Methods and systems for processing sensitive data in the metaverse

Abstract

This invention provides a method and system for processing sensitive data in the metaverse. The method includes: determining multiple flow data features of a target data flow scenario in the metaverse; determining preferred data features from the multiple flow data features based on the historical behavior data of a first target digital human; determining a first preferred feature attribute value and a second preferred feature attribute value based on the preferred data features; determining whether the preferred data feature is a sensitive data feature based on the first preferred feature attribute value and the second preferred feature attribute value; if so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data. This invention improves data security in the metaverse.

Description

Technical Field

[0001] This invention relates to the field of metaverse technology, and in particular to a method and system for processing sensitive data in the metaverse. Background Technology

[0002] In the real world, when data is generated, in order to protect personal privacy and sensitive information, it is usually done by manually specifying which data items are sensitive data, and then desensitizing the sensitive data. For example, personal identification information, sensitive identifiers, etc. are directly deleted or replaced with anonymous identifiers, or specific algorithms are used to desensitize the data.

[0003] The Metaverse is a virtual world created and linked using technological means, mapping and interacting with the real world. In the current representation of the Metaverse, existing methods for desensitizing specific data items are unsuitable because the Metaverse's data is fluid and cannot be directly and accurately designated as sensitive. This could easily lead to the leakage of sensitive data within the Metaverse, compromising data security.

[0004] Therefore, there is an urgent need for a sensitive data processing method and system for the metaverse to solve the above problems. Summary of the Invention

[0005] In view of the problems existing in the prior art, the present invention provides a method and system for processing sensitive data in the metaverse.

[0006] This invention provides a method for processing sensitive data in the metaverse, comprising:

[0007] Identify multiple flow data characteristics of the target data flow scenario in the metaverse;

[0008] Based on the historical behavioral data of the first target digital human, preference data features are determined from multiple flow data features, wherein the first target digital human is a digital human that sends data interaction requests in the target data flow scenario;

[0009] Based on the preference data features, a first preference feature attribute value and a second preference feature attribute value are determined, wherein the first preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the first target digital human, and the second preference feature attribute value is the preference data feature value corresponding to the preference data features of the second target digital human, and the second target digital human is the digital human receiving the data interaction request in the target data flow scenario;

[0010] Based on the first preference feature attribute value and the second preference feature attribute value, it is determined whether the preference data feature is a sensitive data feature. If so, the data corresponding to the sensitive data feature is encrypted to obtain encrypted data.

[0011] According to a sensitive data processing method for the metaverse provided by the present invention, the step of determining preference data features from multiple flow feature data based on the historical behavioral data of a first target digital human includes:

[0012] Determine the historical behavior data corresponding to each of the aforementioned flow data features;

[0013] Based on the basic identity attributes of the first target digital person, multiple third target digital persons in the target data flow scenario are obtained, wherein the basic identity attributes of the multiple third target digital persons are the same as the basic identity attributes of the first target digital person;

[0014] Based on the similarity between the first target digital person and each of the third target digital persons, a fourth target digital person is determined from the plurality of third target digital persons;

[0015] Based on the historical behavior data corresponding to the first target digital person and the fourth target digital person respectively, obtain the flow feature preference value of each flow data feature of the first target digital person;

[0016] The flow data feature whose flow feature preference value satisfies the preset preference feature threshold is determined as the preference data feature.

[0017] According to a sensitive data processing method for the metaverse provided by the present invention, the step of obtaining the flow feature preference values ​​of each flow data feature of the first target digital person based on the historical behavior data corresponding to the first target digital person and the fourth target digital person includes:

[0018] Based on the historical behavioral data corresponding to the same type of flow data features of the first target digital person and the fourth target digital person, the flow feature preference value of the flow data feature corresponding to the first target digital person is calculated using the preference value calculation formula, which is:

[0019]

[0020] Among them, nr Bi nr represents the total amount of historical behavioral data corresponding to the i-th flow data feature of the first target digital person. B Let j represent the total historical behavioral data of all the aforementioned flow data features of the first target digital human, and nr represent the j-th fourth target digital human.Cji nr represents the total amount of historical behavioral data corresponding to the i-th flow data feature of the j-th fourth target digital person. Cj J represents the total amount of historical behavioral data of all the flow data features of the j-th fourth target digital human, and J represents the total number of the fourth target digital human.

