CN117786739A - Data processing methods, servers and systems - Google Patents

Abstract

The application discloses a data processing method, a server and a system, and relates to the technical field of privacy enhancement. The method comprises the following steps: responding to data to be processed sent by a data owner, dividing the data to be processed into a plurality of privacy data blocks, wherein the enhancement degrees corresponding to the privacy data blocks are different; processing at least one privacy data block according to the enhancement degree corresponding to the privacy data block by adopting a preset enhancement mode corresponding to the enhancement degree to obtain the privacy enhancement data block; and sending data to be transmitted to a data user, wherein the data to be transmitted comprises privacy enhanced data blocks. The method is convenient for distinguishing various privacy data blocks in the data to be processed, and correspondingly carries out privacy enhancement of different degrees, so that the data with high enhancement degree can be better protected, and the security of the privacy data is improved.

Description

Data processing methods, servers and systems

Technical Field

This application relates to the field of privacy enhancement technology, specifically to a data processing method, server and system.

Background technique

As society becomes more and more digital, data is collected and applied on a large scale so that the value of the data can be discovered and become a valuable asset. However, during the application process of data, there is the problem of leakage of private information, which reduces the security of data application. How to identify private data and improve the protection of private data is an urgent problem to be solved.

Contents of the invention

This application provides a data processing method, server and system that can improve the identification accuracy of private data and improve the protection of private data.

In a first aspect, the present application provides a data processing method, comprising: in response to data to be processed sent by a data owner, dividing the data to be processed into multiple privacy data blocks, each privacy data block corresponding to a different degree of enhancement; based on the degree of enhancement corresponding to the privacy data block, processing at least one privacy data block using a preset enhancement method corresponding to the degree of enhancement to obtain a privacy-enhanced data block; and sending data to be transmitted to a data user, the data to be transmitted including the privacy-enhanced data block.

In a second aspect, this application provides a data processing method. The method includes: receiving data to be transmitted sent by the server, where the data to be transmitted includes a privacy-enhanced data block, and the privacy-enhanced data block is the degree of enhancement corresponding to the privacy data block by the server, A data block obtained by processing at least one private data block using a preset enhancement method corresponding to the degree of enhancement. The private data block is any one of multiple data blocks provided by the data owner; perform statistical analysis on the data to be transmitted, and determine Data processing results.

In the third aspect, this application provides a privacy enhancement server, including: a dividing module configured to respond to the data to be processed sent by the data owner, and divide the data to be processed into multiple privacy data blocks, and each privacy data block corresponds to The degree of enhancement is different; the processing module is configured to process at least one privacy data block using a preset enhancement method corresponding to the degree of enhancement according to the degree of enhancement corresponding to the privacy data block, and obtain a privacy-enhanced data block; the sending module is configured to Send data to be transmitted to the data user, where the data to be transmitted includes privacy-enhancing data blocks.

In the fourth aspect, this application provides a data processing system, including: a communication-connected privacy enhancement server, a data owner device, and a data user device; the privacy enhancement server is configured to perform any one of the applications in the embodiments of this application. The data processing method of the privacy enhancement server; the data user device is configured to perform any of the data processing methods applied to the data user device in the embodiments of this application; the data owner device is configured to send to the privacy enhancement server. Process the data so that the privacy-enhancing server processes the data to be processed and generates data to be transmitted.

According to the data processing method, server and system provided by the embodiments of this application, by responding to the data to be processed sent by the data owner, the data to be processed is divided into multiple private data blocks, and the corresponding enhancement degrees of each private data block are different, so that It is used to distinguish different private data blocks in the data to be processed, and perform different degrees of privacy enhancement accordingly, so that data with a high degree of enhancement can obtain better protection; according to the degree of enhancement corresponding to the privacy data block, the method corresponding to the degree of enhancement is used Process at least one privacy data block in a preset enhancement method to obtain a privacy enhancement data block, so that the privacy enhancement data block obtained after processing can be processed with higher protection to ensure the security of private data; send to the data user The data to be transmitted includes privacy-enhancing data blocks, so that data users can obtain the data they need while also avoiding the leakage of data with a high degree of privacy.

Description of the drawings

The drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. They are used to explain the present application together with the embodiments of the present application and do not constitute a limitation of the present application. The above and other features and advantages will become more apparent to those skilled in the art by describing detailed example embodiments with reference to the accompanying drawings, in which:

FIG1 is a schematic flow chart of a data processing method provided in an embodiment of the present application.

Figure 2 shows a schematic flowchart of a data processing method provided by an embodiment of the present application.

Figure 3 shows a block diagram of a privacy enhancement server provided by an embodiment of the present application.

Figure 4 shows a block diagram of a data processing system provided by an embodiment of the present application.

FIG5 is a schematic flow chart showing a working method of a data processing system provided in an embodiment of the present application.

