Data privacy protection method, apparatus, device, medium, and program product

Abstract

The application discloses a data privacy protection method and device, equipment, medium and program product. The method comprises the following steps: obtaining a first data set obtained by adding differential privacy noise to an original data set collected by a smart meter; dividing the first data set into N groups; calculating the covariance matrix of each group; in the case of N>1, rotating the covariance matrix of each group to obtain an orthogonal matrix of each group; randomly exchanging the order of each matrix in the orthogonal matrix of each group to obtain a first matrix of each group; for each group, obtaining a third matrix of the group based on the first matrix and the second matrix of the group; and merging the third matrix of each group to obtain a target matrix, wherein the data in the target matrix is protected privacy protection data. In the process of transmitting the smart meter data collected by the smart grid to the server through the grid communication, the privacy and security of the transmitted data are ensured.

Description

Technical Field

[0001] This application relates to the field of information security, specifically to a data privacy protection method, apparatus, device, medium, and program product. Background Technology

[0002] With the development of communication technology and the emergence of cellular mobile communication, connecting terminals and network devices via wireless channels using cellular wireless networking to enable communication between users has become the primary communication method. In smart grid communication, distributed smart meters can generate data reports and transmit them to remote cloud servers via cellular networks for further analysis. When smart meters collect and transmit data, it is crucial to ensure the privacy, reliability, and security of this data. Data privacy protection has become a valuable issue in the field of data dissemination.

[0003] Currently, when smart grids send the collected smart meter data to the server via grid communication, the smart meter data is not encrypted during transmission, which poses a threat to user privacy. Summary of the Invention

[0004] The purpose of this application is to provide a data privacy protection method, apparatus, device, medium, and program product to ensure the privacy and security of transmitted data during the process of sending collected smart meter data to the server via grid communication in a smart grid.

[0005] The technical solution of this application is as follows:

[0006] Firstly, a data privacy protection method is provided, which includes:

[0007] Obtain the first dataset, wherein the first dataset is the dataset obtained by adding differential privacy noise to the original dataset collected by the smart meter;

[0008] Divide the first dataset into N groups, where N is a positive integer;

[0009] Calculate the covariance matrix for each group;

[0010] When N > 1, the covariance matrix of each group is rotated to obtain the orthogonal matrix of each group;

[0011] Randomly swap the order of the matrices in the orthogonal matrix of each group to obtain the first matrix of each group;

[0012] For each group, a third matrix is ​​obtained based on the first and second matrices of the group, wherein the second matrix is ​​a matrix composed of the data in the first dataset that are located in the group;

[0013] The third matrix of each group is merged to obtain the target matrix, wherein the data in the target matrix is ​​protected privacy-preserving data.

[0014] Secondly, a data privacy protection device is provided, the device comprising:

[0015] The first acquisition module is used to acquire a first dataset, wherein the first dataset is a dataset obtained by adding differential privacy noise to the original dataset collected by the smart meter;

[0016] The grouping module is used to divide the first dataset into N groups, where N is a positive integer;

[0017] The first calculation module is used to calculate the covariance matrix for each group;

[0018] The first determining module is used to rotate the covariance matrix of each group when N>1 to obtain the orthogonal matrix of each group;

[0019] The second determining module is used to randomly swap the order of the matrices in the orthogonal matrix of each group to obtain the first matrix of each group;

[0020] The third determining module is used to obtain a third matrix for each group based on the first matrix and the second matrix of the group, wherein the second matrix is ​​a matrix composed of data located in the group in the first dataset;

[0021] The merging module is used to merge the third matrix of each group to obtain a target matrix, wherein the data in the target matrix is ​​protected privacy-preserving data.

[0022] Thirdly, embodiments of this application provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the steps of any of the data privacy protection methods described in the embodiments of this application.

[0023] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, and when the program or instructions are executed by a processor, the steps of any of the data privacy protection methods described in the embodiments of this application are implemented.