[0021] According to a sensitive data processing method for the metaverse provided by the present invention, the step of determining a first preference feature attribute value and a second preference feature attribute value based on the preference data features includes:

[0022] Obtain the feature parameters corresponding to each of the aforementioned preference data features;

[0023] Based on the ratio between the feature parameters and the corresponding standard parameters, the preference feature attribute values ​​of each preference data feature are obtained;

[0024] The step of determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value includes:

[0025] If the value of the first preference feature attribute is less than the value of the second preference feature attribute, then the preference data feature corresponding to the value of the first preference feature attribute is determined to be the sensitive data feature.

[0026] According to a sensitive data processing method for the metaverse provided by the present invention, determining multiple flow data characteristics of a target data flow scenario in the metaverse includes:

[0027] Receive a first input, the first input including a request for image data display initiated by the first target digital human;

[0028] In response to the first input, the target data flow scenario is determined to be an image display scenario and a plurality of corresponding flow data features in the image display scenario, wherein the plurality of flow data features include at least the body shape features, facial features, skin features and clothing features of the digital human.

[0029] According to a sensitive data processing method for a metaverse provided by the present invention, after determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value, and if so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data, the method further includes:

[0030] Determine whether the first target digital human has the feature acquisition permission corresponding to the encrypted data. If it does, send the decoding method of the encrypted data to the first target digital human.

[0031] If not, display the virtual image of the second target digital human to the first target digital human.

[0032] The present invention also provides a sensitive data processing system for the metaverse, comprising:

[0033] The flow scene determination module is used to determine multiple flow data features of the target data flow scene in the metaverse;

[0034] The preference data feature determination module is used to determine preference data features from multiple flow data features based on the historical behavior data of the first target digital human, wherein the first target digital human is a digital human that sends data interaction requests in the target data flow scenario;

[0035] The preference feature attribute value calculation module is used to determine a first preference feature attribute value and a second preference feature attribute value based on the preference data features, wherein the first preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the first target digital person, and the second preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the second target digital person, and the second target digital person is the digital person receiving the data interaction request in the target data flow scenario;

[0036] The sensitive data feature processing module is used to determine whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value. If so, the data corresponding to the sensitive data feature is encrypted to obtain encrypted data.

[0037] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the sensitive data processing method for the metaverse as described above.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the sensitive data processing method for the metaverse as described above.

[0039] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the sensitive data processing method for the metaverse as described above.

[0040] The present invention provides a method and system for processing sensitive data in the metaverse. By using the historical behavioral data of digital humans in the metaverse, it determines the preference data features from multiple flow data features. Then, based on the preference data features, it determines whether the preference data features are sensitive data features according to the preference feature attribute values ​​between digital humans. If so, it encrypts the data corresponding to the sensitive data features, thereby more accurately determining the sensitive data in the metaverse and improving the data security in the metaverse. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 A flowchart illustrating the sensitive data processing method for the metaverse provided by this invention;

[0043] Figure 2 A schematic diagram of the structure of the sensitive data processing system for the metaverse provided by the present invention;

[0044] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0046] The metaverse is a virtual reality application scenario that can be connected on a large scale. It can integrate multiple new technologies to generate new types of virtual and real internet applications and social forms. It provides immersive experiences based on extended reality technology, generates a mirror image of the real world based on digital twin technology, and builds an economic system based on blockchain technology. It closely integrates the virtual world and the real world through economic, social and identity systems, and allows each participant to produce content and edit the world.

[0047] Data in the metaverse also possesses value. If valuable, sensitive data is leaked, it not only affects the secure operation of the metaverse but also poses a risk of data breaches to the real world. In the real world, data is typically anonymized during generation, designating sensitive data items. However, the real world doesn't consider the value of that sensitive data in practical applications during anonymization. In the metaverse, data value lies in data flow. That is, data has value if it is useful to the data recipient during data interaction. If the data recipient lacks the necessary permissions but obtains valuable data, a data breach occurs, and that data becomes sensitive to the recipient.