FIG. 6 shows a block diagram of an electronic device provided by an embodiment of the present application.

Detailed ways

The specific embodiments of the present application are described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present application and are not intended to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of the specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

It should be noted that, as used herein, the terms "include", "comprises" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device that includes a series of elements not only includes those elements, It also includes other elements not expressly listed or inherent in the process, method, article or equipment. Without further limitation, an element defined by the statement "including..." does not exclude the presence of additional identical elements in the process, method, article, or device that includes the element.

In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

In related technical solutions, all user data will be encrypted, and interference factors such as noise will be added during the encryption process so that the processed data will not leak the user's private data. However, in the above process, "on-demand privacy" cannot be achieved, that is, corresponding protection measures cannot be taken for different privacy data according to the importance of user privacy, which increases the system's data processing overhead and reduces data processing efficiency.

Figure 1 shows a schematic flowchart of a data processing method provided by an embodiment of the present application. This data processing method can be applied to privacy-enhancing servers. As shown in Figure 1, the data processing method includes but is not limited to the following steps.

Step S101: In response to the data to be processed sent by the data owner, the data to be processed is divided into multiple private data blocks.

Among them, each private data block corresponds to different degrees of enhancement. For example, the data to be processed includes: electricity consumption data of electricity users, such as user addresses, identity information and other user personal information.

It should be noted that in the technical solution involved in this application, the acquisition of user personal information follows relevant national laws and regulations (for example, "Information Security Technology Personal Information Security Specifications", etc.). Moreover, the information is obtained by clearly informing the user and through legal channels; the type of information obtained is directly related to the business functions of the product or service, and the information obtained is collected with the minimum frequency and quantity; the collection of personal information does not violate the autonomy of the personal information subject. Willingness; obtain authorized consent when collecting personal information; when obtaining personal information indirectly, either from a public data set on the Internet, or in other ways, and comply with the regulatory requirements for obtaining indirect personal information.

Step S102: According to the degree of enhancement corresponding to the privacy data block, process at least one privacy data block using a preset enhancement method corresponding to the degree of enhancement to obtain a privacy-enhanced data block.

Step S103: Send the data to be transmitted to the data user.

The data to be transmitted includes privacy-enhanced data blocks.

In this embodiment, in response to the data to be processed sent by the data owner, the data to be processed is divided into multiple privacy data blocks, and the enhancement levels corresponding to the various privacy data blocks are different, so as to distinguish the various privacy data blocks in the data to be processed, and perform privacy enhancement to different degrees accordingly, so that the data with a high degree of enhancement can be better protected; according to the enhancement level corresponding to the privacy data block, at least one privacy data block is processed in a preset enhancement method corresponding to the enhancement level to obtain a privacy enhanced data block, so that the privacy enhanced data block obtained after the processing can be processed with a higher degree of protection, thereby ensuring the security of the privacy data; the data to be transmitted is sent to the data user, and the data to be transmitted includes the privacy enhanced data block, so that the data user can obtain the data it needs while avoiding the leakage of data with a high degree of privacy.

The embodiment of the present application provides another possible implementation method. In step S101, in response to the data to be processed sent by the data owner, the data to be processed is divided into multiple private data blocks. This can be implemented in the following manner: receiving the data owner The data to be processed is sent by the third party; the data to be processed is divided into a preset number of private data blocks.

Among them, the privacy data block includes data number, enhancement degree and original privacy data. The data number is a number determined based on a preset number.

It should be noted that each private data block corresponds to a unique data number, and this data number can represent the position of the original private data in the private data block in the data to be processed.

The degree of enhancement may include two enhancement degrees of "strong" and "weak", or may include three enhancement degrees of "strong", "medium" and "weak", etc. The above enhancement degree is only an example, and can be specifically set according to actual needs. Other unspecified enhancement degrees are also within the protection scope of this application and will not be described again here.

By dividing the data to be processed to obtain a preset number of private data blocks, it is easy to process different private data blocks differently, and selectively encrypt certain private data blocks based on usage requirements or processing needs. Processing can achieve "on-demand privacy" and improve data processing efficiency.

In some exemplary embodiments, the enhancement degree corresponding to the private data block includes a first enhancement degree, and the preset enhancement method includes a homomorphic encryption method.

In step S102, according to the enhancement degree corresponding to the privacy data block, at least one privacy data block is processed using a preset enhancement method corresponding to the enhancement degree to obtain the privacy enhancement data block, which can be implemented in the following manner: after determining the privacy data block correspondence When the enhancement degree is the first enhancement degree, homomorphic encryption is used to encrypt the original privacy data in the privacy data block to obtain the encrypted data; based on the encrypted data, the homomorphic encryption method and its corresponding encryption Parameters to generate privacy-enhancing data blocks.