[0024] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the steps of any of the data privacy protection methods described in embodiments of this application.

[0025] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0026] In this embodiment, a first dataset is obtained by adding differential privacy noise to the original dataset collected by the smart meter. The first dataset is then divided into N groups, and the covariance matrix of each group is calculated. When N > 1, the covariance matrix of each group is transformed to obtain an orthogonal matrix of each group. The order of the matrices in the orthogonal matrix of each group is randomly swapped to obtain the first matrix of each group. For each group, a third matrix is ​​obtained based on the first and second matrices of the group. The third matrices of each group are merged to obtain the target matrix. In this way, by grouping data and rotating perturbation, the data stream is disturbed before data transmission to obtain a privacy-protected target matrix. Therefore, during data transmission, data can be transmitted based on the target matrix, thus ensuring the privacy of the transmitted data. Moreover, in the case where the smart meter collecting the data is untrusted, the solution of this embodiment can protect the privacy of the data during data transmission, ensuring the security of the user's intermediate data.

[0027] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0028] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application, and do not constitute an undue limitation of this application.

[0029] Figure 1 This is a flowchart illustrating a data privacy protection method provided in an embodiment of this application;

[0030] Figure 2 This is a schematic diagram of the structure of a data privacy protection device provided in an embodiment of this application;

[0031] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0033] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples consistent with some aspects of this application as detailed in the appended claims.

[0034] As described in the background section, existing technologies suffer from the problem that smart meter data is not protected by privacy encryption during transmission. To address this issue, this application provides a data privacy protection method, apparatus, device, medium, and program product. The method involves obtaining a first dataset by adding differential privacy noise to the original dataset collected by the smart meter. This first dataset is then divided into N groups, and the covariance matrix of each group is calculated. When N > 1, the covariance matrix of each group is transformed to obtain an orthogonal matrix for each group. The order of the matrices in the orthogonal matrix of each group is randomly swapped to obtain a first matrix for each group. For each group, a third matrix is ​​obtained based on the first and second matrices. The third matrices of each group are then merged to obtain a target matrix. Thus, by grouping and rotating the data, the data stream is interfered with before data transmission, resulting in a privacy-protected target matrix. Therefore, during data transmission, the data can be transmitted based on the target matrix, ensuring the privacy of the transmitted data. Moreover, even when the smart meter collecting the data is untrusted, the solution of this application can protect the privacy of the data during transmission, ensuring the security of the user's intermediate data.

[0035] The data privacy protection method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0036] Figure 1 This is a flowchart illustrating a data privacy protection method provided in an embodiment of this application. The execution entity of this data privacy protection method can be a server.

[0037] like Figure 1 As shown, the data privacy protection method provided in this application embodiment may include steps 110-170.

[0038] Step 110: Obtain the first dataset.

[0039] The first dataset can be the dataset obtained by adding differential privacy noise to the original dataset collected by the smart meter.

[0040] The original dataset is a collection of data collected by smart meters.

[0041] In existing technologies, there are schemes that add differential privacy noise to the original dataset. However, the drawback of this scheme is that each query consumes a privacy budget. If the privacy budget allocated to a query is larger, its query results will be more accurate; however, this increases the privacy budget and imposes limitations on query processing. Conversely, if the privacy budget allocated to a query is too small, the added noise will be very large, resulting in poor query results and data utility. Therefore, existing schemes for adding differential privacy noise to the original dataset rely on the privacy budget.

[0042] To address the aforementioned issues, this application proposes a novel differential privacy protection scheme based on the hierarchical relationship of data items. Specifically, prior to step 110, the method described above may further include:

[0043] Obtain the raw dataset, which contains at least one raw data collected by the smart meter. Each raw data has at least one attribute information, and the value of each attribute information corresponding to each raw data is not exactly the same.

[0044] For each attribute, calculate the differential privacy perturbation data corresponding to each value of the attribute to obtain the first dataset.