[0048] This invention addresses data flow scenarios in the metaverse by determining the value of data to the flow object (i.e., the data receiver initiating the data request) within that scenario. This leads to the identification of sensitive features. If a sensitive feature exists, it is encrypted until the flow object gains access to view it. Only then is the flow object allowed to access the actual data associated with that sensitive feature. This ensures that sensitive features are determined based on value, improving their accuracy and flexibility.

[0049] Figure 1 This is a flowchart illustrating the sensitive data processing method for the metaverse provided by the present invention, as shown below. Figure 1 As shown, this invention provides a method for processing sensitive data in the metaverse, comprising:

[0050] Step 101: Determine multiple flow data characteristics of the target data flow scenario in the metaverse.

[0051] In the metaverse, fluid data refers to information that is constantly generated, transmitted, and exchanged. This data can include users' virtual identities, virtual items, interaction records, and social network information, among other things. Fluid data plays a crucial role in the metaverse, supporting its various functions and experiences.

[0052] Flowing data forms the infrastructure of the virtual world. Users generate data through devices such as sensors, cameras, and microphones, inputting it into the metaverse, where it is then processed and stored using technologies like cloud computing. This data can be used to create and maintain the images, sounds, and physical simulations of the virtual world, enabling users to interact with other users and objects within the virtual environment.

[0053] Furthermore, streaming data is also used to establish and maintain users' virtual identities. When users enter the metaverse, they can create a unique virtual identity that can include personal information, physical characteristics, and skill background. This data can be continuously updated and improved as users move within the metaverse, thus forming a realistic and rich virtual representation.

[0054] Based on the above embodiments, determining multiple flow data characteristics of the target data flow scenario in the metaverse includes:

[0055] Receive a first input, the first input including a request for image data display initiated by the first target digital human;

[0056] In response to the first input, the target data flow scenario is determined to be an image display scenario and a plurality of corresponding flow data features in the image display scenario, wherein the plurality of flow data features include at least the body shape features, facial features, skin features and clothing features of the digital human.

[0057] In this invention, the data flow scenario in the metaverse is determined based on the initiator and receiver of the data interaction process. For example, when a digital human A in the metaverse encounters another digital human B, it needs to display the image of digital human B. At this time, the image data of digital human A flows. Digital human A is the receiver, and digital human B is the initiator, and needs to encrypt the relevant data of digital human A. Correspondingly, digital human B can also display the image to digital human A. For ease of description, this invention uses the example of a first target digital human (described in subsequent steps as digital human B) sending a data interaction request to a second target digital human (described in subsequent steps as digital human A) in the target data flow scenario. The target data flow scenario can be an image display scenario, that is, digital human B requests to obtain the image data of digital human A.

[0058] Specifically, the first step is to determine the flow data characteristics of digital human B in the data flow scenario. In this invention, the flow data characteristics are for the image display scenario, such as the digital human's body shape characteristics, facial features, skin characteristics, clothing characteristics, food characteristics, facial expression characteristics, and personality characteristics. All features related to the digital human's image are flow data characteristics.

[0059] Step 102: Based on the historical behavior data of the first target digital human, determine the preferred data features from multiple flow data features, wherein the first target digital human is the digital human that sends data interaction requests in the target data flow scenario.

[0060] In this invention, the corresponding historical behavior data is determined based on the changes in the flow data of digital human B within a historical period. That is, it is determined whether the data corresponding to each flow data feature of digital human B has changed within a certain period of time. If the amount of data has changed, it is determined that the flow data feature has historical behavior data. For example, if digital human B changes its clothing, there is a change in the amount of data between the clothing data of the previous period and the clothing data of the current period, which in turn generates historical behavior data corresponding to the clothing data feature.