Among them, the first enhancement degree is the highest intensity among the multiple enhancement degrees. The homomorphic encryption method may include at least one of an additive homomorphic method, a multiplicative homomorphic method, a mixed multiplicative homomorphic method, a subtractive homomorphic method, a division homomorphic method, an algebraic homomorphic method, and an arithmetic homomorphic method. Among them, the algebraic homomorphism method requires the simultaneous use of additive homomorphism and multiplication homomorphism to process the original private data in the private data block; the arithmetic homomorphism method requires the simultaneous use of additive homomorphism, subtraction homomorphism, multiplication homomorphism and Division homomorphism operates on the original private data in the private data block. Different homomorphic encryption methods correspond to different encryption parameters.

By homomorphically encrypting the privacy data block corresponding to the first enhancement degree with the highest level among multiple enhancement degrees, the original privacy data in the privacy data block can be most effectively protected, ensuring that the original privacy data will not be Give way.

In some exemplary embodiments, the degree of enhancement corresponding to the private data block also includes a second degree of enhancement and/or a third degree of enhancement. The second degree of enhancement is weaker than the first degree of enhancement, and the third degree of enhancement is weaker than the second degree of enhancement. The degree of enhancement, the preset enhancement method also includes federated learning models and/or differential privacy algorithms.

In step S102, according to the enhancement degree corresponding to the privacy data block, at least one privacy data block is processed using a preset enhancement method corresponding to the enhancement degree to obtain the privacy enhancement data block, which can be implemented in the following manner: after determining the privacy data block correspondence When the enhancement degree is the second enhancement degree, the federated learning model is used to process the original privacy data in the privacy data block to obtain the processed data; and based on the processed data and the parameter information corresponding to the federated learning model, a generated Privacy enhanced data block; when it is determined that the corresponding enhancement degree of the privacy data block is the third enhancement degree, a differential privacy algorithm is used to process the original privacy data in the privacy data block to obtain the processed data, and based on the processed The data and parameter information corresponding to the differential privacy algorithm are used to generate a privacy-enhanced data block.

Among them, according to different enhancement levels, different levels of processing methods are used to process the original privacy data in the privacy data block to distinguish different levels of privacy protection.

In the case of the second enhancement degree, which is in the middle, the original private data in the privacy data block is processed by using a federated learning model; while in the case of the third enhancement degree, which is the weakest, a differential privacy algorithm is used , process the original privacy data in the privacy data block; it can make different levels of original privacy data obtain different data, while ensuring the security of the data, it can reduce the complexity of data processing, reduce the amount of data processing, and improve Data processing efficiency.

In some exemplary embodiments, the number of privacy-enhancing data blocks is the same as the number of privacy data blocks, or the number of privacy-enhancing data blocks is less than the number of privacy data blocks.

Among them, when the number of privacy-enhancing data blocks is the same as the number of privacy data blocks, it means that all data in the data to be processed needs to be encrypted to ensure the security of the data to be transmitted.

When the number of privacy-enhancing data blocks is less than the number of privacy data blocks, only part of the data in the data to be processed can be encrypted, and other data cannot be encrypted, thereby reducing the amount of data processing and speeding up the data processing efficiency; and, Targeted encryption of part of the data to be processed can not only meet the data owner's need to keep its private data confidential, but also prevent the data user's device from knowing the private data that the data owner wants to protect, and at the same time Quickly and accurately obtain other data other than the privacy-enhancing data blocks in the data to be processed that the data user device wishes to obtain, thereby improving the data processing efficiency of the data user device.

In some exemplary embodiments, before sending the data to be transmitted to the data user in step S103, the method includes: encrypting the privacy-enhancing data block using a preset public key to generate the data to be transmitted.

Among them, the preset public key is the public key determined through negotiation between the data owner and the data user.

By using the preset public key to encrypt the privacy-enhanced data block, the security of the data to be transmitted can be ensured during the transmission process. Moreover, the preset public key is the public key negotiated between the data owner and the data user. Only the data Only the owner and data user can encrypt or decrypt the data to be transmitted. The third-party device cannot obtain the preset public key. Therefore, even if the third-party device intercepts the data to be transmitted, it cannot obtain the essence of the data to be transmitted. Sexual information reduces the possibility of data being transmitted being leaked.

Figure 2 shows a schematic flowchart of a data processing method provided by an embodiment of the present application. This data processing method can be applied to data user devices (for example, terminal devices such as mobile phones and personal computers). As shown in Figure 2, the data processing method includes but is not limited to the following steps.

Step S201, receiving data to be transmitted sent by a server.

Among them, the data to be transmitted includes privacy-enhanced data blocks. The privacy-enhanced data blocks are data blocks obtained by the server using a preset enhancement method corresponding to the degree of enhancement to process at least one privacy data block based on the degree of enhancement corresponding to the privacy data block. Privacy A data block is any one of multiple data blocks provided by the data owner.