[0045] In some embodiments of this application, the raw dataset contains at least one raw data collected by a smart meter, each raw data having at least one attribute information, and the values ​​of each attribute information corresponding to each raw data are not exactly the same.

[0046] In one example, there are smart meters A, B, and C. The raw data in the dataset consists of data collected by the sensors of each smart meter. The data collected by the sensors of each smart meter includes electricity consumption, voltage, and current. Each piece of raw data has three attribute information: electricity consumption, current, and voltage. For each smart meter, each attribute information has a corresponding value. For example, for smart meter A, the value of its electricity consumption attribute is 10 kWh, its voltage attribute is 220V, and its current attribute is 21A.

[0047] In some embodiments of this application, for each attribute information, the data after adding noise to each value of the attribute information, i.e., differential privacy perturbation data, can be calculated to obtain the first dataset.

[0048] In the embodiments of this application, privacy protection can be achieved by adding differential privacy noise to the original dataset collected by the smart meter. In this way, noise is added to the original data during the data privacy addition stage, ensuring the privacy and security of the original data.

[0049] In some embodiments of this application, for each attribute information, in order to accurately calculate the differential privacy perturbation data corresponding to each value of the attribute information, the calculation of the differential privacy perturbation data corresponding to each value of the attribute information may specifically include:

[0050] For each attribute information, the differential privacy perturbation data corresponding to each value of the attribute information is calculated according to the following formula (1):

[0051]

[0052] in, This refers to the differential privacy perturbation data corresponding to the value of the first attribute information of the first raw data in the original dataset. Let Δf be the value of the first attribute information of the first raw data, and Δf be the sensitivity of the first attribute information. Δf = ||A j (max)-A j (min)||,A j (max) represents the maximum value of the first attribute information, A j (min) is the minimum value of the first attribute information, ε is the privacy parameter, which is a constant, the first original data is any original data in the original dataset, and the first attribute information is any attribute information in at least one attribute information of the first original data.

[0053] It should be noted that engineers can continuously adjust the privacy parameter ε to determine the privacy parameter ε used in the final formula (1).

[0054] In the embodiments of this application, the differential privacy perturbation data corresponding to each value of each attribute information can be accurately calculated using formula (1).

[0055] Step 120: Divide the first dataset into N groups.

[0056] Where N is a positive integer.

[0057] In some embodiments of this application, in order to accurately divide the first dataset into N groups, step 120 may specifically include:

[0058] S1. Randomly select the first data from the first dataset.

[0059] The first data can be any data in the first dataset.

[0060] In some embodiments of this application, data can be obtained from the first dataset O. priv Randomly select a data point (the first data point) Xi.

[0061] S2. Select the K-1 data points that are closest to the first data point from the first dataset to obtain the first group.

[0062] In some embodiments of this application, from the first dataset O priv Select the K-1 data points that are closest to the first data point Xi to obtain the first group Gi.

[0063] The K mentioned above is a positive integer.

[0064] S3. Delete the data in the first group of the first dataset to obtain the second dataset.

[0065] The second dataset can be the dataset obtained by deleting the data from the first group in the first dataset.

[0066] S4. Update the second dataset to the first dataset.

[0067] Return to execute S1-S4 until the data in the updated first dataset is empty, resulting in N groups.

[0068] In some embodiments of this application, the second dataset is updated to the first dataset, and then S1-S4 are executed in a loop until the data in the updated first dataset is empty, thus obtaining N groups.

[0069] In the embodiments of this application, the process involves: S1. Randomly selecting a first data point from a first dataset. S2. Selecting the K-1 data points closest to the first data point from the first dataset to obtain a first group. S3. Deleting data from the first group in the first dataset to obtain a second dataset. S4. Updating the second dataset to the first dataset. The process of S1-S4 is repeated until the updated first dataset is empty, thus obtaining N groups precisely.

[0070] Step 130: Calculate the covariance matrix for each group.