[0061] Furthermore, the historical behavior data is classified according to the characteristics of the flow data to obtain the historical behavior data corresponding to each flow data characteristic. Then, based on the feature vectors between digital human B and other digital humans (such as digital humans other than digital human A and digital human B in the current image display scene) (which can be encoded according to the model parameters of each digital human), the similarity is calculated to determine the digital human similar to digital human B (denoted as digital human C). Then, based on the historical behavior data of digital human B and digital human C, the preference value of the flow data characteristic corresponding to each historical behavior data is calculated, and this preference value is compared with a preset threshold to determine whether the flow data characteristic is a preferred data characteristic based on the comparison result.

[0062] Step 103: Based on the preference data features, determine the first preference feature attribute value and the second preference feature attribute value, wherein the first preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the first target digital human, and the second preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the second target digital human, and the second target digital human is the digital human receiving the data interaction request in the target data flow scenario.

[0063] In this invention, after determining the preference data features through the above steps, the feature parameters of each preference data feature of digital human A and digital human B are compared with the corresponding standard parameters. For example, the nose bridge height corresponding to the preference data feature of digital human A (i.e., the nose bridge height feature parameter) is compared with the nose bridge height standard parameter (which can be obtained by averaging the feature parameters of all the same type of flow data features in the current image display scenario). Then, based on the comparison result (such as the ratio between the two), the preference feature attribute value is obtained, thereby obtaining the preference feature attribute value (i.e., the second preference feature attribute value) corresponding to each preference digital feature of digital human A and the preference feature attribute value (i.e., the first preference feature attribute value) corresponding to each preference digital feature of digital human B.

[0064] Step 104: Based on the first preference feature attribute value and the second preference feature attribute value, determine whether the preference data feature is a sensitive data feature. If so, encrypt the data corresponding to the sensitive data feature to obtain encrypted data.

[0065] In this invention, the preference feature attribute values ​​corresponding to each preference data feature of the same type for digital human A and digital human B are compared. That is, it is determined whether the second preference feature attribute value is greater than the first preference feature attribute value. If it is greater, the data corresponding to the current preference data feature is sensitive data and needs to be encrypted. If it is less, the data corresponding to the current preference data feature has low value to digital human B and is not a feature needed by digital human B.

[0066] The sensitive data processing method for the metaverse provided by this invention determines preference data features from multiple flow data features by using historical behavioral data of digital humans in the metaverse. Then, based on the preference data features, it determines whether the preference data features are sensitive data features according to the preference feature attribute values ​​between digital humans. If so, the data corresponding to the sensitive data features is encrypted, thereby more accurately determining the sensitive data in the metaverse and improving the data security in the metaverse.

[0067] Based on the above embodiments, determining preference data features from multiple flow characteristic data according to the historical behavioral data of the first target digital human includes:

[0068] Determine the historical behavior data corresponding to each of the aforementioned flow data features;

[0069] Based on the basic identity attributes of the first target digital person, multiple third target digital persons in the target data flow scenario are obtained, wherein the basic identity attributes of the multiple third target digital persons are the same as the basic identity attributes of the first target digital person;

[0070] Based on the similarity between the first target digital person and each of the third target digital persons, a fourth target digital person is determined from the plurality of third target digital persons;

[0071] Based on the historical behavior data corresponding to the first target digital person and the fourth target digital person respectively, obtain the flow feature preference value of each flow data feature of the first target digital person;

[0072] The flow data feature whose flow feature preference value satisfies the preset preference feature threshold is determined as the preference data feature.

[0073] In this invention, firstly, historical behavioral data related to the flow data characteristics of digital human B is acquired. For example, when digital human B changes its accessories, the resulting data is historical behavioral data related to the flow data characteristics. Then, the historical behavioral data is classified according to the flow data characteristics to obtain historical behavioral data corresponding to each flow data characteristic. For example, the historical behavior of digital human B changing its accessories is classified as accessory flow data characteristic.

[0074] Furthermore, in the current image display scenario, other digital humans similar to digital human B are identified, namely the fourth target digital human. For ease of description, the fourth target digital human is denoted as digital human C. If there are multiple digital humans C, they are specifically referred to as digital human C1, digital human C2, ..., CJ. The specific steps are as follows:

[0075] S1, Obtain the feature vectors of digital human B, forming the feature vector matrix F. B (Obtained by encoding based on the model parameters of each digital human);

[0076] S2. Based on the basic identity attributes (such as gender and age, which are determined when the digital human is generated), obtain other digital humans with the same basic identity attributes as digital human B, i.e., the third target digital human. For ease of description, the third target digital human is denoted as digital human D. If there are multiple digital humans D, they are referred to as digital human D1, digital human D2, etc. in the specific calculation.