Step S202: Perform statistical analysis on the data to be transmitted to determine the data processing results.

In some exemplary embodiments, before performing statistical analysis on the data to be transmitted and determining the data processing results in step S202, the method further includes: using the private key of the current device to decrypt the data to be transmitted to obtain the privacy-enhancing data block. , and other privacy data blocks except privacy-enhancing data blocks.

Among them, the current device's private key matches the preset public key used by the server.

By using the private key of the data user's device to decrypt the data to be transmitted, other privacy data blocks other than the privacy enhancement data block required by the data user's device can be obtained, which facilitates the data user's device to perform data analysis based on other privacy data blocks other than the privacy enhancement data block and obtain the data processing results it needs. For example, the data processing results include information such as data statistical trends.

Moreover, since the data user device does not have the decryption method to learn the privacy-enhanced data block, the data user device can no longer decrypt the privacy-enhanced data block, thereby ensuring the security of the original privacy data in the privacy-enhanced data block. .

Figure 3 shows a block diagram of a privacy enhancement server provided by an embodiment of the present application. As shown in Figure 3, the privacy enhancement server 300 includes but is not limited to the following modules.

The dividing module 301 is configured to respond to the data to be processed sent by the data owner, and divide the data to be processed into multiple private data blocks, and each private data block corresponds to a different degree of enhancement.

The processing module 302 is configured to process at least one private data block according to the enhancement degree corresponding to the private data block by using a preset enhancement method corresponding to the enhancement degree to obtain a privacy-enhanced data block.

The sending module 303 is configured to send data to be transmitted to the data user, where the data to be transmitted includes privacy-enhancing data blocks.

It should be noted that the privacy enhancement server 300 in the embodiment of the present application can perform any data processing method applied to the privacy enhancement server in the present application, which will not be described again here.

In this embodiment, the partitioning module responds to the data to be processed sent by the data owner and divides the data to be processed into multiple privacy data blocks. The enhancement levels corresponding to the various privacy data blocks are different, so as to distinguish the different privacy data blocks in the data to be processed and perform privacy enhancement to different degrees accordingly, so that the data with a high degree of enhancement can be better protected; the processing module is used to process at least one privacy data block according to the enhancement level corresponding to the privacy data block, using a preset enhancement method corresponding to the enhancement level to obtain a privacy-enhanced data block, so that the privacy-enhanced data block obtained after processing can be processed with a higher degree of protection, thereby ensuring the security of the privacy data; the sending module is used to send the data to be transmitted to the data user, and the data to be transmitted includes the privacy-enhanced data block, so that the data user can obtain the data it needs while avoiding the leakage of data with a high degree of privacy.

It is worth mentioning that each module involved in this implementation is a logical module. In practical applications, a logical unit can be a physical unit, or a part of a physical unit, or it can be multiple physical units. The combination of units is realized. In addition, in order to highlight the innovative part of this application, units that are not closely related to solving the technical problems raised in this application are not introduced in this embodiment, but this does not mean that other units do not exist in this embodiment.

Figure 4 shows a block diagram of a data processing system provided by an embodiment of the present application. As shown in Figure 4, the data processing system includes but is not limited to the following devices: a communication-connected privacy enhancement server 401, a data owner device 402, and a data user device 403.

Among them, the privacy enhancement server 401 is configured to execute any of the data processing methods applied to the privacy enhancement server in the embodiments of this application.

The data user device 403 is configured to execute any of the data processing methods applied to the data user device in the embodiments of this application.

The data owner device 402 is configured to send the data to be processed to the privacy enhancement server, so that the privacy enhancement server processes the data to be processed and generates data to be transmitted.

FIG. 5 shows a schematic flowchart of a working method of a data processing system provided by an embodiment of the present application. As shown in Figure 5, the working method of the data processing system includes but is not limited to the following steps:

Step S501: The data owner device 402 establishes a communication connection with the privacy enhancement server 401 through message interaction.

Among them, the data owner device 402 can register and log in to the privacy enhancement server 401 through its internally installed application.

The data owner device 402 may also send a login request to the privacy enhancement server 401, and in response to the login response fed back by the privacy enhancement server 401, determine that the data owner device 402 establishes a communication connection with the privacy enhancement server 401.

Step S502: The data owner device 402 sends the data to be processed to the privacy enhancement server 401.

The data to be processed is data that the data owner device 402 wishes to share with the data user device 403 for use by the data user device 403. However, the data to be processed includes privacy data. In order to protect the security of private data, the privacy enhancement server 401 needs to perform corresponding processing on the data to be processed to avoid the leakage of private data.