[0071] Step 140: When N > 1, rotate the covariance matrix of each group to obtain the orthogonal matrix of each group.

[0072] In some embodiments of this application, in order to accurately obtain the orthogonal matrix of each group, step 140 may specifically include:

[0073] The covariance matrix of each group is rotated according to the following formula (2) to obtain the orthogonal matrix of each group:

[0074] C(Gi) = P(Gi) × Δ(Gi) × P(Gi) T (2)

[0075] Where C(Gi) is the covariance matrix of the first group, and P(Gi) is the orthogonality matrix of the first group. T Let Δ(Gi) be the transpose of the orthogonal matrix of the first group, and let Δ(Gi) be the matrix composed of the eigenvalues ​​of the covariance matrix of the first group. The first group is any one of the N groups.

[0076] It should be noted that the covariance matrix C(Gi) can be decomposed using formula (2) to determine the eigenvectors of each covariance matrix. Here, P(Gi) is the matrix composed of the eigenvectors of the covariance matrix C(Gi). Since the matrix is ​​positive semi-definite, the corresponding eigenvectors form an orthogonal axis system. Therefore, the resulting matrix P(Gi) of the eigenvectors corresponding to the specific covariance matrix of the homogeneous group has the property of an orthogonal matrix, where the rows and columns are orthogonal. Thus, P(Gi) maintains the relationship P(Gi)×P(Gi). T =P(Gi) T ×P(Gi)=I, where I is the identity matrix. This means that P(Gi) of a specific homogeneous group has all the properties of a rotation matrix, and also proves that the resulting matrix is ​​still an orthogonal matrix, although the order of the rows or columns of the orthogonal matrix has changed, that is, the subsequent first matrix and the target matrix are also orthogonal matrices.

[0077] In the embodiments of this application, the orthogonal matrix of each group can be accurately obtained by the above formula (2).

[0078] Step 150: Randomly swap the order of the matrices in the orthogonal matrix of each group to obtain the first matrix of each group.

[0079] The first matrix can be obtained by randomly swapping the order of the matrices in the orthogonal matrix of each group. Since the orthogonal matrix is ​​composed of eigenvectors obtained by decomposing the covariance matrix, each eigenvector can be regarded as a submatrix or column vector of the orthogonal matrix. Therefore, each matrix in the orthogonal matrix refers to each column vector in the orthogonal matrix.

[0080] In some embodiments of this application, for each group, the order of the matrices in the orthogonal matrix of that group can be randomly swapped to obtain the first matrix RP(Gi) of that group.

[0081] Step 160: For each group, obtain the third matrix of the group based on the first and second matrices of the group.

[0082] For each group, the second matrix of that group can be a matrix composed of the data in the first dataset that are located in that group. Specifically, the second matrix is ​​constructed with the attributes of the data in the first dataset that are located in that group as columns and the data points corresponding to the attributes as rows.

[0083] In some embodiments of this application, step 160 may specifically include:

[0084] For each group, the third matrix of the group is obtained based on the first and second matrices of the group according to the following formula (3):

[0085] D p (Gi) = (RP(Gi) × D(Gi)) T ) T (3)

[0086] Among them, D p (Gi) is the third matrix of the first group, RP(Gi) is the first matrix of the first group, and D(Gi) is the matrix composed of the data of the first group. The first group is any group among the N groups.

[0087] Step 170: Merge the third matrix of each group to obtain the target matrix.

[0088] The target matrix can be a matrix composed of the final privacy-protected data, meaning that the data in the target matrix is ​​protected privacy-protected data.

[0089] In some embodiments of this application, in order to accurately obtain the target matrix, step 170 may specifically include:

[0090] The third matrix of each group is merged to obtain the fourth matrix;

[0091] Randomly swap the order of the matrices in the fourth matrix to obtain the target matrix.

[0092] The fourth matrix can be the matrix obtained by merging the third matrices of each group.

