; If it is determined that the risk factor indicates that there is no data interception and network fluctuation, obtaining the eye movement pattern of the user; Generate a random number using a pseudo-random number generation algorithm according to the eye movement pattern; The dynamic key is randomly generated using the random number.

7. The data encryption processing method applied to AR scenarios according to claim 6 is characterized in that: The method further comprises: If it is determined that the privacy domain is the high privacy domain, using an encryption algorithm based on a lattice cipher to allocate the dynamic key to the high privacy domain; If it is determined that the privacy domain is the medium privacy domain, using a medium strength AES encryption algorithm to allocate the dynamic key to the medium privacy domain; If it is determined that the privacy domain is the low privacy domain, a lightweight symmetric encryption algorithm is used to allocate the dynamic key to the low privacy domain.

8. A data encryption processing device applied to AR scenarios, characterized in that: The data encryption processing device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire three-dimensional point cloud data of a target AR scene and gaze point data of a user in the target AR scene, wherein the user wears AR glasses for displaying the target AR scene; The processing module (32) is used to determine the privacy domain of the target AR scene according to the three-dimensional point cloud data and the gaze point data; The acquisition module (31) is further used to acquire sensitive data of the target AR scene; The processing module (32) is further used to store the sensitive data in the privacy domain to obtain data to be encrypted; The processing module (32) is also used to allocate a dynamic key to the data to be encrypted, and encrypt the data to be encrypted in combination with a preset encryption algorithm.

9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images