The data to be processed may include at least one of the following data: meter number, time of acquisition of the data to be processed, meter number, payment time, address information, mobile phone number, household owner identity information corresponding to the meter, household owner's bank card information, payment amount, temperature, sunshine duration, electricity usage type (such as at least one of industrial electricity, agricultural electricity, commercial electricity and residential electricity).

Step S503: the privacy enhancing server 401 divides the data to be processed into a preset number of privacy data blocks.

Among them, the privacy data block includes data number, enhancement degree and original privacy data. The data number is a number determined based on a preset number.

For example, the above division process can be implemented using formula (1):

DF1＝F1(Dnum, Level) (1)

Among them, DF1 represents the divided private data block, F1 represents the function of the dividing method, and Dnum represents the preset number, that is, the data owner device 402 needs to divide the data to be processed into Dnum private data blocks. The default quantity is an integer greater than or equal to 1.

In some embodiments, when dividing the data to be processed, the data to be processed can be divided vertically, the data to be processed can be divided horizontally, or the data to be processed can be divided according to the specific business according to the preset segmentation rules. , this application does not limit this, and will not be repeated here.

It should be noted that the F1 function is a functional component. In different systems or based on different business demand scenarios, the specific algorithm of this functional component is also different.

Level represents the degree of enhancement, for example, the first enhancement degree, the second enhancement degree, the third enhancement degree, etc. which are successively lower in degree. For another example, Level may include two enhancement levels of "strong" and "weak", or may include three enhancement levels of "strong", "medium" and "weak", etc. The above enhancement degree is only an example, and can be specifically set according to actual needs. Other unspecified enhancement degrees are also within the protection scope of this application and will not be described again here.

It should be noted that the divided private data block DF1 can be an ordered sequence. For example, DF1 includes D1, D2, D3,..., Dn, etc., through this ordered sequence, each private data block can be expressed sequentially. The location of the processed data is used to facilitate the subsequent combined restoration of the data to be processed.

Wherein, n represents a preset number, and n is an integer greater than or equal to 1. Each private data block corresponds to a unique data number, and the data number can represent the position of the original private data in the private data block in the data to be processed.

For example, if n is set to 8 and the data to be processed is divided vertically, the following 8 private data blocks can be obtained: D1 (meter number, sunshine duration); D2 (power consumption type); …………; D7 (meter number) ); D8 (household head identity information corresponding to address information, mobile phone number, and electricity meter).

Step S504: The privacy enhancement server 401 processes at least one privacy data block using a preset enhancement method corresponding to the degree of enhancement to obtain a privacy enhancement data block.

The data user device 403 applies to the data owner device 402 to use the data to be processed stored by the data owner device 402, and performs statistical analysis on the data to be processed. The data owner device 402 encrypts the enhanced privacy data D1, D2, D3, ..., D8 through the public key of the data user device 403 to form an encrypted data packet DF3, and sends the encrypted data packet DF3 through the network to Data consumer device 403.

The preset enhancement method includes: at least one of a hash algorithm, a homomorphic encryption method, a federated learning model, and a differential privacy algorithm.

For example, when it is determined that the corresponding enhancement degree of the private data block is the first enhancement degree, homomorphic encryption is used to encrypt the original private data in the private data block to obtain encrypted data, where the first enhancement degree is The strongest degree among multiple enhancement levels; generate a privacy-enhanced data block based on the encrypted data, the homomorphic encryption method and its corresponding encryption parameters.

For example, for statistical analysis of D1 with a Level of "strong", a homomorphic encryption algorithm (such as the Paillier algorithm) can be used to process D1; wherein, the parameters in the homomorphic encryption algorithm can be set as follows:

The two large prime numbers randomly selected are: p = 11, q = 13;

Random integer g=2 in the public key;

λ=lcm(p-1,q-1)=60, μ=25, and random number r=3 in the private key.

It should be noted that the homomorphic encryption method is to perform ring addition and multiplication operations on the plaintext before encrypting it. The result is equivalent to performing corresponding operations on the ciphertext after encryption. Due to this good property, the original private data in the private data block can be homomorphically encrypted without leaking the information in the original private data.

Moreover, only the data owner (eg, data owner device 402) can decrypt and view the encrypted data to ensure the security of the original private data in the private data block.

For another example, when it is determined that the enhancement degree corresponding to the private data block is the second enhancement degree, the federated learning model is used to process the original private data in the private data block to obtain the processed data; and based on the processed data, Parameter information corresponding to the federated learning model generates privacy-enhanced data blocks.

Federated machine learning (Federated Learning), also known as federated learning, is a machine learning technology that uses a single device or system to perform collaborative learning to obtain a federated learning model, and at the same time, saves the data locally (i.e., the privacy-enhancing server 401). For example, the privacy-enhancing server 401 is an ordinary server, and the federated learning model is improved by learning the data on the privacy-enhancing server 401; then, only the updated model parameters are sent to the centralized model on the centralized server (e.g., a server in the cloud, etc.); so that the updated model parameters can be combined with the updated parameters on other devices to obtain a shared federated learning model, which can reduce the amount of data storage on the centralized server and speed up the learning efficiency.