[0077] S3, Obtain the feature vectors of digital human D, forming the feature vector matrix F. D For example, for digital human D1, the resulting feature vector matrix is ​​F. D1 For digital human D2, the resulting feature vector matrix is ​​F. D2 .

[0078] S4, calculate the similarity between digital human D and digital human B. Digital human D with a similarity greater than a preset similarity threshold is considered a similar digital human, i.e., digital human C. The similarity calculation formula is:

[0079]

[0080] S5. Obtain historical behavioral data related to the flow data characteristics of digital human C, classify the historical behavioral data according to the flow data characteristics, and obtain the historical behavioral data corresponding to each flow data characteristic. For example, if the historical behavioral data of digital human C is clothing data characteristics, then classify it as the historical behavioral data corresponding to clothing data characteristics.

[0081] S6, based on the historical behavior data of digital human B and digital human C, calculate the preference value of each flow feature. Building upon the above embodiment, the step of obtaining the flow feature preference value of each flow data feature of the first target digital human based on the historical behavior data corresponding to both the first target digital human and the fourth target digital human includes:

[0082] Based on the historical behavioral data corresponding to the same type of flow data features of the first target digital person and the fourth target digital person, the flow feature preference value of the flow data feature corresponding to the first target digital person is calculated using the preference value calculation formula, which is:

[0083]

[0084] Among them, nr Bi nr represents the total amount of historical behavioral data corresponding to the i-th flow data feature of the first target digital person. B Let j represent the total historical behavioral data of all the aforementioned flow data features of the first target digital human, and nr represent the j-th fourth target digital human. Cji nr represents the total amount of historical behavioral data corresponding to the i-th flow data feature of the j-th fourth target digital person. Cj J represents the total amount of historical behavioral data of all the flow data features of the j-th fourth target digital human, and J represents the total number of the fourth target digital human.

[0085] S7, determine the standard deviation and mean of each flow characteristic preference value, and then obtain the preset preference characteristic threshold based on the mean × (1 + standard deviation).

[0086] S8, compare each flow feature preference value with a preset preference feature threshold, and take the flow data feature corresponding to the flow feature preference value that is greater than the preset preference feature threshold as the preference data feature.

[0087] This invention can quickly determine the preference data characteristics in the metaverse image display scene through similarity calculation and preference value calculation, providing more accurate data support for the subsequent sensitive data judgment process.

[0088] Based on the above embodiments, determining the first preference feature attribute value and the second preference feature attribute value based on the preference data features includes:

[0089] Obtain the feature parameters corresponding to each of the aforementioned preference data features;

[0090] Based on the ratio between the feature parameters and the corresponding standard parameters, the preference feature attribute values ​​of each preference data feature are obtained;

[0091] The step of determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value includes:

[0092] If the value of the first preference feature attribute is less than the value of the second preference feature attribute, then the preference data feature corresponding to the value of the first preference feature attribute is determined to be the sensitive data feature.

[0093] In this invention, it is necessary to determine the value of each preference data feature for the target data flow scenario based on the feature parameters corresponding to each preference data feature. This value characterizes the coordination degree of the current preference data feature with the entire target data flow scenario; the greater the coordination degree, the greater the value. Taking the preference data feature as the eyes as an example, the image of digital human A is first determined, for example, whether it is a cartoon version or a lifelike version. If it is a cartoon version, the current eye length L of digital human A is determined (i.e., eye length is the preference data feature, and L is its corresponding feature parameter). The distance D between the inner corners of the two eyes in the frontal face of digital human A is determined (i.e., the standard parameter corresponding to the eye length). The value of D / L is calculated. If the value is 1, the value is determined to be 1. If it is not 1, the decimal part is used as the value, thereby obtaining the preference feature attribute value of the preference data feature. For other preference data features, the same approach is used to determine the ratio between the current feature parameter and the standard parameter. If the ratio is the same as the standard feature, the value is set to 1. If the ratio is different, the decimal is used as the value. For example, if the bridge of the nose is used as a preference data feature, the ratio between the standard parameter of the bridge of the nose of digital human A and the feature parameter of the current bridge of the nose is used as the preference feature attribute value.