[0093] In some embodiments of this application, the third matrix of each group can be merged according to the following formula (4) to obtain the fourth matrix:

[0094]

[0095] in, This is the fourth matrix.

[0096] Then, the order of the matrices in the fourth matrix is ​​randomly swapped to obtain the target matrix D as shown in formula (5). p :

[0097]

[0098] in, for Each matrix in the matrix is ​​i-1,2,…t.

[0099] In the embodiments of this application, by merging the third matrix of each group to obtain the fourth matrix, and then randomly swapping the order of each matrix in the fourth matrix, the target matrix composed of privacy-protected data can be accurately obtained.

[0100] In some embodiments of this application, the properties of data grouping and rotational perturbation, combined with the efficiency of grouping and the accuracy of rotational perturbation, are used to disrupt the data flow of the Internet of Things (IoT) before the general storage phase (i.e., the data transmission phase). First, data with added differential privacy noise is clustered into multiple homogeneous groups. Then, privacy-preserving data processing is performed on fixed-size data blocks. Next, covariance matrix statistics are generated for each group. Then, the covariance matrix is ​​used to generate the corresponding geometric rotation group. After rotational perturbation, the groups are merged, and the tuples are randomly shuffled and released.

[0101] It should be noted that the data privacy protection method provided in this application embodiment can be executed by a data privacy protection device or a control module in the data privacy protection device for executing the data privacy protection method.

[0102] Based on the same inventive concept as the aforementioned data privacy protection method, this application also provides a data privacy protection device. The following is in conjunction with… Figure 2 The data privacy protection device provided in the embodiments of this application will be described in detail.

[0103] Figure 2 This is a schematic diagram illustrating the structure of a data privacy protection device according to an exemplary embodiment.

[0104] like Figure 2 As shown, the data privacy protection device 200 may include:

[0105] The first acquisition module 210 is used to acquire a first dataset, wherein the first dataset is a dataset obtained by adding differential privacy noise to the original dataset collected by the smart meter;

[0106] Grouping module 220 is used to divide the first dataset into N groups, where N is a positive integer;

[0107] The first calculation module 230 is used to calculate the covariance matrix of each group;

[0108] The first determining module 240 is used to rotate the covariance matrix of each group when N>1 to obtain the orthogonal matrix of each group.

[0109] The second determining module 250 is used to randomly swap the order of the matrices in the orthogonal matrix of each group to obtain the first matrix of each group;

[0110] The third determining module 260 is used to obtain a third matrix for each group based on the first matrix and the second matrix of the group, wherein the second matrix is ​​a matrix composed of data located in the group in the first dataset;

[0111] The merging module 270 is used to merge the third matrix of each group to obtain a target matrix, wherein the data in the target matrix is ​​protected privacy-preserving data.

[0112] The first dataset is obtained by adding differential privacy noise to the original dataset collected by the smart meter. The first dataset is then divided into N groups, and the covariance matrix of each group is calculated. When N>1, the covariance matrix of each group is transformed to obtain the orthogonal matrix of each group. The order of the matrices in the orthogonal matrix of each group is randomly swapped to obtain the first matrix of each group. For each group, the third matrix of the group is obtained based on the first and second matrices of the group. The third matrices of each group are merged to obtain the target matrix. In this way, by grouping data and rotating perturbation, the data flow is disturbed before data transmission to obtain the privacy-protected target matrix. Therefore, during data transmission, the data can be transmitted based on the target matrix, thus ensuring the privacy of the transmitted data. Moreover, in the case where the smart meter collecting the data is untrusted, the solution of this application can protect the privacy of the data during data transmission and ensure the security of the user's intermediate data.

[0113] In some embodiments of this application, the apparatus described above may further include:

[0114] The second acquisition module is used to acquire the original dataset, wherein the original dataset contains at least one original data collected by the smart meter, each original data has at least one attribute information, and the value of each attribute information corresponding to each original data is not exactly the same;

[0115] The second calculation module is used to calculate the differential privacy perturbation data corresponding to each value of the attribute information for each attribute information, so as to obtain the first dataset.