When it is determined that the corresponding enhancement degree of the private data block is the third enhancement degree, a differential privacy algorithm is used to process the original private data in the private data block to obtain the processed data, and based on the processed data and differential privacy Parameter information corresponding to the algorithm generates privacy-enhanced data blocks.

The differential privacy algorithm adds processed interference information to the original private data in the private data block, so that the original private data can be hidden, so that the obtained processed data can enhance data security and reduce the risk of being leaked. . For example, differential privacy algorithms include local differential privacy used by the client, distributed differential privacy perturbed through trusted intermediate nodes, centralized differential privacy completed by the server, and a combination of the above Hybrid differential privacy of at least two algorithms, etc.

Among them, the second enhancement degree is weaker than the first enhancement degree, and the third enhancement degree is weaker than the second enhancement degree.

In some embodiments, the above process of processing private data blocks can be implemented using formula (2):

DF2＝F2(Ekind, k1, k2, ..., km) (2)

Among them, DF2 represents the privacy-enhanced data block obtained after the above processing; DF2 can include: D11, D22, D33,..., Dnn, etc., which is also an ordered sequence, in which the privacy-enhanced data block Dnn Corresponds one-to-one with the privacy data block Dn in the privacy data block DF1, nn represents the preset number, and nn is an integer greater than or equal to 1.

F2 represents the data processing method, Ekind represents the preset enhancement method, k1, k2,..., km respectively represent the parameters corresponding to the preset enhancement method, and m is an integer greater than or equal to 1.

For example, when Ekind is set to 1, the preset enhancement method used is homomorphic encryption. At this time, the parameters needed to be used include: addition homomorphic parameter k1, multiplication homomorphic parameter k2, mixed multiplication homomorphic parameter k3, subtraction homomorphic parameter k4, division homomorphic parameter k5, algebraic homomorphic parameter k6, arithmetic homomorphic parameter k7, etc.

Among them, different parameters can represent the weight values in different homomorphic processing processes in the homomorphic encryption method. For example, if additive homomorphism is used, the corresponding additive homomorphism parameter k1 is 1 and other parameters are 0; if multiplicative homomorphism is used, the corresponding multiplicative homomorphism parameter k2 is 1 and other parameters are 0; and so on.

It should be noted that when the algebraic homomorphism parameter k6 is 1, it means that both additive and multiplicative homomorphisms need to be used for data processing; when the arithmetic homomorphism parameter k7 is 1, it means that both additive and subtractive homomorphisms need to be used. Homomorphisms, multiplication homomorphisms and division homomorphisms.

For another example, when Ekind is set to 2, the preset enhancement method used for characterization is the differential privacy algorithm. At this time, the parameters that need to be used include: the global average of the score k1, the data bias parameter k2, etc.

When Ekind is set to 3, the preset enhancement method used for representation is the federated learning model. At this time, the parameters that need to be used include: the number of jointly processed models k1, the number of rollback wheel intervals k2, the number of pruning wheel intervals k3, etc.

It should be noted that in the pruning round, the convolutional layer is structured pruned, and in the rollback round, the global model is rolled back based on the set model rollback conditions. For example, if the rollback round interval is set to 30 and the pruning round interval is set to 70, the 70th round is the pruning round, and the 100th (i.e., 70+30) round is the rollback round.

During the training process of the federated learning model, it is determined whether the current round is a rollback wheel. If it is a rollback wheel, the model accuracy of the updated federated learning model to be pruned is calculated. If the current wheel is not a rollback wheel, determine whether the current wheel is a pruning wheel. If the current round is a pruning round, the updated federated learning model to be pruned is pruned according to the pruning rate of the convolution layer corresponding to the current round, and the pruned federated learning model to be pruned is determined to be target model.

Step S505: The privacy enhancement server 401 uses the preset public key to encrypt at least one obtained privacy enhancement data block, generates data to be transmitted, and sends the data to be transmitted to the data user device 403.

The data to be transmitted may also include other data blocks except the privacy-enhancing data blocks. Since the enhancement degree of other data blocks is lower than the preset threshold, the corresponding preset enhancement method may be no processing, that is, no processing of other data blocks. Encryption processing, thereby reducing data processing time and improving data processing efficiency.

Step S506: After receiving the data to be transmitted, the data user device 403 decrypts the data to be transmitted using the private key of the data user device 403 to obtain the privacy-enhanced data block and other data blocks except the privacy-enhanced data block.