[0094] Accordingly, through the above steps, the preference feature attribute values ​​corresponding to each preference feature data of digital human B are obtained. Further, based on the same preference data feature, the difference between the preference feature attribute values ​​of digital human A and digital human B is calculated. This difference is used as the sensitivity value of the attribute value. Preference data features with a sensitivity value greater than 0 are then identified as sensitive features. The sensitivity value indicates whether the preference feature attribute value of digital human A is superior to that of digital human B. For example, for a certain preference data feature, although digital human B values ​​this feature more, it does not mean that digital human B's preference feature attribute value in this feature is lower than that of digital human A. If the value of digital human B's preference data feature is higher, digital human B has no need to acquire that feature value from digital human A and can maintain its current data. Only when the value of digital human A is higher will digital human B want to acquire that feature. Therefore, when the sensitivity value is greater than 0, it indicates that digital human B has a need to acquire the feature value from digital human A. The data corresponding to this preference data feature can then be determined as sensitive data, thus accurately identifying the sensitive data in the preference data features.

[0095] Based on the above embodiments, after determining whether the preference data feature is a sensitive data feature according to the first preference feature attribute value and the second preference feature attribute value, and if so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data, the method further includes:

[0096] Determine whether the first target digital human has the feature acquisition permission corresponding to the encrypted data. If it does, send the decoding method of the encrypted data to the first target digital human.

[0097] If not, display the virtual image of the second target digital human to the first target digital human.

[0098] In this invention, data identified as sensitive features in digital human A is encrypted to form encrypted data. At this point, digital human B can see the image of digital human A; however, if digital human B needs to obtain the image data of digital human A, it will not directly obtain the data of the sensitive feature. Furthermore, if digital human B wants to possess the sensitive features of digital human A, it can send a request to digital human A. After digital human A agrees (e.g., digital human B obtains query permissions for the sensitive feature), the original value of the sensitive feature (i.e., the data corresponding to the sensitive feature) is sent to digital human B. Alternatively, the system can send the decryption method to digital human B, who can then decrypt the data to obtain the data of the sensitive feature. In other words, for the data of sensitive features, the corresponding data will only be obtained after the requesting party obtains the appropriate permissions.

[0099] The following describes the sensitive data processing system for the metaverse provided by the present invention. The sensitive data processing system for the metaverse described below and the sensitive data processing method for the metaverse described above can be referred to in correspondence.

[0100] Figure 2 A schematic diagram of the structure of the sensitive data processing system for the metaverse provided by this invention is shown below. Figure 2As shown, this invention provides a sensitive data processing system for a metaverse, including a flow scene determination module 201, a preference data feature determination module 202, a preference feature attribute value calculation module 203, and a sensitive data feature processing module 204. The flow scene determination module 201 is used to determine multiple flow data features of a target data flow scene in the metaverse; the preference data feature determination module 202 is used to determine preference data features from the multiple flow data features based on the historical behavior data of a first target digital person, wherein the first target digital person is a digital person sending a data interaction request in the target data flow scene; the preference feature attribute value calculation module 203 is used to calculate preference data features based on the preference data... Based on the features, a first preference feature attribute value and a second preference feature attribute value are determined, wherein the first preference feature attribute value is the preference feature attribute value corresponding to the preference data feature of the first target digital person, and the second preference feature attribute value is the preference feature attribute value corresponding to the preference data feature of the second target digital person, the second target digital person being the digital person receiving the data interaction request in the target data flow scenario; the sensitive data feature processing module 204 is used to determine whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value, and if so, to encrypt the data corresponding to the sensitive data feature to obtain encrypted data.