[0116] In some embodiments of this application, the second computing module is specifically used for:

[0117] For each attribute information, the differential privacy perturbation data corresponding to each value of the attribute information is calculated according to the following formula:

[0118]

[0119] in, The differential privacy perturbation data corresponds to the value of the first attribute information of the first original data in the original dataset. Let Δf be the value of the first attribute information of the first original data, and Δf be the sensitivity of the first attribute information, where Δf = ||A| j (max)-A j (min)||,A j (max) represents the maximum value of the first attribute information, A j(min) is the minimum value of the first attribute information, ε is the privacy parameter, which is a constant, the first original data is any original data in the original dataset, and the first attribute information is any attribute information in at least one attribute information of the first original data.

[0120] In some embodiments of this application, the grouping module 220 is specifically used for:

[0121] S1. Randomly select first data from the first dataset, wherein the first data is any data in the first dataset;

[0122] S2. Select the K-1 data points that are closest to the first data from the first dataset to obtain the first group, where K is a positive integer;

[0123] S3. Delete the data in the first group of the first dataset to obtain the second dataset;

[0124] S4. Update the second dataset to the first dataset;

[0125] Return to execute S1-S4 until the data in the updated first dataset is empty, resulting in N groups.

[0126] In some embodiments of this application, the second determining module 250 is specifically used for:

[0127] The covariance matrix of each group is rotated according to the following formula to obtain the orthogonal matrix of each group:

[0128] C(Gi) = P(Gi) × Δ(Gi) × P(Gi) T

[0129] Where C(Gi) is the covariance matrix of the first group, and P(Gi) is the orthogonality matrix of the first group. T Let Δ(Gi) be the transpose of the orthogonal matrix of the first group, and let Δ(Gi) be the matrix composed of the eigenvalues ​​of the covariance matrix. The first group is any one of the N groups.

[0130] In some embodiments of this application, the merging module 270 is specifically used for:

[0131] The third matrix of each group is merged to obtain the fourth matrix;

[0132] The target matrix is ​​obtained by randomly swapping the order of the matrices in the fourth matrix.

[0133] The data privacy protection device provided in this application embodiment can be used to execute the data privacy protection methods provided in the above method embodiments. Its implementation principle and technical effect are similar, and will not be described in detail here for the sake of brevity.

[0134] Based on the same inventive concept, this application also provides an electronic device.

[0135] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 3 As shown, the electronic device may include a processor 301 and a memory 302 storing computer programs or instructions.

[0136] Specifically, the processor 301 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0137] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory. Memory may include read-only memory (ROM), random-access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, a memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described in the data privacy protection methods provided in the above embodiments.

[0138] The processor 301 implements any of the data privacy protection methods described in the above embodiments by reading and executing computer program instructions stored in the memory 302.

[0139] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0140] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or devices in the embodiments of the present invention.

[0141] Bus 310 includes hardware, software, or both, that couples components of an electronic device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.

[0142] The electronic device can execute the data privacy protection method in the embodiments of the present invention, thereby achieving... Figure 1 Describe the data privacy protection methods.

[0143] Furthermore, in conjunction with the data privacy protection methods described in the above embodiments, this invention can be implemented using a readable storage medium. This readable storage medium stores program instructions, which, when executed by a processor, implement any of the data privacy protection methods described in the above embodiments.

[0144] In addition, in conjunction with the data privacy protection methods in the above embodiments, the present invention can provide a computer program product in which the instructions are executed by the processor of an electronic device, causing the electronic device to perform any of the data privacy protection methods in the above embodiments.