After receiving the encrypted data packet DF3, the data user device 403 first logs in to the privacy enhancement server 401 deployed to the local client of the data user device 403, then uses the data user device 403's own private key to decrypt DF3, and performs inverse operations through the components provided by the privacy enhancement server 401 to obtain D1, D2, D3, ..., D8. On this basis, the data user device 403 performs statistical analysis and utilization of the privacy data D1, D2, D3, ..., D8.

Step S507: The data user device 403 analyzes other data blocks except the privacy-enhancing data blocks to obtain the data processing results expected by the data user device 403.

It should be noted that since the privacy-enhanced data blocks are data blocks that have been processed in a preset enhancement method, it can be ensured that privacy data blocks with an enhancement degree higher than the preset threshold are not acquired by the data user device 403, thereby reducing the leakage of private data. possibility to improve the security of private data.

In this embodiment, the privacy enhancement server 401 divides the data to be processed into a preset number of privacy data blocks, and each privacy data block can be processed in different ways based on the corresponding enhancement degree of each privacy data block, thus achieving " "On-demand privacy", minimizing data processing processes (such as data encryption and decryption processes, joint operation processes, etc.) and reducing data processing delays can not only ensure the security of private data, but also reduce the risk of weak enhancements. This will eliminate the waste of system resources caused by enhanced processing of private data and improve data processing efficiency.

Moreover, in the above embodiments, "on-demand privacy" is used for different data types in different scenarios, that is, targeted privacy enhancement technology, and the user sets the data that needs to be privacy enhanced (i.e., the data to be processed) Data), and only classify the data to be processed, and use a combination of different privacy enhancement technologies to strengthen the data to be processed in a targeted manner, minimizing processes such as encryption, decryption, and joint operations. It saves computing resources (such as resources for encryption processing of data without privacy enhancement requirements), reduces encryption, decryption, joint operations and other processes, and reduces the system resource occupation ratio and computing power overhead caused by unnecessary privacy enhancement; it can improve The quality of data encryption reduces the risk of sensitive information being leaked when the data user device 403 explores data value.

FIG. 6 shows a block diagram of an electronic device provided by an embodiment of the present application.

As shown in FIG. 6 , the electronic device 600 includes an input device 601 , an input interface 602 , a central processing unit 603 , a memory 604 , an output interface 605 , and an output device 606 . Among them, the input interface 602, the central processing unit 603, the memory 604, and the output interface 605 are connected to each other through the bus 607. The input device 601 and the output device 606 are connected to the bus 607 through the input interface 602 and the output interface 605 respectively, and then to the electronic device 600 to connect other components.

Specifically, the input device 601 receives input information from the outside and transmits the input information to the central processing unit 603 through the input interface 602; the central processing unit 603 processes the input information based on the computer executable instructions stored in the memory 604 to generate output information, temporarily or permanently stores the output information in the memory 604, and then transmits the output information to the output device 606 through the output interface 605; the output device 606 outputs the output information to the outside of the electronic device 600 for user use.

In one embodiment, the electronic device shown in FIG. 6 may include: a memory configured to store a program; and a processor configured to run the program stored in the memory to perform the data processing method described in the above embodiment.

In one embodiment, the electronic device shown in FIG. 6 may be implemented as a data processing system, and the data processing system may include: a memory configured to store a program; a processor configured to run the program stored in the memory. , to perform the data processing method described in the above embodiment.

The above descriptions are only exemplary embodiments of the present application and are not used to limit the protection scope of the present application. Generally speaking, the various embodiments of the present application may be implemented in hardware or special purpose circuitry, software, logic, or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the application is not limited thereto.

Embodiments of the present application may be implemented by a data processor of the mobile device executing computer program instructions, for example in a processor entity, or by hardware, or by a combination of software and hardware. Computer program instructions may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code written in any combination of one or more programming languages or target code.

Any block diagram of a logic flow in the figures of this application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions. Computer programs can be stored on memory. The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as, but not limited to, read only memory (ROM), random access memory (RAM), optical storage devices and systems (digital versatile disc DVD or CD), etc. Computer-readable media may include non-transitory storage media. The data processor may be of any type suitable for the local technical environment, such as, but not limited to, general purpose computers, special purpose computers, microprocessors, digital signal processors (DSP), application specific integrated circuits (ASIC), programmable logic devices (FGPA) and processors based on multi-core processor architecture.

A detailed description of exemplary embodiments of the present application has been provided above, by way of illustrative and non-limiting examples. However, when considered in conjunction with the accompanying drawings and claims, various modifications and adjustments to the above embodiments will be apparent to those skilled in the art without departing from the scope of the present disclosure. Accordingly, the proper scope of the disclosure will be determined from the claims.