[0101] The sensitive data processing system for the metaverse provided by this invention determines preference data features from multiple flow data features by using historical behavioral data of digital humans in the metaverse. Then, based on the preference data features, it determines whether the preference data features are sensitive data features according to the preference feature attribute values ​​between digital humans. If so, the data corresponding to the sensitive data features is encrypted, thereby more accurately determining the sensitive data in the metaverse and improving the data security in the metaverse.

[0102] The system provided by this invention is used to execute the above-described method embodiments. For specific processes and details, please refer to the above embodiments, which will not be repeated here.

[0103] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 3As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303, and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304. Processor 301 can invoke logical instructions in memory 303 to execute a sensitive data processing method for the metaverse. This method includes: determining multiple flow data features of a target data flow scenario in the metaverse; determining a preference data feature from the multiple flow data features based on the historical behavioral data of a first target digital human, wherein the first target digital human is a digital human sending a data interaction request in the target data flow scenario; determining a first preference feature attribute value and a second preference feature attribute value based on the preference data feature, wherein the first preference feature attribute value is a preference feature attribute value corresponding to the preference data feature of the first target digital human, and the second preference feature attribute value is a preference feature attribute value corresponding to the preference data feature of a second target digital human, wherein the second target digital human is a digital human receiving the data interaction request in the target data flow scenario; and determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value. If so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data.

[0104] Furthermore, the logical instructions in the aforementioned memory 303 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the sensitive data processing method for the metaverse provided by the above methods, the method comprising: determining multiple flow data features of a target data flow scenario in the metaverse; determining a preference data feature from the multiple flow data features based on the historical behavioral data of a first target digital human, wherein the first target digital human is a digital human who sends a data interaction request in the target data flow scenario; determining a first preference feature attribute value and a second preference feature attribute value based on the preference data feature, wherein the first preference feature attribute value is a preference feature attribute value corresponding to the preference data feature of the first target digital human, and the second preference feature attribute value is a preference feature attribute value corresponding to the preference data feature of a second target digital human, wherein the second target digital human is a digital human who receives the data interaction request in the target data flow scenario; determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value, and if so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data.

[0106] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, is implemented to perform the sensitive data processing method for the metaverse provided in the above embodiments. The method includes: determining multiple flow data features of a target data flow scenario in the metaverse; determining a preference data feature from the multiple flow data features based on the historical behavioral data of a first target digital person, wherein the first target digital person is a digital person sending a data interaction request in the target data flow scenario; determining a first preference feature attribute value and a second preference feature attribute value based on the preference data feature, wherein the first preference feature attribute value is a preference feature attribute value corresponding to the preference data feature of the first target digital person, and the second preference feature attribute value is a preference feature attribute value corresponding to the preference data feature of a second target digital person, wherein the second target digital person is a digital person receiving the data interaction request in the target data flow scenario; and determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value, and if so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data.

[0107] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0109] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing sensitive data in the metaverse, characterized in that, include: Identify multiple flow data characteristics of the target data flow scenario in the metaverse; Based on the historical behavioral data of the first target digital human, preference data features are determined from multiple flow data features, wherein the first target digital human is a digital human that sends data interaction requests in the target data flow scenario; Based on the preference data features, a first preference feature attribute value and a second preference feature attribute value are determined, wherein the first preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the first target digital human, and the second preference feature attribute value is the preference data feature value corresponding to the preference data features of the second target digital human, and the second target digital human is the digital human receiving the data interaction request in the target data flow scenario; Based on the first preference feature attribute value and the second preference feature attribute value, determine whether the preference data feature is a sensitive data feature. If so, encrypt the data corresponding to the sensitive data feature to obtain encrypted data. The step of determining the first preference feature attribute value and the second preference feature attribute value based on the preference data features includes: Obtain the feature parameters corresponding to each of the aforementioned preference data features; Based on the ratio between the feature parameters and the corresponding standard parameters, the preference feature attribute values ​​of each preference data feature are obtained; The step of determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value includes: If the value of the first preference feature attribute is less than the value of the second preference feature attribute, then the preference data feature corresponding to the value of the first preference feature attribute is determined to be the sensitive data feature.