[0145] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0146] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0147] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0148] The aspects of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0149] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A data privacy protection method, characterized in that, The method includes: Obtain the first dataset, wherein the first dataset is the dataset obtained by adding differential privacy noise to the original dataset collected by the smart meter; Divide the first dataset into N groups, where N is a positive integer; Calculate the covariance matrix for each group; When N > 1, the covariance matrix of each group is rotated to obtain the orthogonal matrix of each group; Randomly swap the column vectors in the orthogonal matrix of each group to obtain the first matrix of each group; For each group, a third matrix is ​​obtained based on the first and second matrices of the group, wherein the second matrix is ​​composed of the attributes of the data in the first dataset located in the group as columns and the data points corresponding to the attributes as rows; The third matrix of each group is merged to obtain the target matrix, wherein the data in the target matrix is ​​protected privacy-preserving data.

2. The method according to claim 1, characterized in that, Prior to obtaining the first dataset, the method further includes: Obtain the original dataset, wherein the original dataset contains at least one original data collected by the smart meter, each original data has at least one attribute information, and the value of each attribute information corresponding to each original data is not exactly the same; For each attribute information, calculate the differential privacy perturbation data corresponding to each value of the attribute information to obtain the first dataset.

3. The method according to claim 2, characterized in that, The step of calculating the differential privacy perturbation data corresponding to each value of each attribute information includes: For each attribute information, the differential privacy perturbation data corresponding to each value of the attribute information is calculated according to the following formula: in, The differential privacy perturbation data corresponds to the value of the first attribute information of the first original data in the original dataset. The value of the first attribute information of the first original data. The sensitivity of the first attribute information. , The maximum value of the first attribute information. The minimum value of the first attribute information. Here, is a privacy parameter, is a constant, the first original data is any original data in the original dataset, and the first attribute information is any attribute information in at least one attribute information of the first original data.

4. The method according to claim 1, characterized in that, The step of dividing the first dataset into N groups includes: S1. Randomly select first data from the first dataset, wherein the first data is any data in the first dataset; S2. Select the K-1 data points that are closest to the first data from the first dataset to obtain the first group, where K is a positive integer; S3. Delete the data in the first group of the first dataset to obtain the second dataset; S4. Update the second dataset to the first dataset; Return to execute S1-S4 until the data in the updated first dataset is empty, resulting in N groups.

5. The method according to claim 1, characterized in that, The step of transforming the covariance matrix of each group to obtain the orthogonal matrix of each group includes: The covariance matrix of each group is rotated according to the following formula to obtain the orthogonal matrix of each group: in, The covariance matrix of the first group is... Let be the orthogonal matrix of the first group. Let be the transpose of the orthogonal matrix of the first group. The first group is any one of the N groups, and the matrix is ​​composed of the eigenvalues ​​of the covariance matrix.

6. The method according to claim 1, characterized in that, The step of merging the third matrix of each group to obtain the target matrix includes: The third matrix of each group is merged to obtain the fourth matrix; The target matrix is ​​obtained by randomly swapping the order of the matrices in the fourth matrix.

7. A data privacy protection device, characterized in that, The device includes: The first acquisition module is used to acquire a first dataset, wherein the first dataset is a dataset obtained by adding differential privacy noise to the original dataset collected by the smart meter; The grouping module is used to divide the first dataset into N groups, where N is a positive integer; The first calculation module is used to calculate the covariance matrix for each group; The first determining module is used to rotate the covariance matrix of each group when N>1 to obtain the orthogonal matrix of each group; The second determining module is used to randomly swap the order of column vectors in the orthogonal matrix of each group to obtain the first matrix of each group; The third determining module is used to obtain a third matrix for each group based on the first matrix and the second matrix of the group, wherein the second matrix is ​​composed of the attributes of the data in the first dataset located in the group as columns and the data points corresponding to the attributes as rows; The merging module is used to merge the third matrix of each group to obtain a target matrix, wherein the data in the target matrix is ​​protected privacy-preserving data.

8. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the data privacy protection method as described in any one of claims 1-6.

9. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the data privacy protection method as described in any one of claims 1-6.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the steps of the data privacy protection method as described in any one of claims 1-6.

Images