Claims (10)

1. A method of data processing, the method comprising:

responding to data to be processed sent by a data owner, dividing the data to be processed into a plurality of privacy data blocks, wherein the enhancement degrees corresponding to the privacy data blocks are different;

processing at least one privacy data block by adopting a preset enhancement mode corresponding to the enhancement degree according to the enhancement degree corresponding to the privacy data block to obtain a privacy enhancement data block;

and sending data to be transmitted to a data user, wherein the data to be transmitted comprises the privacy enhanced data block.

2. The method of claim 1, wherein the dividing the data to be processed into a plurality of private data blocks in response to the data to be processed sent by the data owner comprises:

receiving data to be processed sent by the data owner;

dividing the data to be processed into a preset number of privacy data blocks;

the privacy data block comprises a data number, an enhancement degree and original privacy data, wherein the data number is determined based on the preset number.

3. The method according to claim 2, wherein the enhancement level corresponding to the privacy data block includes a first enhancement level, and the preset enhancement mode includes a homomorphic encryption mode;

Processing at least one privacy data block by adopting a preset enhancement mode corresponding to the enhancement degree according to the enhancement degree corresponding to the privacy data block to obtain a privacy enhanced data block, wherein the processing comprises the following steps:

under the condition that the enhancement degree corresponding to the privacy data block is determined to be a first enhancement degree, encrypting original privacy data in the privacy data block in a homomorphic encryption mode to obtain encrypted data, wherein the first enhancement degree is the highest intensity degree in a plurality of enhancement degrees;

and generating the privacy enhanced data block according to the encrypted data, the homomorphic encryption mode and the corresponding encryption parameters.

4. A method according to claim 3, wherein the corresponding enhancement levels of the privacy data block further comprise a second enhancement level and/or a third enhancement level, the second enhancement level being weaker than the first enhancement level and the third enhancement level being weaker than the second enhancement level, the preset enhancement mode further comprising a federal learning model and/or a differential privacy algorithm;

processing at least one privacy data block by adopting a preset enhancement mode corresponding to the enhancement degree according to the enhancement degree corresponding to the privacy data block to obtain a privacy enhanced data block, wherein the processing comprises the following steps:

Under the condition that the enhancement degree corresponding to the privacy data block is determined to be the second enhancement degree, processing the original privacy data in the privacy data block by adopting a federal learning model to obtain processed data; generating the privacy enhanced data block according to the processed data and the parameter information corresponding to the federal learning model;

and under the condition that the enhancement degree corresponding to the privacy data block is the third enhancement degree, adopting a differential privacy algorithm to process the original privacy data in the privacy data block to obtain processed data, and generating the privacy enhancement data block according to the processed data and parameter information corresponding to the differential privacy algorithm.

5. The method according to any of claims 1 to 4, wherein the number of privacy enhanced data blocks is the same as the number of privacy data blocks or the number of privacy enhanced data blocks is less than the number of privacy data blocks.

6. The method according to any of claims 1 to 4, characterized in that before the sending of the data to be transmitted to the data consumer, the method comprises:

Encrypting the privacy enhanced data block by adopting a preset public key to generate the data to be transmitted; the preset public key is a public key determined by negotiation between the data owner and the data user.

7. A method of data processing, the method comprising:

receiving data to be transmitted sent by a server, wherein the data to be transmitted comprises privacy enhancement data blocks, the privacy enhancement data blocks are data blocks obtained by processing at least one privacy data block by the server according to enhancement degrees corresponding to the privacy data blocks in a preset enhancement mode corresponding to the enhancement degrees, and the privacy data blocks are any one of a plurality of data blocks provided by a data owner;

and carrying out statistical analysis on the data to be transmitted, and determining a data processing result.

8. The method of claim 7, wherein the statistical analysis is performed on the data to be transmitted, and wherein prior to determining the data processing result, the method further comprises:

decrypting the data to be transmitted by adopting a private key of the current equipment to obtain the privacy enhanced data block and other data blocks except the privacy enhanced data block;

Wherein the private key of the current device matches a preset public key used by the server.

9. A privacy enhancing server, comprising:

the dividing module is configured to respond to data to be processed sent by a data owner and divide the data to be processed into a plurality of privacy data blocks, and the enhancement degrees corresponding to the privacy data blocks are different;

the processing module is configured to process at least one privacy data block by adopting a preset enhancement mode corresponding to the enhancement degree according to the enhancement degree corresponding to the privacy data block to obtain a privacy enhancement data block;

and the sending module is configured to send data to be transmitted to a data user, wherein the data to be transmitted comprises the privacy enhanced data block.

10. A data processing system, comprising: a privacy enhancement server, a data owner device and a data consumer device in communication connection;

the privacy enhancing server configured to perform the data processing method of any one of claims 1 to 6;

the data consumer device configured to perform the data processing method of any one of claims 7 to 8;

The data owner device is configured to send data to be processed to the privacy enhancement server, so that the privacy enhancement server processes the data to be processed to generate data to be transmitted.