2. The sensitive data processing method for the metaverse according to claim 1, characterized in that, The step of determining preference data features from multiple flow data features based on the historical behavioral data of the first target digital human includes: Determine the historical behavior data corresponding to each of the aforementioned flow data features; Based on the basic identity attributes of the first target digital person, multiple third target digital persons in the target data flow scenario are obtained, wherein the basic identity attributes of the multiple third target digital persons are the same as the basic identity attributes of the first target digital person; Based on the similarity between the first target digital person and each of the third target digital persons, a fourth target digital person is determined from the plurality of third target digital persons; Based on the historical behavior data corresponding to the first target digital person and the fourth target digital person respectively, obtain the flow feature preference value of each flow data feature of the first target digital person; The flow data feature whose flow feature preference value satisfies the preset preference feature threshold is determined as the preference data feature.

3. The sensitive data processing method for the metaverse according to claim 2, characterized in that, The step of obtaining the flow characteristic preference values ​​of each of the flow data features of the first target digital person based on the historical behavior data corresponding to the first target digital person and the fourth target digital person includes: Based on the historical behavioral data corresponding to the same type of flow data features of the first target digital person and the fourth target digital person, the flow feature preference value of the flow data feature corresponding to the first target digital person is calculated using the preference value calculation formula, which is: Among them, nr Bi nr represents the total amount of historical behavioral data corresponding to the i-th flow data feature of the first target digital person. B Let j represent the total historical behavioral data of all the aforementioned flow data features of the first target digital human, and nr represent the j-th fourth target digital human. Cji nr represents the total amount of historical behavioral data corresponding to the i-th flow data feature of the j-th fourth target digital person. Cj J represents the total amount of historical behavioral data of all the flow data features of the j-th fourth target digital human, and J represents the total number of the fourth target digital human.

4. The sensitive data processing method for the metaverse according to claim 1, characterized in that, The determination of multiple flow data characteristics of the target data flow scenario in the metaverse includes: Receive a first input, the first input including a request for image data display initiated by the first target digital human; In response to the first input, the target data flow scenario is determined to be an image display scenario and a plurality of corresponding flow data features in the image display scenario, wherein the plurality of flow data features include at least the body shape features, facial features, skin features and clothing features of the digital human.

5. The sensitive data processing method for the metaverse according to any one of claims 1 to 4, characterized in that, After determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value, and if so, encrypting the data corresponding to the sensitive data feature to obtain encrypted data, the method further includes: Determine whether the first target digital human has the feature acquisition permission corresponding to the encrypted data. If it does, send the decoding method of the encrypted data to the first target digital human. If not, display the virtual image of the second target digital human to the first target digital human.

6. A sensitive data processing system for the metaverse, characterized in that, include: The flow scene determination module is used to determine multiple flow data features of the target data flow scene in the metaverse; The preference data feature determination module is used to determine preference data features from multiple flow data features based on the historical behavior data of the first target digital human, wherein the first target digital human is a digital human that sends data interaction requests in the target data flow scenario; The preference feature attribute value calculation module is used to determine a first preference feature attribute value and a second preference feature attribute value based on the preference data features, wherein the first preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the first target digital person, and the second preference feature attribute value is the preference feature attribute value corresponding to the preference data features of the second target digital person, and the second target digital person is the digital person receiving the data interaction request in the target data flow scenario; The sensitive data feature processing module is used to determine whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value. If so, the data corresponding to the sensitive data feature is encrypted to obtain encrypted data. The preference feature attribute value calculation module is specifically used for: Obtain the feature parameters corresponding to each of the aforementioned preference data features; Based on the ratio between the feature parameters and the corresponding standard parameters, the preference feature attribute values ​​of each preference data feature are obtained; The step of determining whether the preference data feature is a sensitive data feature based on the first preference feature attribute value and the second preference feature attribute value includes: If the value of the first preference feature attribute is less than the value of the second preference feature attribute, then the preference data feature corresponding to the value of the first preference feature attribute is determined to be the sensitive data feature.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the sensitive data processing method for the metaverse as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the sensitive data processing method for the metaverse as described in any one of claims 1 to 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the sensitive data processing method for the metaverse as described in any one of claims 1 to 5.

Images